Release 2021.04.11

Closes: https://github.com/yt-dlp/yt-dlp/issues/99 https://github.com/yt-dlp/yt-dlp/issues/102

.gitattributes

@@ -0,0 +1 @@
+Makefile* text whitespace=-tab-in-indent

.github/ISSUE_TEMPLATE/1_broken_site.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.19. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.04.03. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/yt-dlp/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support
-- [ ] I've verified that I'm running yt-dlp version **2021.02.19**
+- [ ] I've verified that I'm running yt-dlp version **2021.04.03**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar issues including closed ones
@@ -44,7 +44,7 @@ Add the `-v` flag to your command line you run yt-dlp with (`yt-dlp -v <your com
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.02.19
+ [debug] yt-dlp version 2021.04.03
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/2_site_support_request.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.19. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.04.03. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that site you are requesting is not dedicated to copyright infringement, see https://github.com/yt-dlp/yt-dlp. yt-dlp does not support such sites. In order for site support request to be accepted all provided example URLs should not violate any copyrights.
 - Search the bugtracker for similar site support requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -29,7 +29,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a new site support request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.19**
+- [ ] I've verified that I'm running yt-dlp version **2021.04.03**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that none of provided URLs violate any copyrights
 - [ ] I've searched the bugtracker for similar site support requests including closed ones

.github/ISSUE_TEMPLATE/3_site_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.19. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.04.03. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar site feature requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a site feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.19**
+- [ ] I've verified that I'm running yt-dlp version **2021.04.03**
 - [ ] I've searched the bugtracker for similar site feature requests including closed ones
 
 

.github/ISSUE_TEMPLATE/4_bug_report.md

@@ -21,7 +21,7 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.19. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.04.03. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Make sure that all provided video/audio/playlist URLs (if any) are alive and playable in a browser.
 - Make sure that all URLs and arguments with special characters are properly quoted or escaped as explained in https://github.com/yt-dlp/yt-dlp.
 - Search the bugtracker for similar issues: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
@@ -30,7 +30,7 @@ Carefully read and work through this check list in order to prevent the most com
 -->
 
 - [ ] I'm reporting a broken site support issue
-- [ ] I've verified that I'm running yt-dlp version **2021.02.19**
+- [ ] I've verified that I'm running yt-dlp version **2021.04.03**
 - [ ] I've checked that all provided URLs are alive and playable in a browser
 - [ ] I've checked that all URLs and arguments with special characters are properly quoted or escaped
 - [ ] I've searched the bugtracker for similar bug reports including closed ones
@@ -46,7 +46,7 @@ Add the `-v` flag to your command line you run yt-dlp with (`yt-dlp -v <your com
  [debug] User config: []
  [debug] Command-line args: [u'-v', u'http://www.youtube.com/watch?v=BaW_jenozKcj']
  [debug] Encodings: locale cp1251, fs mbcs, out cp866, pref cp1251
- [debug] yt-dlp version 2021.02.19
+ [debug] yt-dlp version 2021.04.03
  [debug] Python version 2.7.11 - Windows-2003Server-5.2.3790-SP2
  [debug] exe versions: ffmpeg N-75573-g1d0487f, ffprobe N-75573-g1d0487f, rtmpdump 2.4
  [debug] Proxy map: {}

.github/ISSUE_TEMPLATE/5_feature_request.md

@@ -21,13 +21,13 @@ assignees: ''
 
 <!--
 Carefully read and work through this check list in order to prevent the most common mistakes and misuse of yt-dlp:
-- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.02.19. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
+- First of, make sure you are using the latest version of yt-dlp. Run `yt-dlp --version` and ensure your version is 2021.04.03. If it's not, see https://github.com/yt-dlp/yt-dlp on how to update. Issues with outdated version will be REJECTED.
 - Search the bugtracker for similar feature requests: https://github.com/yt-dlp/yt-dlp. DO NOT post duplicates.
 - Finally, put x into all relevant boxes like this [x] (Dont forget to delete the empty space)
 -->
 
 - [ ] I'm reporting a feature request
-- [ ] I've verified that I'm running yt-dlp version **2021.02.19**
+- [ ] I've verified that I'm running yt-dlp version **2021.04.03**
 - [ ] I've searched the bugtracker for similar feature requests including closed ones
 
 

.github/workflows/core.yml

@@ -3,7 +3,7 @@ on: [push, pull_request]
 jobs:
   tests:
     name: Core Tests
-    if: "!contains(github.event.head_commit.message, 'ci skip all')"
+    if: "!contains(github.event.head_commit.message, 'ci skip')"
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: true

.github/workflows/download.yml

@@ -3,7 +3,7 @@ on: [push, pull_request]
 jobs:
   tests:
     name: Download Tests
-    if: "!contains(github.event.head_commit.message, 'ci skip dl') && !contains(github.event.head_commit.message, 'ci skip all')"
+    if: "contains(github.event.head_commit.message, 'ci run dl')"
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: true

.gitignore

@@ -8,6 +8,7 @@ dist/
 zip/
 tmp/
 venv/
+completions/
 
 # Misc
 *~
@@ -24,7 +25,9 @@ updates_key.pem
 *.class
 
 # Generated
+AUTHORS
 README.txt
+.mailmap
 *.1
 *.bash-completion
 *.fish
@@ -34,8 +37,9 @@ README.txt
 *.spec
 
 # Binary
-youtube-dl
-youtube-dlc
+/youtube-dl
+/youtube-dlc
+/yt-dlp
 yt-dlp.zip
 *.exe
 
@@ -50,12 +54,15 @@ yt-dlp.zip
 *.m4v
 *.mp3
 *.3gp
+*.webm
 *.wav
 *.ape
 *.mkv
 *.swf
 *.part
+*.part-*
 *.ytdl
+*.dump
 *.frag
 *.frag.urls
 *.aria2

.readthedocs.yml

@@ -20,4 +20,3 @@ python:
     version: 3
     install:
     - requirements: docs/requirements.txt
-    - requirements: requirements.txt

.travis.yml.disabled

@@ -1,38 +0,0 @@
-language: python
-python:
-  - "2.6"
-  - "2.7"
-  - "3.2"
-  - "3.3"
-  - "3.4"
-  - "3.5"
-  - "3.6"
-  - "pypy"
-  - "pypy3"
-dist: trusty
-env:
-  - YTDL_TEST_SET=core
-jobs:
-  include:
-    - python: 3.7
-      dist: xenial
-      env: YTDL_TEST_SET=core
-    - python: 3.8
-      dist: xenial
-      env: YTDL_TEST_SET=core
-    - python: 3.8-dev
-      dist: xenial
-      env: YTDL_TEST_SET=core
-    - env: JYTHON=true; YTDL_TEST_SET=core
-    - name: flake8
-      python: 3.8
-      dist: xenial
-      install: pip install flake8
-      script: flake8 .
-  fast_finish: true
-  allow_failures:
-    - env: YTDL_TEST_SET=download
-    - env: JYTHON=true; YTDL_TEST_SET=core
-before_install:
-  - if [ "$JYTHON" == "true" ]; then ./devscripts/install_jython.sh; export PATH="$HOME/jython/bin:$PATH"; fi
-script: ./devscripts/run_tests.sh

CONTRIBUTORS

@@ -1,5 +1,6 @@
 pukkandan (owner)
 shirt-dev (collaborator)
+colethedj (collaborator)
 h-h-h-h
 pauldubois98
 nixxo
@@ -21,5 +22,19 @@ nao20010128nao
 kurumigi
 tsukumi
 bbepis
+animelover1984
 Pccode66
-Ashish
+Ashish0804
+RobinD42
+hseg
+DennyDai
+codeasashu
+teesid
+kevinoconnor7
+damianoamatruda
+2ShedsJackson
+CXwudi
+xtkoba
+llacb47
+hheimbuerger
+B0pol

Changelog.md

@@ -6,8 +6,10 @@
 * Run `make doc`
 * Update Changelog.md and CONTRIBUTORS
 * Change "Merged with ytdl" version in Readme.md if needed
+* Add new/fixed extractors in "new features" section of Readme.md
 * Commit to master as `Release <version>`
-* Push to origin/release - build task will now run
+* Push to origin/release using `git push origin master:release`
+    build task will now run
 * Update version.py using devscripts\update-version.py
 * Run `make issuetemplates`
 * Commit to master as `[version] update :ci skip all`
@@ -17,28 +19,188 @@
 -->
 
 
+### 2021.04.11
+* Add option `--convert-thumbnails` (only jpg currently supported)
+* Format selector `mergeall` to download and merge all formats
+* Pass any field to `--exec` using similar syntax to output template
+* Choose downloader for each protocol using `--downloader PROTO:NAME`
+    * Alias `--downloader` for `--external-downloader`
+    * Added `native` as an option for the downloader
+* Merge youtube-dl: Upto [commit/4fb25ff](https://github.com/ytdl-org/youtube-dl/commit/4fb25ff5a3be5206bb72e5c4046715b1529fb2c7) (except vimeo)
+* [DiscoveryPlusIndia] Add DiscoveryPlusIndiaShowIE by [Ashish0804](https://github.com/Ashish0804)
+* [NFHSNetwork] Add extractor by [llacb47](https://github.com/llacb47)
+* [nebula] Add extractor (watchnebula.com) by [hheimbuerger](https://github.com/hheimbuerger)
+* [nitter] Fix extraction of reply tweets and update instance list by [B0pol](https://github.com/B0pol)
+* [nitter] Fix thumbnails by [B0pol](https://github.com/B0pol)
+* [youtube] Fix thumbnail URL
+* [youtube] Parse API parameters from initial webpage by [colethedj](https://github.com/colethedj)
+* [youtube] Extract comments' approximate timestamp by [colethedj](https://github.com/colethedj)
+* [youtube] Fix `\_extract_alerts`
+* [bilibili] Fix uploader
+* [utils] Add `datetime_from_str` and `datetime_add_months` by [colethedj](https://github.com/colethedj)
+* Run some `postprocessors` before actual download
+* Improve argument parsing for `-P`, `-o`, `-S`
+* Fix some `m3u8` not obeying `--allow-unplayable-formats`
+* Fix default of `dynamic_mpd`
+* Deprecate `--all-formats`, `--include-ads`, `--hls-prefer-native`, `--hls-prefer-ffmpeg`
+* [documentation] Improvements
+
+### 2021.04.03
+* Merge youtube-dl: Upto [commit/654b4f4](https://github.com/ytdl-org/youtube-dl/commit/654b4f4ff2718f38b3182c1188c5d569c14cc70a)
+* Ability to set a specific field in the file's metadata using `--parse-metadata`
+* Ability to select n'th best format like `-f bv*.2`
+* [DiscoveryPlus] Add discoveryplus.in
+* [la7] Add podcasts and podcast playlists by [nixxo](https://github.com/nixxo)
+* [mildom] Update extractor with current proxy by [nao20010128nao](https://github.com/nao20010128nao)
+* [ard:mediathek] Fix video id extraction
+* [generic] Detect Invidious' link element
+* [youtube] Show premium state in `availability` by [colethedj](https://github.com/colethedj)
+* [viewsource] Add extractor to handle `view-source:`
+* [sponskrub] Run before embedding thumbnail
+* [documentation] Improve `--parse-metadata` documentation
+
+
+### 2021.03.24.1
+* Revert [commit/8562218](https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf)
+
+### 2021.03.24
+* Merge youtube-dl: Upto 2021.03.25 ([commit/8562218](https://github.com/ytdl-org/youtube-dl/commit/8562218350a79d4709da8593bb0c538aa0824acf))
+* Parse metadata from multiple fields using `--parse-metadata`
+* Ability to load playlist infojson using `--load-info-json`
+* Write current epoch to infojson when using `--no-clean-infojson`
+* [youtube_live_chat] fix bug when trying to set cookies
+* [niconico] Fix for when logged in by [CXwudi](https://github.com/CXwudi) and [xtkoba](https://github.com/xtkoba)
+* [linuxacadamy] Fix login
+
+
+### 2021.03.21
+* Merge youtube-dl: Upto [commit/7e79ba7](https://github.com/ytdl-org/youtube-dl/commit/7e79ba7dd6e6649dd2ce3a74004b2044f2182881)
+* Option `--no-clean-infojson` to keep private keys in the infojson
+* [aria2c] Support retry/abort unavailable fragments by [damianoamatruda](https://github.com/damianoamatruda)
+* [aria2c] Better default arguments
+* [movefiles] Fix bugs and make more robust
+* [formatSort] Fix `quality` being ignored
+* [splitchapters] Fix for older ffmpeg
+* [sponskrub] Pass proxy to sponskrub
+* Make sure `post_hook` gets the final filename
+* Recursively remove any private keys from infojson
+* Embed video URL metadata inside `mp4` by [damianoamatruda](https://github.com/damianoamatruda) and [pukkandan](https://github.com/pukkandan)
+* Merge `webm` formats into `mkv` if thumbnails are to be embedded by [damianoamatruda](https://github.com/damianoamatruda)
+* Use headers and cookies when downloading subtitles by [damianoamatruda](https://github.com/damianoamatruda)
+* Parse resolution in info dictionary by [damianoamatruda](https://github.com/damianoamatruda)
+* More consistent warning messages by [damianoamatruda](https://github.com/damianoamatruda) and [pukkandan](https://github.com/pukkandan)
+* [documentation] Add deprecated options and aliases in readme
+* [documentation] Fix some minor mistakes
+
+* [niconico] Partial fix adapted from [animelover1984/youtube-dl@b5eff52](https://github.com/animelover1984/youtube-dl/commit/b5eff52dd9ed5565672ea1694b38c9296db3fade) (login and smile formats still don't work)
+* [niconico] Add user extractor by [animelover1984](https://github.com/animelover1984)
+* [bilibili] Add anthology support by [animelover1984](https://github.com/animelover1984)
+* [amcnetworks] Fix extractor by [2ShedsJackson](https://github.com/2ShedsJackson)
+* [stitcher] Merge from youtube-dl by [nixxo](https://github.com/nixxo)
+* [rcs] Improved extraction by [nixxo](https://github.com/nixxo)
+* [linuxacadamy] Improve regex
+* [youtube] Show if video is `private`, `unlisted` etc in info (`availability`) by [colethedj](https://github.com/colethedj) and [pukkandan](https://github.com/pukkandan)
+* [youtube] bugfix for channel playlist extraction
+* [nbc] Improve metadata extraction by [2ShedsJackson](https://github.com/2ShedsJackson)
+
+
+### 2021.03.15
+* **Split video by chapters**: using option `--split-chapters`
+    * The output file of the split files can be set with `-o`/`-P` using the prefix `chapter:`
+    * Additional keys `section_title`, `section_number`, `section_start`, `section_end` are available in the output template
+* **Parallel fragment downloads** by [shirt](https://github.com/shirt-dev)
+    * Use option `--concurrent-fragments` (`-N`) to set the number of threads (default 1)
+* Merge youtube-dl: Upto [commit/3be0980](https://github.com/ytdl-org/youtube-dl/commit/3be098010f667b14075e3dfad1e74e5e2becc8ea)
+* [zee5] Add Show Extractor by [Ashish0804](https://github.com/Ashish0804) and [pukkandan](https://github.com/pukkandan)
+* [rai] fix drm check [nixxo](https://github.com/nixxo)
+* [wimtv] Add extractor by [nixxo](https://github.com/nixxo)
+* [mtv] Add mtv.it and extract series metadata by [nixxo](https://github.com/nixxo)
+* [pluto.tv] Add extractor by [kevinoconnor7](https://github.com/kevinoconnor7)
+* [youtube] Rewrite comment extraction by [colethedj](https://github.com/colethedj)
+* [embedthumbnail] Set mtime correctly
+* Refactor some postprocessor/downloader code by [pukkandan](https://github.com/pukkandan) and [shirt](https://github.com/shirt-dev)
+
+
+### 2021.03.07
+* [youtube] Fix history, mixes, community pages and trending by [pukkandan](https://github.com/pukkandan) and [colethedj](https://github.com/colethedj)
+* [youtube] Fix private feeds/playlists on multi-channel accounts by [colethedj](https://github.com/colethedj)
+* [youtube] Extract alerts from continuation by [colethedj](https://github.com/colethedj)
+* [cbs] Add support for ParamountPlus by [shirt](https://github.com/shirt-dev)
+* [mxplayer] Rewrite extractor with show support by [pukkandan](https://github.com/pukkandan) and [Ashish0804](https://github.com/Ashish0804)
+* [gedi] Improvements from youtube-dl by [nixxo](https://github.com/nixxo)
+* [vimeo] Fix videos with password by [teesid](https://github.com/teesid)
+* [lbry] Support `lbry://` url by [nixxo](https://github.com/nixxo)
+* [bilibili] Change `Accept` header by [pukkandan](https://github.com/pukkandan) and [animelover1984](https://github.com/animelover1984)
+* [trovo] Pass origin header
+* [rai] Check for DRM by [nixxo](https://github.com/nixxo)
+* [downloader] Fix bug for `ffmpeg`/`httpie`
+* [update] Fix updater removing the executable bit on some UNIX distros
+* [update] Fix current build hash for UNIX
+* [documentation] Include wget/curl/aria2c install instructions for Unix by [Ashish0804](https://github.com/Ashish0804)
+* Fix some videos downloading with `m3u8` extension
+* Remove "fixup is ignored" warning when fixup wasn't passed by user
+
+
+### 2021.03.03.2
+* [build] Fix bug
+
+### 2021.03.03
+* [youtube] Use new browse API for continuation page extraction by [colethedj](https://github.com/colethedj) and [pukkandan](https://github.com/pukkandan)
+* Fix HLS playlist downloading by [shirt](https://github.com/shirt-dev)
+* Merge youtube-dl: Upto [2021.03.03](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.03.03)
+* [mtv] Fix extractor
+* [nick] Fix extractor by [DennyDai](https://github.com/DennyDai)
+* [mxplayer] Add new extractor by [codeasashu](https://github.com/codeasashu)
+* [youtube] Throw error when `--extractor-retries` are exhausted
+* Reduce default of `--extractor-retries` to 3
+* Fix packaging bugs by [hseg](https://github.com/hseg)
+
+
+### 2021.03.01
+* Allow specifying path in `--external-downloader`
+* Add option `--sleep-requests` to sleep b/w requests
+* Add option `--extractor-retries` to retry on known extractor errors
+* Extract comments only when needed
+* `--get-comments` doesn't imply `--write-info-json` if `-J`, `-j` or `--print-json` are used
+* Fix `get_executable_path` by [shirt](https://github.com/shirt-dev)
+* [youtube] Retry on more known errors than just HTTP-5xx
+* [youtube] Fix inconsistent `webpage_url`
+* [tennistv] Fix format sorting
+* [bilibiliaudio] Recognize the file as audio-only
+* [hrfensehen] Fix wrong import
+* [viki] Fix viki play pass authentication by [RobinD42](https://github.com/RobinD42)
+* [readthedocs] Improvements by [shirt](https://github.com/shirt-dev)
+* [hls] Fix bug with m3u8 format extraction
+* [hls] Enable `--hls-use-mpegts` by default when downloading live-streams
+* [embedthumbnail] Fix bug with deleting original thumbnail
+* [build] Fix completion paths, zsh pip completion install by [hseg](https://github.com/hseg)
+* [ci] Disable download tests unless specifically invoked
+* Cleanup some code and fix typos
+
+
 ### 2021.02.24
 * Moved project to an organization [yt-dlp](https://github.com/yt-dlp)
 * **Completely changed project name to yt-dlp** by [Pccode66](https://github.com/Pccode66) and [pukkandan](https://github.com/pukkandan)
-* **Merge youtube-dl:** Upto [commit/4460329](https://github.com/ytdl-org/youtube-dl/commit/44603290e5002153f3ebad6230cc73aef42cc2cd) (except tmz, gedi)
+    * Also, `youtube-dlc` config files are no longer loaded
+* Merge youtube-dl: Upto [commit/4460329](https://github.com/ytdl-org/youtube-dl/commit/44603290e5002153f3ebad6230cc73aef42cc2cd) (except tmz, gedi)
 * [Readthedocs](https://yt-dlp.readthedocs.io) support by [shirt](https://github.com/shirt-dev)
 * [youtube] Show if video was a live stream in info (`was_live`)
-* [Zee5] Add new extractor by [Ashish](https://github.com/Ashish) and [pukkandan](https://github.com/pukkandan)
+* [Zee5] Add new extractor by [Ashish0804](https://github.com/Ashish0804) and [pukkandan](https://github.com/pukkandan)
 * [jwplatform] Add support for `hyland.com`
 * [tennistv] Fix extractor
 * [hls] Support media initialization by [shirt](https://github.com/shirt-dev)
 * [hls] Added options `--hls-split-discontinuity` to better support media discontinuity by [shirt](https://github.com/shirt-dev)
-* [ffmpeg] Allow passing custom arguments before -i using `--ppa "ffmpeg_i1:ARGS"` synatax
+* [ffmpeg] Allow passing custom arguments before -i using `--ppa "ffmpeg_i1:ARGS"` syntax
 * Fix `--windows-filenames` removing `/` from UNIX paths
 * [hls] Show warning if pycryptodome is not found
 * [documentation] Improvements
     * Fix documentation of `Extractor Options`
-    * Document `all` in format selection (Closes #101)
+    * Document `all` in format selection
     * Document `playable_in_embed` in output templates
 
 
 ### 2021.02.19
-* **Merge youtube-dl:** Upto [commit/cf2dbec](https://github.com/ytdl-org/youtube-dl/commit/cf2dbec6301177a1fddf72862de05fa912d9869d) (except kakao)
+* Merge youtube-dl: Upto [commit/cf2dbec](https://github.com/ytdl-org/youtube-dl/commit/cf2dbec6301177a1fddf72862de05fa912d9869d) (except kakao)
 * [viki] Fix extractor
 * [niconico] Extract `channel` and `channel_id` by [kurumigi](https://github.com/kurumigi)
 * [youtube] Multiple page support for hashtag URLs
@@ -63,7 +225,7 @@
 
 
 ### 2021.02.15
-* **Merge youtube-dl:** Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
+* Merge youtube-dl: Upto [2021.02.10](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.10) (except archive.org)
 * [niconico] Improved extraction and support encrypted/SMILE movies by [kurumigi](https://github.com/kurumigi), [tsukumi](https://github.com/tsukumi), [bbepis](https://github.com/bbepis), [pukkandan](https://github.com/pukkandan)
 * Fix HLS AES-128 with multiple keys in external downloaders by [shirt](https://github.com/shirt-dev)
 * [youtube_live_chat] Fix by using POST API by [siikamiika](https://github.com/siikamiika)
@@ -106,7 +268,7 @@
 
 
 ### 2021.02.04
-* **Merge youtube-dl:** Upto [2021.02.04.1](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.04.1)
+* Merge youtube-dl: Upto [2021.02.04.1](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.02.04.1)
 * **Date/time formatting in output template:**
     * You can use [`strftime`](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) to format date/time fields. Example: `%(upload_date>%Y-%m-%d)s`
 * **Multiple output templates:**
@@ -160,7 +322,7 @@
 
 
 ### 2021.01.24
-* **Merge youtube-dl:** Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
+* Merge youtube-dl: Upto [2021.01.24](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
 * Plugin support ([documentation](https://github.com/yt-dlp/yt-dlp#plugins))
 * **Multiple paths**: New option `-P`/`--paths` to give different paths for different types of files
     * The syntax is `-P "type:path" -P "type:path"` ([documentation](https://github.com/yt-dlp/yt-dlp#:~:text=-P,%20--paths%20TYPE:PATH))
@@ -189,7 +351,7 @@
 
 
 ### 2021.01.16
-* **Merge youtube-dl:** Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
+* Merge youtube-dl: Upto [2021.01.16](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.16)
 * **Configuration files:**
     * Portable configuration file: `./yt-dlp.conf`
     * Allow the configuration files to be named `yt-dlp` instead of `youtube-dlc`. See [this](https://github.com/yt-dlp/yt-dlp#configuration) for details
@@ -219,7 +381,7 @@
 * [archive.org] Fix extractor and add support for audio and playlists by [wporr](https://github.com/wporr)
 * [Animelab] Added by [mariuszskon](https://github.com/mariuszskon)
 * [youtube:search] Fix view_count by [ohnonot](https://github.com/ohnonot)
-* [youtube] Show if video is embeddable in info
+* [youtube] Show if video is embeddable in info (`playable_in_embed`)
 * Update version badge automatically in README
 * Enable `test_youtube_search_matching`
 * Create `to_screen` and similar functions in postprocessor/common
@@ -235,9 +397,8 @@
 
 
 ### 2021.01.08
-* **Merge youtube-dl:** Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.08)
-    * Extractor stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f)) have not been merged
-* Moved changelog to seperate file
+* Merge youtube-dl: Upto [2021.01.08](https://github.com/ytdl-org/youtube-dl/releases/tag/2021.01.08) except stitcher ([1](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc), [2](https://github.com/ytdl-org/youtube-dl/commit/a563c97c5cddf55f8989ed7ea8314ef78e30107f))
+* Moved changelog to separate file
 
 
 ### 2021.01.07-1
@@ -275,8 +436,8 @@
     * Changed video format sorting to show video only files and video+audio files together.
     * Added `--video-multistreams`, `--no-video-multistreams`, `--audio-multistreams`, `--no-audio-multistreams`
     * Added `b`,`w`,`v`,`a` as alias for `best`, `worst`, `video` and `audio` respectively
-* **Shortcut Options:** Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
-* **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-options-sponsorblock) for details
+* Shortcut Options: Added `--write-link`, `--write-url-link`, `--write-webloc-link`, `--write-desktop-link` by [h-h-h-h](https://github.com/h-h-h-h) - See [Internet Shortcut Options](README.md#internet-shortcut-options) for details
+* **Sponskrub integration:** Added `--sponskrub`, `--sponskrub-cut`, `--sponskrub-force`, `--sponskrub-location`, `--sponskrub-args` - See [SponSkrub Options](README.md#sponskrub-sponsorblock-options) for details
 * Added `--force-download-archive` (`--force-write-archive`) by [h-h-h-h](https://github.com/h-h-h-h)
 * Added `--list-formats-as-table`,  `--list-formats-old`
 * **Negative Options:** Makes it possible to negate most boolean options by adding a `no-` to the switch. Usefull when you want to reverse an option that is defined in a config file
@@ -285,36 +446,38 @@
 * Relaxed validation for format filters so that any arbitrary field can be used
 * Fix for embedding thumbnail in mp3 by [pauldubois98](https://github.com/pauldubois98) ([ytdl-org/youtube-dl#21569](https://github.com/ytdl-org/youtube-dl/pull/21569))
 * Make Twitch Video ID output from Playlist and VOD extractor same. This is only a temporary fix
-* **Merge youtube-dl:** Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
+* Merge youtube-dl: Upto [2021.01.03](https://github.com/ytdl-org/youtube-dl/commit/8e953dcbb10a1a42f4e12e4e132657cb0100a1f8) - See [blackjack4494/yt-dlc#280](https://github.com/blackjack4494/yt-dlc/pull/280) for details
     * Extractors [tiktok](https://github.com/ytdl-org/youtube-dl/commit/fb626c05867deab04425bad0c0b16b55473841a2) and [hotstar](https://github.com/ytdl-org/youtube-dl/commit/bb38a1215718cdf36d73ff0a7830a64cd9fa37cc) have not been merged
 * Cleaned up the fork for public use
 
 
+**PS**: All uncredited changes above this point are authored by [pukkandan](https://github.com/pukkandan)
+
 ### Unreleased changes in [blackjack4494/yt-dlc](https://github.com/blackjack4494/yt-dlc)
-* Updated to youtube-dl release 2020.11.26
-* [youtube]
+* Updated to youtube-dl release 2020.11.26 by [pukkandan](https://github.com/pukkandan)
+* Youtube improvements by [pukkandan](https://github.com/pukkandan)
     * Implemented all Youtube Feeds (ytfav, ytwatchlater, ytsubs, ythistory, ytrec) and SearchURL
-    * Fix ytsearch not returning results sometimes due to promoted content
-    * Temporary fix for automatic captions - disable json3
     * Fix some improper Youtube URLs
     * Redirect channel home to /video
     * Print youtube's warning message
-    * Multiple pages are handled better for feeds
+    * Handle Multiple pages for feeds better
+* [youtube] Fix ytsearch not returning results sometimes due to promoted content by [colethedj](https://github.com/colethedj)
+* [youtube] Temporary fix for automatic captions - disable json3 by [blackjack4494](https://github.com/blackjack4494)
 * Add --break-on-existing by [gergesh](https://github.com/gergesh)
-* Pre-check video IDs in the archive before downloading
-* [bitwave.tv] New extractor
-* [Gedi] Add extractor
-* [Rcs] Add new extractor
-* [skyit] Add support for multiple Sky Italia website and removed old skyitalia extractor
-* [france.tv] Fix thumbnail URL
-* [ina] support mobile links
-* [instagram] Fix extractor
-* [itv] BTCC new pages' URL update (articles instead of races)
-* [SouthparkDe] Support for English URLs
-* [spreaker] fix SpreakerShowIE test URL
-* [Vlive] Fix playlist handling when downloading a channel
-* [generic] Detect embedded bitchute videos
-* [generic] Extract embedded youtube and twitter videos
-* [ffmpeg] Ensure all streams are copied
-* Fix for os.rename error when embedding thumbnail to video in a different drive
-* make_win.bat: don't use UPX to pack vcruntime140.dll
+* Pre-check video IDs in the archive before downloading by [pukkandan](https://github.com/pukkandan)
+* [bitwave.tv] New extractor by [lorpus](https://github.com/lorpus)
+* [Gedi] Add extractor by [nixxo](https://github.com/nixxo)
+* [Rcs] Add new extractor by [nixxo](https://github.com/nixxo)
+* [skyit] New skyitalia extractor by [nixxo](https://github.com/nixxo)
+* [france.tv] Fix thumbnail URL by [renalid](https://github.com/renalid)
+* [ina] support mobile links by [B0pol](https://github.com/B0pol)
+* [instagram] Fix thumbnail extractor by [nao20010128nao](https://github.com/nao20010128nao)
+* [SouthparkDe] Support for English URLs by [xypwn](https://github.com/xypwn)
+* [spreaker] fix SpreakerShowIE test URL by [pukkandan](https://github.com/pukkandan)
+* [Vlive] Fix playlist handling when downloading a channel by [kyuyeunk](https://github.com/kyuyeunk)
+* [tmz] Fix extractor by [diegorodriguezv](https://github.com/diegorodriguezv)
+* [generic] Detect embedded bitchute videos by [pukkandan](https://github.com/pukkandan)
+* [generic] Extract embedded youtube and twitter videos by [diegorodriguezv](https://github.com/diegorodriguezv)
+* [ffmpeg] Ensure all streams are copied by [pukkandan](https://github.com/pukkandan)
+* [embedthumbnail] Fix for os.rename error by [pukkandan](https://github.com/pukkandan)
+* make_win.bat: don't use UPX to pack vcruntime140.dll by [jbruchon](https://github.com/jbruchon)

MANIFEST.in

@@ -1,9 +1,9 @@
-include README.md
-include LICENSE
 include AUTHORS
-include ChangeLog
-include yt-dlp.bash-completion
-include yt-dlp.fish
+include Changelog.md
+include LICENSE
+include README.md
+include completions/*/*
+include supportedsites.md
 include yt-dlp.1
-recursive-include docs Makefile conf.py *.rst
+recursive-include devscripts *
 recursive-include test *

Makefile

@@ -1,12 +1,28 @@
-all: yt-dlp doc man
+all: yt-dlp doc pypi-files
+clean: clean-test clean-dist clean-cache
+completions: completion-bash completion-fish completion-zsh
 doc: README.md CONTRIBUTING.md issuetemplates supportedsites
-man: README.txt yt-dlp.1 yt-dlp.bash-completion yt-dlp.zsh yt-dlp.fish
+ot: offlinetest
+tar: yt-dlp.tar.gz
 
+# Keep this list in sync with MANIFEST.in
+# intended use: when building a source distribution,
+# make pypi-files && python setup.py sdist
+pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites completions yt-dlp.1 devscripts/* test/*
 
-clean:
-	rm -rf yt-dlp.1.temp.md yt-dlp.1 yt-dlp.bash-completion README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz yt-dlp.zsh yt-dlp.fish yt_dlp/extractor/lazy_extractors.py *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.spec *.frag *.frag.urls *.frag.aria2 CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe
-	find . -name "*.pyc" -delete
-	find . -name "*.class" -delete
+.PHONY: all clean install test tar pypi-files completions ot offlinetest codetest supportedsites
+
+clean-test:
+	rm -rf *.dump *.part* *.ytdl *.info.json *.mp4 *.m4a *.flv *.mp3 *.avi *.mkv *.webm *.3gp *.wav *.ape *.swf *.jpg *.png *.frag *.frag.urls *.frag.aria2
+clean-dist:
+	rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS .mailmap
+clean-cache:
+	find . -name "*.pyc" -o -name "*.class" -delete
+
+completion-bash: completions/bash/yt-dlp
+completion-fish: completions/fish/yt-dlp.fish
+completion-zsh: completions/zsh/_yt-dlp
+lazy-extractors: yt_dlp/extractor/lazy_extractors.py
 
 PREFIX ?= /usr/local
 BINDIR ?= $(PREFIX)/bin
@@ -21,17 +37,12 @@ SYSCONFDIR = $(shell if [ $(PREFIX) = /usr -o $(PREFIX) = /usr/local ]; then ech
 # set markdown input format to "markdown-smart" for pandoc version 2 and to "markdown" for pandoc prior to version 2
 MARKDOWN = $(shell if [ `pandoc -v | head -n1 | cut -d" " -f2 | head -c1` = "2" ]; then echo markdown-smart; else echo markdown; fi)
 
-install: yt-dlp yt-dlp.1 yt-dlp.bash-completion yt-dlp.zsh yt-dlp.fish
-	install -d $(DESTDIR)$(BINDIR)
-	install -m 755 yt-dlp $(DESTDIR)$(BINDIR)
-	install -d $(DESTDIR)$(MANDIR)/man1
-	install -m 644 yt-dlp.1 $(DESTDIR)$(MANDIR)/man1
-	install -d $(DESTDIR)$(SYSCONFDIR)/bash_completion.d
-	install -m 644 yt-dlp.bash-completion $(DESTDIR)$(SYSCONFDIR)/bash_completion.d/yt-dlp
-	install -d $(DESTDIR)$(SHAREDIR)/zsh/site-functions
-	install -m 644 yt-dlp.zsh $(DESTDIR)$(SHAREDIR)/zsh/site-functions/_yt-dlp
-	install -d $(DESTDIR)$(SYSCONFDIR)/fish/completions
-	install -m 644 yt-dlp.fish $(DESTDIR)$(SYSCONFDIR)/fish/completions/yt-dlp.fish
+install: yt-dlp yt-dlp.1 completions
+	install -Dm755 yt-dlp $(DESTDIR)$(BINDIR)
+	install -Dm644 yt-dlp.1 $(DESTDIR)$(MANDIR)/man1
+	install -Dm644 completions/bash/yt-dlp $(DESTDIR)$(SHAREDIR)/bash-completion/completions/yt-dlp
+	install -Dm644 completions/zsh/_yt-dlp $(DESTDIR)$(SHAREDIR)/zsh/site-functions/_yt-dlp
+	install -Dm644 completions/fish/yt-dlp.fish $(DESTDIR)$(SHAREDIR)/fish/vendor_completions.d/yt-dlp.fish
 
 codetest:
 	flake8 .
@@ -41,8 +52,6 @@ test:
 	nosetests --verbose test
 	$(MAKE) codetest
 
-ot: offlinetest
-
 # Keep this list in sync with devscripts/run_tests.sh
 offlinetest: codetest
 	$(PYTHON) -m nose --verbose test \
@@ -57,12 +66,6 @@ offlinetest: codetest
 		--exclude test_youtube_signature.py \
 		--exclude test_post_hooks.py
 
-tar: yt-dlp.tar.gz
-
-.PHONY: all clean install test tar bash-completion pypi-files zsh-completion fish-completion ot offlinetest codetest supportedsites
-
-pypi-files: yt-dlp.bash-completion README.txt yt-dlp.1 yt-dlp.fish
-
 yt-dlp: yt_dlp/*.py yt_dlp/*/*.py
 	mkdir -p zip
 	for d in yt_dlp yt_dlp/downloader yt_dlp/extractor yt_dlp/postprocessor ; do \
@@ -92,7 +95,7 @@ issuetemplates: devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl/1_
 	$(PYTHON) devscripts/make_issue_template.py .github/ISSUE_TEMPLATE_tmpl/5_feature_request.md .github/ISSUE_TEMPLATE/5_feature_request.md
 
 supportedsites:
-	$(PYTHON) devscripts/make_supportedsites.py docs/supportedsites.md
+	$(PYTHON) devscripts/make_supportedsites.py supportedsites.md
 
 README.txt: README.md
 	pandoc -f $(MARKDOWN) -t plain README.md -o README.txt
@@ -102,29 +105,24 @@ yt-dlp.1: README.md
 	pandoc -s -f $(MARKDOWN) -t man yt-dlp.1.temp.md -o yt-dlp.1
 	rm -f yt-dlp.1.temp.md
 
-yt-dlp.bash-completion: yt_dlp/*.py yt_dlp/*/*.py devscripts/bash-completion.in
+completions/bash/yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/bash-completion.in
+	mkdir -p completions/bash
 	$(PYTHON) devscripts/bash-completion.py
 
-bash-completion: yt-dlp.bash-completion
-
-yt-dlp.zsh: yt_dlp/*.py yt_dlp/*/*.py devscripts/zsh-completion.in
+completions/zsh/_yt-dlp: yt_dlp/*.py yt_dlp/*/*.py devscripts/zsh-completion.in
+	mkdir -p completions/zsh
 	$(PYTHON) devscripts/zsh-completion.py
 
-zsh-completion: yt-dlp.zsh
-
-yt-dlp.fish: yt_dlp/*.py yt_dlp/*/*.py devscripts/fish-completion.in
+completions/fish/yt-dlp.fish: yt_dlp/*.py yt_dlp/*/*.py devscripts/fish-completion.in
+	mkdir -p completions/fish
 	$(PYTHON) devscripts/fish-completion.py
 
-fish-completion: yt-dlp.fish
-
-lazy-extractors: yt_dlp/extractor/lazy_extractors.py
-
 _EXTRACTOR_FILES = $(shell find yt_dlp/extractor -iname '*.py' -and -not -iname 'lazy_extractors.py')
 yt_dlp/extractor/lazy_extractors.py: devscripts/make_lazy_extractors.py devscripts/lazy_load_template.py $(_EXTRACTOR_FILES)
 	$(PYTHON) devscripts/make_lazy_extractors.py $@
 
-yt-dlp.tar.gz: yt-dlp README.md README.txt yt-dlp.1 yt-dlp.bash-completion yt-dlp.zsh yt-dlp.fish ChangeLog AUTHORS
-	@tar -czf yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
+yt-dlp.tar.gz: README.md yt-dlp.1 completions Changelog.md AUTHORS
+	@tar -czf $(DESTDIR)/yt-dlp.tar.gz --transform "s|^|yt-dlp/|" --owner 0 --group 0 \
 		--exclude '*.DS_Store' \
 		--exclude '*.kate-swp' \
 		--exclude '*.pyc' \
@@ -134,8 +132,13 @@ yt-dlp.tar.gz: yt-dlp README.md README.txt yt-dlp.1 yt-dlp.bash-completion yt-dl
 		--exclude '.git' \
 		--exclude 'docs/_build' \
 		-- \
-		bin devscripts test yt_dlp docs \
-		ChangeLog AUTHORS LICENSE README.md README.txt \
-		Makefile MANIFEST.in yt-dlp.1 yt-dlp.bash-completion \
-		yt-dlp.zsh yt-dlp.fish setup.py setup.cfg \
-		yt-dlp
+		devscripts test \
+		Changelog.md AUTHORS LICENSE README.md supportedsites.md \
+		Makefile MANIFEST.in yt-dlp.1 completions \
+		setup.py setup.cfg yt-dlp
+
+AUTHORS: .mailmap
+	git shortlog -s -n | cut -f2 | sort > AUTHORS
+
+.mailmap:
+	git shortlog -s -e -n | awk '!(out[$$NF]++) { $$1="";sub(/^[ \t]+/,""); print}' > .mailmap

README.md

@@ -1,39 +1,44 @@
+<div align="center">
+
 # YT-DLP
+A command-line program to download videos from YouTube and many other [video platforms](supportedsites.md)
 
-[![Release version](https://img.shields.io/github/v/release/yt-dlp/yt-dlp?color=brightgreen&label=Release)](https://github.com/yt-dlp/yt-dlp/releases/latest)
-[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg)](LICENSE)
+<!-- GHA doesnot have for-the-badge style
 [![CI Status](https://github.com/yt-dlp/yt-dlp/workflows/Core%20Tests/badge.svg?branch=master)](https://github.com/yt-dlp/yt-dlp/actions)
-[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&label=discord&logo=discord)](https://discord.gg/S75JaBna)  
+-->
+[![Release version](https://img.shields.io/github/v/release/yt-dlp/yt-dlp?color=brightgreen&label=Release&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/releases/latest)
+[![License: Unlicense](https://img.shields.io/badge/License-Unlicense-blue.svg?style=for-the-badge)](LICENSE)
+[![Doc Status](https://readthedocs.org/projects/yt-dlp/badge/?version=latest&style=for-the-badge)](https://yt-dlp.readthedocs.io)
+[![Discord](https://img.shields.io/discord/807245652072857610?color=blue&label=discord&logo=discord&style=for-the-badge)](https://discord.gg/H5MNcFW63r)  
 
-[![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits)](https://github.com/yt-dlp/yt-dlp/commits)
-[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master)](https://github.com/yt-dlp/yt-dlp/commits)
-[![Downloads](https://img.shields.io/github/downloads/yt-dlp/yt-dlp/total)](https://github.com/yt-dlp/yt-dlp/releases/latest)
-[![PyPi Downloads](https://img.shields.io/pypi/dm/yt-dlp?label=PyPi)](https://pypi.org/project/yt-dlp)
-[![Doc Status](https://readthedocs.org/projects/yt-dlp/badge/?version=latest)](https://yt-dlp.readthedocs.io)
+[![Commits](https://img.shields.io/github/commit-activity/m/yt-dlp/yt-dlp?label=commits&style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits)
+[![Last Commit](https://img.shields.io/github/last-commit/yt-dlp/yt-dlp/master?style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/commits)
+[![Downloads](https://img.shields.io/github/downloads/yt-dlp/yt-dlp/total?style=for-the-badge)](https://github.com/yt-dlp/yt-dlp/releases/latest)
+[![PyPi Downloads](https://img.shields.io/pypi/dm/yt-dlp?label=PyPi&style=for-the-badge)](https://pypi.org/project/yt-dlp)
 
-A command-line program to download videos from youtube.com and many other [video platforms](docs/supportedsites.md)
+</div>
 
-This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which is inturn a fork of [youtube-dl](https://github.com/ytdl-org/youtube-dl)
+yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on the now inactive [youtube-dlc](https://github.com/blackjack4494/yt-dlc). The main focus of this project is adding new features and patches while also keeping up to date with the original project
 
 * [NEW FEATURES](#new-features)
 * [INSTALLATION](#installation)
+    * [Dependancies](#dependancies)
     * [Update](#update)
     * [Compile](#compile)
-* [DESCRIPTION](#description)
-* [OPTIONS](#options)
+* [USAGE AND OPTIONS](#usage-and-options)
+    * [General Options](#general-options)
     * [Network Options](#network-options)
-    * [Geo Restriction](#geo-restriction)
+    * [Geo-restriction](#geo-restriction)
     * [Video Selection](#video-selection)
     * [Download Options](#download-options)
     * [Filesystem Options](#filesystem-options)
-    * [Thumbnail images](#thumbnail-images)
+    * [Thumbnail Options](#thumbnail-options)
     * [Internet Shortcut Options](#internet-shortcut-options)
     * [Verbosity and Simulation Options](#verbosity-and-simulation-options)
     * [Workarounds](#workarounds)
     * [Video Format Options](#video-format-options)
     * [Subtitle Options](#subtitle-options)
     * [Authentication Options](#authentication-options)
-    * [Adobe Pass Options](#adobe-pass-options)
     * [Post-processing Options](#post-processing-options)
     * [SponSkrub (SponsorBlock) Options](#sponskrub-sponsorblock-options)
     * [Extractor Options](#extractor-options)
@@ -46,8 +51,12 @@ This is a fork of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) which i
     * [Filtering Formats](#filtering-formats)
     * [Sorting Formats](#sorting-formats)
     * [Format Selection examples](#format-selection-examples)
+* [MODIFYING METADATA](#modifying-metadata)
+    * [Modifying metadata examples](#modifying-metadata-examples)
 * [PLUGINS](#plugins)
+* [DEPRECATED OPTIONS](#deprecated-options)
 * [MORE](#more)
+</div>
 
 
 # NEW FEATURES
@@ -57,7 +66,7 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
 
 * **[Format Sorting](#sorting-formats)**: The default format sorting options have been changed so that higher resolution and better codecs will be now preferred instead of simply using larger bitrate. Furthermore, you can now specify the sort order using `-S`. This allows for much easier format selection that what is possible by simply using `--format` ([examples](#format-selection-examples))
 
-* **Merged with youtube-dl v2021.02.10**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
+* **Merged with youtube-dl v2021.04.07**: You get all the latest features and patches of [youtube-dl](https://github.com/ytdl-org/youtube-dl) in addition to all the features of [youtube-dlc](https://github.com/blackjack4494/yt-dlc)
 
 * **Merged with animelover1984/youtube-dl**: You get most of the features and improvements from [animelover1984/youtube-dl](https://github.com/animelover1984/youtube-dl) including `--get-comments`, `BiliBiliSearch`, `BilibiliChannel`, Embedding thumbnail in mp4/ogg/opus, Playlist infojson etc. Note that the NicoNico improvements are not available. See [#31](https://github.com/yt-dlp/yt-dlp/pull/31) for details.
 
@@ -66,17 +75,17 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
     * Youtube search (`ytsearch:`, `ytsearchdate:`) along with Search URLs works correctly
     * Redirect channel's home URL automatically to `/video` to preserve the old behaviour
 
-* **Aria2c with HLS/DASH**: You can use aria2c as the external downloader for DASH(mpd) and HLS(m3u8) formats. No more slow ffmpeg/native downloads
+* **Split video by chapters**: Videos can be split into multiple files based on chapters using `--split-chapters`
 
-* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5
+* **Multi-threaded fragment downloads**: Download multiple fragments of m3u8/mpd videos in parallel. Use `--concurrent-fragments` (`-N`) option to set the number of threads used
 
-* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, tiktok, akamai, ina, rumble, tennistv
+* **Aria2c with HLS/DASH**: You can use `aria2c` as the external downloader for DASH(mpd) and HLS(m3u8) formats
 
-* **Plugin support**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
+* **New extractors**: AnimeLab, Philo MSO, Rcs, Gedi, bitwave.tv, mildom, audius, zee5, mtv.it, wimtv, pluto.tv, niconico users, discoveryplus.in, mediathek, NFHSNetwork, nebula
 
-* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to. See [`--paths`](https://github.com/yt-dlp/yt-dlp/#:~:text=-P,%20--paths%20TYPE:PATH) for details
+* **Fixed extractors**: archive.org, roosterteeth.com, skyit, instagram, itv, SouthparkDe, spreaker, Vlive, akamai, ina, rumble, tennistv, amcnetworks, la7 podcasts, linuxacadamy, nitter
 
-<!-- Relative link doesn't work for "#:~:text=" -->
+* **Multiple paths and output templates**: You can give different [output templates](#output-template) and download paths for different types of files. You can also set a temporary path where intermediary files are downloaded to using `--paths` (`-P`)
 
 * **Portable Configuration**: Configuration files are automatically loaded from the home and root directories. See [configuration](#configuration) for details
 
@@ -84,6 +93,8 @@ The major new features from the latest release of [blackjack4494/yt-dlc](https:/
 
 * **Improvements**: Multiple `--postprocessor-args` and `--external-downloader-args`, Date/time formatting in `-o`, faster archive checking, more [format selection options](#format-selection) etc
 
+* **Plugin extractors**: Extractors can be loaded from an external file. See [plugins](#plugins) for details
+
 * **Self-updater**: The releases can be updated using `yt-dlp -U`
 
 
@@ -92,10 +103,11 @@ See [changelog](Changelog.md) or [commits](https://github.com/yt-dlp/yt-dlp/comm
 
 **PS**: Some of these changes are already in youtube-dlc, but are still unreleased. See [this](Changelog.md#unreleased-changes-in-blackjack4494yt-dlc) for details
 
-If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the amount of changes are very large. Compare [options](#options) and [supported sites](docs/supportedsites.md) with youtube-dl's to get an idea of the massive number of features/patches [youtube-dlc](https://github.com/blackjack4494/yt-dlc) has accumulated.
+If you are coming from [youtube-dl](https://github.com/ytdl-org/youtube-dl), the amount of changes are very large. Compare [options](#options) and [supported sites](supportedsites.md) with youtube-dl's to get an idea of the massive number of features/patches [youtube-dlc](https://github.com/blackjack4494/yt-dlc) has accumulated.
 
 
 # INSTALLATION
+yt-dlp is not platform specific. So it should work on your Unix box, on Windows or on macOS
 
 You can install yt-dlp using one of the following methods:
 * Download the binary from the [latest release](https://github.com/yt-dlp/yt-dlp/releases/latest) (recommended method)
@@ -103,8 +115,31 @@ You can install yt-dlp using one of the following methods:
 * Use pip+git: `python -m pip install --upgrade git+https://github.com/yt-dlp/yt-dlp.git@release`
 * Install master branch: `python -m pip install --upgrade git+https://github.com/yt-dlp/yt-dlp`
 
+UNIX users (Linux, macOS, BSD) can also install the [latest release](https://github.com/yt-dlp/yt-dlp/releases/latest) one of the following ways:
+
+```
+sudo curl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
+```
+sudo wget https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -O /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
+```
+sudo aria2c https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o /usr/local/bin/yt-dlp
+sudo chmod a+rx /usr/local/bin/yt-dlp
+```
+
+### DEPENDANCIES
+
+Python versions 2.6, 2.7, or 3.2+ are currently supported. However, 3.2+ is strongly recommended and python2 support will be deprecated in the future.
+
+Although there are no required dependancies, `ffmpeg` and `ffprobe` are highly recommended. Other optional dependancies are `sponskrub`, `AtomicParsley`, `mutagen`, `pycryptodome` and any of the supported external downloaders. Note that the windows releases are already built with the python interpreter, mutagen and pycryptodome included.
+
 ### UPDATE
-Starting from version `2021.02.09`, you can use `yt-dlp -U` to update if you are using the provided release.
+You can use `yt-dlp -U` to update if you are using the provided release.
 If you are using `pip`, simply re-run the same command that was used to install the program.
 
 ### COMPILE
@@ -122,17 +157,14 @@ You can also build the executable without any version info or metadata by using:
 
 **For Unix**:
 You will need the required build tools: `python`, `make` (GNU), `pandoc`, `zip`, `nosetests`  
-Then simply run `make`. You can also run `make youtube_dlc` instead to compile only the binary without updating any of the additional files
+Then simply run `make`. You can also run `make yt-dlp` instead to compile only the binary without updating any of the additional files
 
 **Note**: In either platform, `devscripts\update-version.py` can be used to automatically update the version number
 
-# DESCRIPTION
-**yt-dlp** is a command-line program to download videos from youtube.com many other [video platforms](docs/supportedsites.md). It requires the Python interpreter, version 2.6, 2.7, or 3.2+, and it is not platform specific. It should work on your Unix box, on Windows or on macOS. It is released to the public domain, which means you can modify it, redistribute it or use it however you like.
+# USAGE AND OPTIONS
 
     yt-dlp [OPTIONS] [--] URL [URL...]
 
-
-# OPTIONS
 `Ctrl+F` is your friend :D
 <!-- Autogenerated -->
 
@@ -177,7 +209,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      only list them
     --no-flat-playlist               Extract the videos of a playlist
     --mark-watched                   Mark videos watched (YouTube only)
-    --no-mark-watched                Do not mark videos watched
+    --no-mark-watched                Do not mark videos watched (default)
     --no-colors                      Do not emit color codes in output
 
 ## Network Options:
@@ -191,7 +223,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     -4, --force-ipv4                 Make all connections via IPv4
     -6, --force-ipv6                 Make all connections via IPv6
 
-## Geo Restriction:
+## Geo-restriction:
     --geo-verification-proxy URL     Use this proxy to verify the IP address for
                                      some geo-restricted sites. The default
                                      proxy specified by --proxy (or none, if the
@@ -245,7 +277,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      "OUTPUT TEMPLATE" for a list of available
                                      keys) to match if the key is present, !key
                                      to check if the key is not present,
-                                     key>NUMBER (like "comment_count > 12", also
+                                     key>NUMBER (like "view_count > 12", also
                                      works with >=, <, <=, !=, =) to compare
                                      against a number, key = 'LITERAL' (like
                                      "uploader = 'Mike Smith'", also works with
@@ -275,11 +307,11 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --break-on-reject                Stop the download process when encountering
                                      a file that has been filtered out
     --no-download-archive            Do not use archive file (default)
-    --include-ads                    Download advertisements as well
-                                     (experimental)
-    --no-include-ads                 Do not download advertisements (default)
 
 ## Download Options:
+    -N, --concurrent-fragments N     Number of fragments of a dash/hlsnative
+                                     video that should be download concurrently
+                                     (default is 1)
     -r, --limit-rate RATE            Maximum download rate in bytes per second
                                      (e.g. 50K or 4.2M)
     -R, --retries RETRIES            Number of retries (default is 10), or
@@ -313,17 +345,28 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --playlist-random                Download playlist videos in random order
     --xattr-set-filesize             Set file xattribute ytdl.filesize with
                                      expected file size
-    --hls-prefer-native              Use the native HLS downloader instead of
-                                     ffmpeg
-    --hls-prefer-ffmpeg              Use ffmpeg instead of the native HLS
-                                     downloader
-    --hls-use-mpegts                 Use the mpegts container for HLS videos,
-                                     allowing to play the video while
-                                     downloading (some players may not be able
-                                     to play it)
-    --external-downloader NAME       Use the specified external downloader.
-                                     Currently supports aria2c, avconv, axel,
-                                     curl, ffmpeg, httpie, wget
+    --hls-use-mpegts                 Use the mpegts container for HLS videos;
+                                     allowing some players to play the video
+                                     while downloading, and reducing the chance
+                                     of file corruption if download is
+                                     interrupted. This is enabled by default for
+                                     live streams
+    --no-hls-use-mpegts              Do not use the mpegts container for HLS
+                                     videos. This is default when not
+                                     downloading live streams
+    --downloader [PROTO:]NAME        Name or path of the external downloader to
+                                     use (optionally) prefixed by the protocols
+                                     (http, ftp, m3u8, dash, rstp, rtmp, mms) to
+                                     use it for. Currently supports native,
+                                     aria2c, avconv, axel, curl, ffmpeg, httpie,
+                                     wget (Recommended: aria2c). You can use
+                                     this option multiple times to set different
+                                     downloaders for different protocols. For
+                                     example, --downloader aria2c --downloader
+                                     "dash,m3u8:native" will use aria2c for
+                                     http/ftp downloads, and the native
+                                     downloader for dash/m3u8 downloads
+                                     (Alias: --external-downloader)
     --downloader-args NAME:ARGS      Give these arguments to the external
                                      downloader. Specify the downloader name and
                                      the arguments separated by a colon ":". You
@@ -335,7 +378,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      stdin), one URL per line. Lines starting
                                      with '#', ';' or ']' are considered as
                                      comments and ignored
-    -P, --paths TYPE:PATH            The paths where the files should be
+    -P, --paths TYPES:PATH           The paths where the files should be
                                      downloaded. Specify the type of file and
                                      the path separated by a colon ":". All the
                                      same types as --output are supported.
@@ -346,7 +389,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      home path after download is finished. This
                                      option is ignored if --output is an
                                      absolute path
-    -o, --output [TYPE:]TEMPLATE     Output filename template, see "OUTPUT
+    -o, --output [TYPES:]TEMPLATE    Output filename template; see "OUTPUT
                                      TEMPLATE" for details
     --output-na-placeholder TEXT     Placeholder value for unavailable meta
                                      fields in output filename template
@@ -396,8 +439,15 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      --write-description etc. (default)
     --no-write-playlist-metafiles    Do not write playlist metadata when using
                                      --write-info-json, --write-description etc.
+    --clean-infojson                 Remove some private fields such as
+                                     filenames from the infojson. Note that it
+                                     could still contain some personal
+                                     information (default)
+    --no-clean-infojson              Write all fields to the infojson
     --get-comments                   Retrieve video comments to be placed in the
-                                     .info.json file
+                                     .info.json file. The comments are fetched
+                                     even without this option if the extraction
+                                     is known to be quick
     --load-info-json FILE            JSON file containing the video information
                                      (created with the "--write-info-json"
                                      option)
@@ -415,7 +465,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --no-cache-dir                   Disable filesystem caching
     --rm-cache-dir                   Delete all filesystem cache files
 
-## Thumbnail Images:
+## Thumbnail Options:
     --write-thumbnail                Write thumbnail image to disk
     --no-write-thumbnail             Do not write thumbnail image to disk
                                      (default)
@@ -437,7 +487,8 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --no-warnings                    Ignore warnings
     -s, --simulate                   Do not download the video and do not write
                                      anything to disk
-    --skip-download                  Do not download the video
+    --skip-download                  Do not download the video but write all
+                                     related files (Alias: --no-download)
     -g, --get-url                    Simulate, quiet but print URL
     -e, --get-title                  Simulate, quiet but print title
     --get-id                         Simulate, quiet but print id
@@ -474,7 +525,7 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --encoding ENCODING              Force the specified encoding (experimental)
     --no-check-certificate           Suppress HTTPS certificate validation
     --prefer-insecure                Use an unencrypted connection to retrieve
-                                     information about the video. (Currently
+                                     information about the video (Currently
                                      supported only for YouTube)
     --user-agent UA                  Specify a custom user agent
     --referer URL                    Specify a custom referer, use if the video
@@ -485,17 +536,16 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --bidi-workaround                Work around terminals that lack
                                      bidirectional text support. Requires bidiv
                                      or fribidi executable in PATH
+    --sleep-requests SECONDS         Number of seconds to sleep between requests
+                                     during data extraction
     --sleep-interval SECONDS         Number of seconds to sleep before each
-                                     download when used alone or a lower bound
-                                     of a range for randomized sleep before each
-                                     download (minimum possible number of
-                                     seconds to sleep) when used along with
-                                     --max-sleep-interval
-    --max-sleep-interval SECONDS     Upper bound of a range for randomized sleep
-                                     before each download (maximum possible
-                                     number of seconds to sleep). Must only be
-                                     used along with --min-sleep-interval
-    --sleep-subtitles SECONDS        Enforce sleep interval on subtitles as well
+                                     download. This is the minimum time to sleep
+                                     when used along with --max-sleep-interval
+                                     (Alias: --min-sleep-interval)
+    --max-sleep-interval SECONDS     Maximum number of seconds to sleep. Can
+                                     only be used along with --min-sleep-interval
+    --sleep-subtitles SECONDS        Number of seconds to sleep before each
+                                     subtitle download
 
 ## Video Format Options:
     -f, --format FORMAT              Video format code, see "FORMAT SELECTION"
@@ -516,7 +566,6 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      into a single file
     --no-audio-multistreams          Only one audio stream is downloaded for
                                      each output file (default)
-    --all-formats                    Download all available video formats
     --prefer-free-formats            Prefer video formats with free containers
                                      over non-free ones of same quality. Use
                                      with "-S ext" to strictly prefer free
@@ -543,16 +592,16 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --write-subs                     Write subtitle file
     --no-write-subs                  Do not write subtitle file (default)
     --write-auto-subs                Write automatically generated subtitle file
-                                     (YouTube only)
-    --no-write-auto-subs             Do not write automatically generated
-                                     subtitle file (default)
+                                     (Alias: --write-automatic-subs)
+    --no-write-auto-subs             Do not write auto-generated subtitles
+                                     (default) (Alias: --no-write-automatic-subs)
     --all-subs                       Download all the available subtitles of the
                                      video
     --list-subs                      List all available subtitles for the video
     --sub-format FORMAT              Subtitle format, accepts formats
                                      preference, for example: "srt" or
                                      "ass/srt/best"
-    --sub-lang LANGS                 Languages of the subtitles to download
+    --sub-langs LANGS                Languages of the subtitles to download
                                      (optional) separated by commas, use --list-
                                      subs for available language tags
 
@@ -563,8 +612,6 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     -2, --twofactor TWOFACTOR        Two-factor authentication code
     -n, --netrc                      Use .netrc authentication data
     --video-password PASSWORD        Video password (vimeo, youku)
-
-## Adobe Pass Options:
     --ap-mso MSO                     Adobe Pass multiple-system operator (TV
                                      provider) identifier, use --ap-list-mso for
                                      a list of available MSOs
@@ -601,23 +648,24 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      Specify the postprocessor/executable name
                                      and the arguments separated by a colon ":"
                                      to give the argument to the specified
-                                     postprocessor/executable. Supported
-                                     postprocessors are: SponSkrub,
-                                     ExtractAudio, VideoRemuxer, VideoConvertor,
-                                     EmbedSubtitle, Metadata, Merger,
-                                     FixupStretched, FixupM4a, FixupM3u8,
-                                     SubtitlesConvertor and EmbedThumbnail. The
-                                     supported executables are: SponSkrub,
-                                     FFmpeg, FFprobe, and AtomicParsley. You can
+                                     postprocessor/executable. Supported PP are:
+                                     Merger, ExtractAudio, SplitChapters,
+                                     Metadata, EmbedSubtitle, EmbedThumbnail,
+                                     SubtitlesConvertor, ThumbnailsConvertor,
+                                     VideoRemuxer, VideoConvertor, SponSkrub,
+                                     FixupStretched, FixupM4a and FixupM3u8. The
+                                     supported executables are: AtomicParsley,
+                                     FFmpeg, FFprobe, and SponSkrub. You can
                                      also specify "PP+EXE:ARGS" to give the
                                      arguments to the specified executable only
                                      when being used by the specified
                                      postprocessor. Additionally, for
-                                     ffmpeg/ffprobe, a number can be appended to
-                                     the exe name seperated by "_i" to pass the
-                                     argument before the specified input file.
-                                     Eg: --ppa "Merger+ffmpeg_i1:-v quiet". You
-                                     can use this option multiple times to give
+                                     ffmpeg/ffprobe, "_i"/"_o" can be appended
+                                     to the prefix optionally followed by a
+                                     number to pass the argument before the
+                                     specified input/output file. Eg: --ppa
+                                     "Merger+ffmpeg_i1:-v quiet". You can use
+                                     this option multiple times to give
                                      different arguments to different
                                      postprocessors. (Alias: --ppa)
     -k, --keep-video                 Keep the intermediate video file on disk
@@ -633,20 +681,9 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
     --no-embed-thumbnail             Do not embed thumbnail (default)
     --add-metadata                   Write metadata to the video file
     --no-add-metadata                Do not write metadata (default)
-    --parse-metadata FIELD:FORMAT    Parse additional metadata like title/artist
-                                     from other fields. Give field name to
-                                     extract data from, and format of the field
-                                     seperated by a ":". Either regular
-                                     expression with named capture groups or a
-                                     similar syntax to the output template can
-                                     also be used. The parsed parameters replace
-                                     any existing values and can be use in
-                                     output templateThis option can be used
-                                     multiple times. Example: --parse-metadata
-                                     "title:%(artist)s - %(title)s" matches a
-                                     title like "Coldplay - Paradise". Example
-                                     (regex): --parse-metadata
-                                     "description:Artist - (?P<artist>.+?)"
+    --parse-metadata FROM:TO         Parse additional metadata like title/artist
+                                     from other fields; see "MODIFYING METADATA"
+                                     for details
     --xattrs                         Write metadata to the video file's xattrs
                                      (using dublin core and xdg standards)
     --fixup POLICY                   Automatically correct known faults of the
@@ -658,11 +695,26 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      path to the binary or its containing
                                      directory
     --exec CMD                       Execute a command on the file after
-                                     downloading and post-processing, similar to
-                                     find's -exec syntax. Example: --exec 'adb
-                                     push {} /sdcard/Music/ && rm {}'
-    --convert-subs FORMAT            Convert the subtitles to other format
+                                     downloading and post-processing. Similar
+                                     syntax to the output template can be used
+                                     to pass any field as arguments to the
+                                     command. An additional field "filepath"
+                                     that contains the final path of the
+                                     downloaded file is also available. If no
+                                     fields are passed, "%(filepath)s" is
+                                     appended to the end of the command
+    --convert-subs FORMAT            Convert the subtitles to another format
                                      (currently supported: srt|ass|vtt|lrc)
+                                     (Alias: --convert-subtitles)
+    --convert-thumbnails FORMAT      Convert the thumbnails to another format
+                                     (currently supported: jpg)
+    --split-chapters                 Split video into multiple files based on
+                                     internal chapters. The "chapter:" prefix
+                                     can be used with "--paths" and "--output"
+                                     to set the output filename for the split
+                                     files. See "OUTPUT TEMPLATE" for details
+    --no-split-chapters              Do not split video based on chapters
+                                     (default)
 
 ## SponSkrub (SponsorBlock) Options:
 [SponSkrub](https://github.com/yt-dlp/SponSkrub) is a utility to
@@ -686,6 +738,8 @@ Then simply run `make`. You can also run `make youtube_dlc` instead to compile o
                                      directory
 
 ## Extractor Options:
+    --extractor-retries RETRIES      Number of retries for known extractor
+                                     errors (default is 3), or "infinite"
     --allow-dynamic-mpd              Process dynamic DASH manifests (default)
                                      (Alias: --no-ignore-dynamic-mpd)
     --ignore-dynamic-mpd             Do not process dynamic DASH manifests
@@ -776,9 +830,9 @@ The `-o` option is used to indicate a template for the output file names while `
 
 **tl;dr:** [navigate me to examples](#output-template-examples).
 
-The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `yt-dlp -o funny_video.flv "https://some/video"`. However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Date/time fields can also be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses seperated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
+The basic usage of `-o` is not to set any template arguments when downloading a single file, like in `yt-dlp -o funny_video.flv "https://some/video"` (hard-coding file extension like this is not recommended). However, it may contain special sequences that will be replaced when downloading each video. The special sequences may be formatted according to [python string formatting operations](https://docs.python.org/2/library/stdtypes.html#string-formatting). For example, `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations. Date/time fields can also be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it inside the parantheses separated from the field name using a `>`. For example, `%(duration>%H-%M-%S)s`.
 
-Additionally, you can set different output templates for the various metadata files seperately from the general output template by specifying the type of file followed by the template seperated by a colon ":". The different filetypes supported are `subtitle|thumbnail|description|annotation|infojson|pl_description|pl_infojson`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'`  will put the thumbnails in a folder with the same name as the video.
+Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different filetypes supported are `subtitle`, `thumbnail`, `description`, `annotation`, `infojson`, `pl_description`, `pl_infojson`, `chapter`. For example, `-o '%(title)s.%(ext)s' -o 'thumbnail:%(title)s\%(title)s.%(ext)s'`  will put the thumbnails in a folder with the same name as the video.
 
 The available fields are:
 
@@ -787,6 +841,7 @@ The available fields are:
  - `url` (string): Video URL
  - `ext` (string): Video filename extension
  - `alt_title` (string): A secondary title of the video
+ - `description` (string): The description of the video
  - `display_id` (string): An alternative identifier for the video
  - `uploader` (string): Full name of the video uploader
  - `license` (string): License name the video is licensed under
@@ -805,11 +860,12 @@ The available fields are:
  - `dislike_count` (numeric): Number of negative ratings of the video
  - `repost_count` (numeric): Number of reposts of the video
  - `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
- - `comment_count` (numeric): Number of comments on the video
+ - `comment_count` (numeric): Number of comments on the video (For some extractors, comments are only downloaded at the end, and so this field cannot be used)
  - `age_limit` (numeric): Age restriction for the video (years)
  - `is_live` (boolean): Whether this video is a live stream or a fixed-length video
  - `was_live` (boolean): Whether this video was originally a live stream
  - `playable_in_embed` (string): Whether this video is allowed to play in embedded players on other sites
+ - `availability` (string): Whether the video is 'private', 'premium_only', 'subscriber_only', 'needs_auth', 'unlisted' or 'public'
  - `start_time` (numeric): Time in seconds where the reproduction should start, as specified in the URL
  - `end_time` (numeric): Time in seconds where the reproduction should end, as specified in the URL
  - `format` (string): A human-readable description of the format
@@ -869,6 +925,13 @@ Available for the media that is a track or a part of a music album:
  - `disc_number` (numeric): Number of the disc or other physical medium the track belongs to
  - `release_year` (numeric): Year (YYYY) when the album was released
 
+Available for `chapter:` prefix when using `--split-chapters` for videos with internal chapters:
+
+ - `section_title` (string): Title of the chapter
+ - `section_number` (numeric): Number of the chapter within the file
+ - `section_start` (numeric): Start time of the chapter in seconds
+ - `section_end` (numeric): End time of the chapter in seconds
+
 Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. Note that some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
 
 For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKcj`, this will result in a `yt-dlp test video-BaW_jenozKcj.mp4` file created in the current directory.
@@ -901,7 +964,7 @@ youtube-dl_test_video_.mp4          # A simple file name
 # Download YouTube playlist videos in separate directory indexed by video order in a playlist
 $ yt-dlp -o '%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
 
-# Download YouTube playlist videos in seperate directories according to their uploaded year
+# Download YouTube playlist videos in separate directories according to their uploaded year
 $ yt-dlp -o '%(upload_date>%Y)s/%(title)s.%(ext)s' https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re
 
 # Download all playlists of YouTube channel/user keeping each playlist in separate directory:
@@ -922,7 +985,7 @@ $ yt-dlp -o - BaW_jenozKc
 By default, yt-dlp tries to download the best available quality if you **don't** pass any options.
 This is generally equivalent to using `-f bestvideo*+bestaudio/best`. However, if multiple audiostreams is enabled (`--audio-multistreams`), the default format changes to `-f bestvideo+bestaudio/best`. Similarly, if ffmpeg is unavailable, or if you use yt-dlp to stream to `stdout` (`-o -`), the default becomes `-f best/bestvideo+bestaudio`.
 
-The general syntax for format selection is `--f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
+The general syntax for format selection is `-f FORMAT` (or `--format FORMAT`) where `FORMAT` is a *selector expression*, i.e. an expression that describes format or formats you would like to download.
 
 **tl;dr:** [navigate me to examples](#format-selection-examples).
 
@@ -933,8 +996,9 @@ You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`,
 You can also use special names to select particular edge case formats:
 
  - `all`: Select all formats
- - `b*`, `best*`: Select the best quality format irrespective of whether it contains video or audio.
- - `w*`, `worst*`: Select the worst quality format irrespective of whether it contains video or audio.
+ - `mergeall`: Select and merge all formats (Must be used with `--audio-multistreams`, `--video-multistreams` or both)
+ - `b*`, `best*`: Select the best quality format irrespective of whether it contains video or audio
+ - `w*`, `worst*`: Select the worst quality format irrespective of whether it contains video or audio
  - `b`, `best`: Select the best quality format that contains both video and audio. Equivalent to `best*[vcodec!=none][acodec!=none]`
  - `w`, `worst`: Select the worst quality format that contains both video and audio. Equivalent to `worst*[vcodec!=none][acodec!=none]`
  - `bv`, `bestvideo`: Select the best quality video-only format. Equivalent to `best*[acodec=none]`
@@ -946,7 +1010,9 @@ You can also use special names to select particular edge case formats:
  - `ba*`, `bestaudio*`: Select the best quality format that contains audio. It may also contain video. Equivalent to `best*[acodec!=none]`
  - `wa*`, `worstaudio*`: Select the worst quality format that contains audio. It may also contain video. Equivalent to `worst*[acodec!=none]`
 
-For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recomended to never actually use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps` instead of `-f worst`. See [sorting formats](#sorting-formats) for more details.
+For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recomended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps` instead of `-f worst`. See [sorting formats](#sorting-formats) for more details.
+
+You can select the n'th best format of a type by using `best<type>.<n>`. For example, `best.2` will select the 2nd best combined format. Similarly, `bv*.3` will select the 3rd best format that contains a video stream.
 
 If you want to download multiple videos and they don't have the same formats available, you can specify the order of preference using slashes. Note that formats on the left hand side are preferred, for example `-f 22/17/18` will download format 22 if it's available, otherwise it will download format 17 if it's available, otherwise it will download format 18 if it's available, otherwise it will complain that no suitable formats are available for download.
 
@@ -1017,7 +1083,7 @@ You can change the criteria for being considered the `best` by using `-S` (`--fo
  - `br`: Equivalent to using `tbr,vbr,abr`
  - `asr`: Audio sample rate in Hz
 
-Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, seperated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
+Note that any other **numerical** field made available by the extractor can also be used. All fields, unless specified otherwise, are sorted in decending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a prefered value for the fields, separated by a `:`. Eg: `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two prefered values, the first for video and the second for audio. Eg: `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. Eg: `filesize~1G` prefers the format with filesize closest to 1 GiB.
 
 The fields `hasvid`, `ie_pref`, `lang` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--force-format-sort`. Apart from these, the default order used is: `quality,res,fps,codec:vp9.2,size,br,asr,proto,ext,hasaud,source,id`. Note that the extractors may override this default order, but they cannot override the user-provided order.
 
@@ -1046,10 +1112,17 @@ $ yt-dlp
 # by default, bestvideo and bestaudio will have the same file name.
 $ yt-dlp -f 'bv,ba' -o '%(title)s.f%(format_id)s.%(ext)s'
 
+# Download and merge the best format that has a video stream,
+# and all audio-only formats into one file
+$ yt-dlp -f 'bv*+mergeall[vcodec=none]' --audio-multistreams
+
+# Download and merge the best format that has a video stream,
+# and the best 2 audio-only formats into one file
+$ yt-dlp -f 'bv*+ba+ba.2' --audio-multistreams
 
 
 # The following examples show the old method (without -S) of format selection
-# and how to use -S to achieve a similar but better result
+# and how to use -S to achieve a similar but (generally) better result
 
 # Download the worst video available (old method)
 $ yt-dlp -f 'wv*+wa/w'
@@ -1130,7 +1203,7 @@ $ yt-dlp -S '+codec:h264'
 $ yt-dlp -f '((bv*[fps>30]/bv*)[height<=720]/(wv*[fps>30]/wv*)) + ba / (b[fps>30]/b)[height<=720]/(w[fps>30]/w)'
 
 # Download the video with the largest resolution no better than 720p,
-# or the video with the smallest resolution available  if there is no such video,
+# or the video with the smallest resolution available if there is no such video,
 # prefering larger framerate for formats with the same resolution
 $ yt-dlp -S 'res:720,fps'
 
@@ -1142,11 +1215,77 @@ $ yt-dlp -S 'res:720,fps'
 $ yt-dlp -S '+res:480,codec,br'
 ```
 
+# MODIFYING METADATA
+
+The metadata obtained the the extractors can be modified by using `--parse-metadata FROM:TO`. The general syntax is to give the name of a field or a template (with similar syntax to [output template](#output-template)) to extract data from, and the format to interpret it as, separated by a colon `:`. Either a [python regular expression](https://docs.python.org/3/library/re.html#regular-expression-syntax) with named capture groups or a similar syntax to the [output template](#output-template) (only `%(field)s` formatting is supported) can be used for `TO`. The option can be used multiple times to parse and modify various fields.
+
+Note that any field created by this can be used in the [output template](#output-template) and will also affect the media file's metadata added when using `--add-metadata`.
+
+You can also use this to change only the metadata that is embedded in the media file. To do this, set the value of the corresponding field with a `meta_` prefix. For example, any value you set to `meta_description` field will be added to the `description` field in the file. You can use this to set a different "description" and "synopsis", for example.
+
+## Modifying metadata examples
+
+Note that on Windows you may need to use double quotes instead of single.
+
+```bash
+# Interpret the title as "Artist - Title"
+$ yt-dlp --parse-metadata 'title:%(artist)s - %(title)s'
+
+# Regex example
+$ yt-dlp --parse-metadata 'description:Artist - (?P<artist>.+)'
+
+# Set title as "Series name S01E05"
+$ yt-dlp --parse-metadata '%(series)s S%(season_number)02dE%(episode_number)02d:%(title)s'
+
+# Set "comment" field in video metadata using description instead of webpage_url
+$ yt-dlp --parse-metadata 'description:(?s)(?P<meta_comment>.+)' --add-metadata
+
+```
+
 # PLUGINS
 
 Plugins are loaded from `<root-dir>/ytdlp_plugins/<type>/__init__.py`. Currently only `extractor` plugins are supported. Support for `downloader` and `postprocessor` plugins may be added in the future. See [ytdlp_plugins](ytdlp_plugins) for example.
 
 **Note**: `<root-dir>` is the directory of the binary (`<root-dir>/yt-dlp`), or the root directory of the module if you are running directly from source-code (`<root dir>/yt_dlp/__main__.py`)
 
+# DEPRECATED OPTIONS
+
+These are all the deprecated options and the current alternative to achieve the same effect
+
+    --cn-verification-proxy URL      --geo-verification-proxy URL
+    --id                             -o "%(id)s.%(ext)s"
+    -A, --auto-number                -o "%(autonumber)s-%(id)s.%(ext)s"
+    -t, --title                      -o "%(title)s-%(id)s.%(ext)s"
+    -l, --literal                    -o accepts literal names
+    --all-formats                    -f all
+    --autonumber-size NUMBER         Use string formatting. Eg: %(autonumber)03d
+    --metadata-from-title FORMAT     --parse-metadata "%(title)s:FORMAT"
+    --prefer-avconv                  avconv is no longer officially supported (Alias: --no-prefer-ffmpeg)
+    --prefer-ffmpeg                  Default (Alias: --no-prefer-avconv)
+    --hls-prefer-native              --downloader "m3u8:native"
+    --hls-prefer-ffmpeg              --downloader "m3u8:ffmpeg"
+    --avconv-location                avconv is no longer officially supported
+    -C, --call-home                  Not implemented
+    --no-call-home                   Default
+    --include-ads                    Not implemented
+    --no-include-ads                 Default
+    --write-srt                      --write-subs
+    --no-write-srt                   --no-write-subs
+    --srt-lang LANGS                 --sub-langs LANGS
+    --prefer-unsecure                --prefer-insecure
+    --rate-limit RATE                --limit-rate RATE
+    --force-write-download-archive   --force-write-archive
+    --dump-intermediate-pages        --dump-pages
+    --dump-headers                   --print-traffic
+    --youtube-print-sig-code         No longer supported
+    --trim-file-names LENGTH         --trim-filenames LENGTH
+    --yes-overwrites                 --force-overwrites
+    --load-info                      --load-info-json
+    --split-tracks                   --split-chapters
+    --no-split-tracks                --no-split-chapters
+    --sponskrub-args ARGS            --ppa "sponskrub:ARGS"
+    --test                           Only used for testing extractors
+
+
 # MORE
 For FAQ, Developer Instructions etc., see the [original README](https://github.com/ytdl-org/youtube-dl#faq)

devscripts/bash-completion.py

@@ -8,7 +8,7 @@ import sys
 sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import yt_dlp
 
-BASH_COMPLETION_FILE = "yt-dlp.bash-completion"
+BASH_COMPLETION_FILE = "completions/bash/yt-dlp"
 BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
 
 

devscripts/fish-completion.py

@@ -10,7 +10,7 @@ sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import yt_dlp
 from yt_dlp.utils import shell_quote
 
-FISH_COMPLETION_FILE = 'yt-dlp.fish'
+FISH_COMPLETION_FILE = 'completions/fish/yt-dlp.fish'
 FISH_COMPLETION_TEMPLATE = 'devscripts/fish-completion.in'
 
 EXTRA_ARGS = {

devscripts/release.sh

@@ -61,7 +61,7 @@ if ! type pandoc >/dev/null 2>/dev/null; then echo 'ERROR: pandoc is missing'; e
 if ! python3 -c 'import rsa' 2>/dev/null; then echo 'ERROR: python3-rsa is missing'; exit 1; fi
 if ! python3 -c 'import wheel' 2>/dev/null; then echo 'ERROR: wheel is missing'; exit 1; fi
 
-read -p "Is ChangeLog up to date? (y/n) " -n 1
+read -p "Is Changelog up to date? (y/n) " -n 1
 if [[ ! $REPLY =~ ^[Yy]$ ]]; then exit 1; fi
 
 /bin/echo -e "\n### First of all, testing..."
@@ -75,12 +75,12 @@ fi
 /bin/echo -e "\n### Changing version in version.py..."
 sed -i "s/__version__ = '.*'/__version__ = '$version'/" yt_dlp/version.py
 
-/bin/echo -e "\n### Changing version in ChangeLog..."
-sed -i "s/<unreleased>/$version/" ChangeLog
+/bin/echo -e "\n### Changing version in Changelog..."
+sed -i "s/<unreleased>/$version/" Changelog.md
 
 /bin/echo -e "\n### Committing documentation, templates and yt_dlp/version.py..."
 make README.md CONTRIBUTING.md issuetemplates supportedsites
-git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE/1_broken_site.md .github/ISSUE_TEMPLATE/2_site_support_request.md .github/ISSUE_TEMPLATE/3_site_feature_request.md .github/ISSUE_TEMPLATE/4_bug_report.md .github/ISSUE_TEMPLATE/5_feature_request.md .github/ISSUE_TEMPLATE/6_question.md docs/supportedsites.md yt_dlp/version.py ChangeLog
+git add README.md CONTRIBUTING.md .github/ISSUE_TEMPLATE/1_broken_site.md .github/ISSUE_TEMPLATE/2_site_support_request.md .github/ISSUE_TEMPLATE/3_site_feature_request.md .github/ISSUE_TEMPLATE/4_bug_report.md .github/ISSUE_TEMPLATE/5_feature_request.md .github/ISSUE_TEMPLATE/6_question.md docs/supportedsites.md yt_dlp/version.py Changelog.md
 git commit $gpg_sign_commits -m "release $version"
 
 /bin/echo -e "\n### Now tagging, signing and pushing..."
@@ -111,7 +111,7 @@ RELEASE_FILES="yt-dlp yt-dlp.exe yt-dlp-$version.tar.gz"
 for f in $RELEASE_FILES; do gpg --passphrase-repeat 5 --detach-sig "build/$version/$f"; done
 
 ROOT=$(pwd)
-python devscripts/create-github-release.py ChangeLog $version "$ROOT/build/$version"
+python devscripts/create-github-release.py Changelog.md $version "$ROOT/build/$version"
 
 ssh ytdl@yt-dl.org "sh html/update_latest.sh $version"
 

devscripts/zsh-completion.py

@@ -8,7 +8,7 @@ import sys
 sys.path.insert(0, dirn(dirn((os.path.abspath(__file__)))))
 import yt_dlp
 
-ZSH_COMPLETION_FILE = "yt-dlp.zsh"
+ZSH_COMPLETION_FILE = "completions/zsh/_yt-dlp"
 ZSH_COMPLETION_TEMPLATE = "devscripts/zsh-completion.in"
 
 

docs/Changelog.md

@@ -0,0 +1,5 @@
+---
+orphan: true
+---
+```{include} ../Changelog.md
+```

docs/LICENSE.md

@@ -0,0 +1,6 @@
+---
+orphan: true
+---
+# LICENSE
+```{include} ../LICENSE
+```

docs/README.md

@@ -0,0 +1,2 @@
+```{include} ../README.md
+```

docs/conf.py

@@ -7,26 +7,21 @@ import os
 
 # Allows to import yt-dlp
 sys.path.insert(0, os.path.abspath('..'))
-from recommonmark.transform import AutoStructify
 
 # -- General configuration ------------------------------------------------
 
-# The suffix of source filenames.
-source_suffix = ['.rst', '.md']
-
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'recommonmark',
+    'myst_parser',
 ]
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ['_templates']
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = 'README'
 
 # General information about the project.
 project = u'yt-dlp'
@@ -64,12 +59,10 @@ highlight_language = 'none'
 # so a file named "default.css" will overwrite the builtin "default.css".
 # html_static_path = ['_static']
 
+# Enable heading anchors
+myst_heading_anchors = 4
 
-def setup(app):
-    app.add_config_value('recommonmark_config', {
-        'enable_math': False,
-        'enable_inline_math': False,
-        'enable_eval_rst': True,
-        'enable_auto_toc_tree': True,
-    }, True)
-    app.add_transform(AutoStructify)
+# Suppress heading warnings
+suppress_warnings = [
+    'myst.header',
+]

docs/index.md

@@ -1 +0,0 @@
-../README.md

docs/requirements.txt

@@ -1,2 +1 @@
-recommonmark>=0.6.0
-m2r2
+myst-parser

docs/ytdlp_plugins.md

@@ -0,0 +1,6 @@
+---
+orphan: true
+---
+# ytdlp_plugins
+
+See [https://github.com/yt-dlp/yt-dlp/tree/master/ytdlp_plugins](https://github.com/yt-dlp/yt-dlp/tree/master/ytdlp_plugins).

setup.py

@@ -27,8 +27,9 @@ if len(sys.argv) >= 2 and sys.argv[1] == 'py2exe':
     print("inv")
 else:
     files_spec = [
-        ('etc/bash_completion.d', ['yt-dlp.bash-completion']),
-        ('etc/fish/completions', ['yt-dlp.fish']),
+        ('share/bash-completion/completions', ['completions/bash/yt-dlp']),
+        ('share/zsh/site-functions', ['completions/zsh/_yt-dlp']),
+        ('share/fish/vendor_completions.d', ['completions/fish/yt-dlp.fish']),
         ('share/doc/yt_dlp', ['README.txt']),
         ('share/man/man1', ['yt-dlp.1'])
     ]
@@ -38,7 +39,7 @@ else:
         resfiles = []
         for fn in files:
             if not os.path.exists(fn):
-                warnings.warn('Skipping file %s since it is not present. Type  make  to build all automatically generated files.' % fn)
+                warnings.warn('Skipping file %s since it is not present. Try running `make pypi-files` first.' % fn)
             else:
                 resfiles.append(fn)
         data_files.append((dirname, resfiles))
@@ -86,7 +87,7 @@ setup(
         #'Funding': 'https://donate.pypi.org',
     },
     classifiers=[
-	    "Topic :: Multimedia :: Video",
+        "Topic :: Multimedia :: Video",
         "Development Status :: 5 - Production/Stable",
         "Environment :: Console",
         "Programming Language :: Python",
@@ -110,7 +111,7 @@ setup(
         "Operating System :: OS Independent",
     ],
     python_requires='>=2.6',
-	
-	cmdclass={'build_lazy_extractors': build_lazy_extractors},
+
+    cmdclass={'build_lazy_extractors': build_lazy_extractors},
     **params
 )

test/test_all_urls.py

@@ -37,7 +37,6 @@ class TestAllURLsMatching(unittest.TestCase):
         assertPlaylist('PL63F0C78739B09958')
         assertTab('https://www.youtube.com/AsapSCIENCE')
         assertTab('https://www.youtube.com/embedded')
-        assertTab('https://www.youtube.com/feed')  # Own channel's home page
         assertTab('https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q')
         assertTab('https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8')
         assertTab('https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC')

test/test_postprocessors.py

@@ -14,10 +14,10 @@ from yt_dlp.postprocessor import MetadataFromFieldPP, MetadataFromTitlePP
 class TestMetadataFromField(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromFieldPP(None, ['title:%(title)s - %(artist)s'])
-        self.assertEqual(pp._data[0]['regex'], r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')
+        self.assertEqual(pp._data[0]['regex'], r'(?P<title>.+)\ \-\ (?P<artist>.+)')
 
 
 class TestMetadataFromTitle(unittest.TestCase):
     def test_format_to_regex(self):
         pp = MetadataFromTitlePP(None, '%(title)s - %(artist)s')
-        self.assertEqual(pp._titleregex, r'(?P<title>[^\r\n]+)\ \-\ (?P<artist>[^\r\n]+)')
+        self.assertEqual(pp._titleregex, r'(?P<title>.+)\ \-\ (?P<artist>.+)')

test/test_utils.py

@@ -23,6 +23,7 @@ from yt_dlp.utils import (
     clean_html,
     clean_podcast_url,
     date_from_str,
+    datetime_from_str,
     DateRange,
     detect_exe_version,
     determine_ext,
@@ -311,8 +312,18 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(date_from_str('yesterday'), date_from_str('now-1day'))
         self.assertEqual(date_from_str('now+7day'), date_from_str('now+1week'))
         self.assertEqual(date_from_str('now+14day'), date_from_str('now+2week'))
-        self.assertEqual(date_from_str('now+365day'), date_from_str('now+1year'))
-        self.assertEqual(date_from_str('now+30day'), date_from_str('now+1month'))
+        self.assertEqual(date_from_str('20200229+365day'), date_from_str('20200229+1year'))
+        self.assertEqual(date_from_str('20210131+28day'), date_from_str('20210131+1month'))
+
+    def test_datetime_from_str(self):
+        self.assertEqual(datetime_from_str('yesterday', precision='day'), datetime_from_str('now-1day', precision='auto'))
+        self.assertEqual(datetime_from_str('now+7day', precision='day'), datetime_from_str('now+1week', precision='auto'))
+        self.assertEqual(datetime_from_str('now+14day', precision='day'), datetime_from_str('now+2week', precision='auto'))
+        self.assertEqual(datetime_from_str('20200229+365day', precision='day'), datetime_from_str('20200229+1year', precision='auto'))
+        self.assertEqual(datetime_from_str('20210131+28day', precision='day'), datetime_from_str('20210131+1month', precision='auto'))
+        self.assertEqual(datetime_from_str('20210131+59day', precision='day'), datetime_from_str('20210131+2month', precision='auto'))
+        self.assertEqual(datetime_from_str('now+1day', precision='hour'), datetime_from_str('now+24hours', precision='auto'))
+        self.assertEqual(datetime_from_str('now+23hours', precision='hour'), datetime_from_str('now+23hours', precision='auto'))
 
     def test_daterange(self):
         _20century = DateRange("19000101", "20000101")

yt_dlp/__init__.py

@@ -169,25 +169,35 @@ def _real_main(argv=None):
             parser.error('max sleep interval must be greater than or equal to min sleep interval')
     else:
         opts.max_sleep_interval = opts.sleep_interval
+    if opts.sleep_interval_subtitles is not None:
+        if opts.sleep_interval_subtitles < 0:
+            parser.error('subtitles sleep interval must be positive or 0')
+    if opts.sleep_interval_requests is not None:
+        if opts.sleep_interval_requests < 0:
+            parser.error('requests sleep interval must be positive or 0')
     if opts.ap_mso and opts.ap_mso not in MSO_INFO:
         parser.error('Unsupported TV Provider, use --ap-list-mso to get a list of supported TV Providers')
     if opts.overwrites:
         # --yes-overwrites implies --no-continue
         opts.continue_dl = False
+    if opts.concurrent_fragment_downloads <= 0:
+        raise ValueError('Concurrent fragments must be positive')
 
-    def parse_retries(retries):
+    def parse_retries(retries, name=''):
         if retries in ('inf', 'infinite'):
             parsed_retries = float('inf')
         else:
             try:
                 parsed_retries = int(retries)
             except (TypeError, ValueError):
-                parser.error('invalid retry count specified')
+                parser.error('invalid %sretry count specified' % name)
         return parsed_retries
     if opts.retries is not None:
         opts.retries = parse_retries(opts.retries)
     if opts.fragment_retries is not None:
-        opts.fragment_retries = parse_retries(opts.fragment_retries)
+        opts.fragment_retries = parse_retries(opts.fragment_retries, 'fragment ')
+    if opts.extractor_retries is not None:
+        opts.extractor_retries = parse_retries(opts.extractor_retries, 'extractor ')
     if opts.buffersize is not None:
         numeric_buffersize = FileDownloader.parse_bytes(opts.buffersize)
         if numeric_buffersize is None:
@@ -218,8 +228,11 @@ def _real_main(argv=None):
         if not re.match(remux_regex, opts.remuxvideo):
             parser.error('invalid video remux format specified')
     if opts.convertsubtitles is not None:
-        if opts.convertsubtitles not in ['srt', 'vtt', 'ass', 'lrc']:
+        if opts.convertsubtitles not in ('srt', 'vtt', 'ass', 'lrc'):
             parser.error('invalid subtitle format specified')
+    if opts.convertthumbnails is not None:
+        if opts.convertthumbnails not in ('jpg', ):
+            parser.error('invalid thumbnail format specified')
 
     if opts.date is not None:
         date = DateRange.day(opts.date)
@@ -262,11 +275,21 @@ def _real_main(argv=None):
     any_printing = opts.print_json
     download_archive_fn = expand_path(opts.download_archive) if opts.download_archive is not None else opts.download_archive
 
+    # If JSON is not printed anywhere, but comments are requested, save it to file
+    printing_json = opts.dumpjson or opts.print_json or opts.dump_single_json
+    if opts.getcomments and not printing_json:
+        opts.writeinfojson = True
+
     def report_conflict(arg1, arg2):
         write_string('WARNING: %s is ignored since %s was given\n' % (arg2, arg1), out=sys.stderr)
+
     if opts.remuxvideo and opts.recodevideo:
         report_conflict('--recode-video', '--remux-video')
         opts.remuxvideo = False
+    if opts.sponskrub_cut and opts.split_chapters and opts.sponskrub is not False:
+        report_conflict('--split-chapter', '--sponskrub-cut')
+        opts.sponskrub_cut = False
+
     if opts.allow_unplayable_formats:
         if opts.extractaudio:
             report_conflict('--allow-unplayable-formats', '--extract-audio')
@@ -302,7 +325,22 @@ def _real_main(argv=None):
         postprocessors.append({
             'key': 'MetadataFromField',
             'formats': opts.metafromfield,
-            'when': 'beforedl'
+            # Run this immediately after extraction is complete
+            'when': 'pre_process'
+        })
+    if opts.convertsubtitles:
+        postprocessors.append({
+            'key': 'FFmpegSubtitlesConvertor',
+            'format': opts.convertsubtitles,
+            # Run this before the actual video download
+            'when': 'before_dl'
+        })
+    if opts.convertthumbnails:
+        postprocessors.append({
+            'key': 'FFmpegThumbnailsConvertor',
+            'format': opts.convertthumbnails,
+            # Run this before the actual video download
+            'when': 'before_dl'
         })
     if opts.extractaudio:
         postprocessors.append({
@@ -331,15 +369,11 @@ def _real_main(argv=None):
     # so metadata can be added here.
     if opts.addmetadata:
         postprocessors.append({'key': 'FFmpegMetadata'})
-    if opts.convertsubtitles:
-        postprocessors.append({
-            'key': 'FFmpegSubtitlesConvertor',
-            'format': opts.convertsubtitles,
-        })
     if opts.embedsubtitles:
         already_have_subtitle = opts.writesubtitles
         postprocessors.append({
             'key': 'FFmpegEmbedSubtitle',
+            # already_have_subtitle = True prevents the file from being deleted after embedding
             'already_have_subtitle': already_have_subtitle
         })
         if not already_have_subtitle:
@@ -348,19 +382,9 @@ def _real_main(argv=None):
     # this was the old behaviour if only --all-sub was given.
     if opts.allsubtitles and not opts.writeautomaticsub:
         opts.writesubtitles = True
-    if opts.embedthumbnail:
-        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
-        postprocessors.append({
-            'key': 'EmbedThumbnail',
-            'already_have_thumbnail': already_have_thumbnail
-        })
-        if not already_have_thumbnail:
-            opts.writethumbnail = True
-    # XAttrMetadataPP should be run after post-processors that may change file
-    # contents
-    if opts.xattrs:
-        postprocessors.append({'key': 'XAttrMetadata'})
-    # This should be below all ffmpeg PP because it may cut parts out from the video
+    # This should be above EmbedThumbnail since sponskrub removes the thumbnail attachment
+    # but must be below EmbedSubtitle and FFmpegMetadata
+    # See https://github.com/yt-dlp/yt-dlp/issues/204 , https://github.com/faissaloo/SponSkrub/issues/29
     # If opts.sponskrub is None, sponskrub is used, but it silently fails if the executable can't be found
     if opts.sponskrub is not False:
         postprocessors.append({
@@ -371,12 +395,27 @@ def _real_main(argv=None):
             'force': opts.sponskrub_force,
             'ignoreerror': opts.sponskrub is None,
         })
+    if opts.embedthumbnail:
+        already_have_thumbnail = opts.writethumbnail or opts.write_all_thumbnails
+        postprocessors.append({
+            'key': 'EmbedThumbnail',
+            # already_have_thumbnail = True prevents the file from being deleted after embedding
+            'already_have_thumbnail': already_have_thumbnail
+        })
+        if not already_have_thumbnail:
+            opts.writethumbnail = True
+    if opts.split_chapters:
+        postprocessors.append({'key': 'FFmpegSplitChapters'})
+    # XAttrMetadataPP should be run after post-processors that may change file contents
+    if opts.xattrs:
+        postprocessors.append({'key': 'XAttrMetadata'})
     # ExecAfterDownload must be the last PP
     if opts.exec_cmd:
         postprocessors.append({
             'key': 'ExecAfterDownload',
             'exec_cmd': opts.exec_cmd,
-            'when': 'aftermove'
+            # Run this only after the files have been moved to their final locations
+            'when': 'after_move'
         })
 
     def report_args_compat(arg, name):
@@ -402,7 +441,6 @@ def _real_main(argv=None):
         else match_filter_func(opts.match_filter))
 
     ydl_opts = {
-        'convertsubtitles': opts.convertsubtitles,
         'usenetrc': opts.usenetrc,
         'username': opts.username,
         'password': opts.password,
@@ -447,8 +485,10 @@ def _real_main(argv=None):
         'overwrites': opts.overwrites,
         'retries': opts.retries,
         'fragment_retries': opts.fragment_retries,
+        'extractor_retries': opts.extractor_retries,
         'skip_unavailable_fragments': opts.skip_unavailable_fragments,
         'keep_fragments': opts.keep_fragments,
+        'concurrent_fragment_downloads': opts.concurrent_fragment_downloads,
         'buffersize': opts.buffersize,
         'noresizebuffer': opts.noresizebuffer,
         'http_chunk_size': opts.http_chunk_size,
@@ -466,8 +506,9 @@ def _real_main(argv=None):
         'updatetime': opts.updatetime,
         'writedescription': opts.writedescription,
         'writeannotations': opts.writeannotations,
-        'writeinfojson': opts.writeinfojson or opts.getcomments,
+        'writeinfojson': opts.writeinfojson,
         'allow_playlist_files': opts.allow_playlist_files,
+        'clean_infojson': opts.clean_infojson,
         'getcomments': opts.getcomments,
         'writethumbnail': opts.writethumbnail,
         'write_all_thumbnails': opts.write_all_thumbnails,
@@ -524,6 +565,7 @@ def _real_main(argv=None):
         'fixup': opts.fixup,
         'source_address': opts.source_address,
         'call_home': opts.call_home,
+        'sleep_interval_requests': opts.sleep_interval_requests,
         'sleep_interval': opts.sleep_interval,
         'max_sleep_interval': opts.max_sleep_interval,
         'sleep_interval_subtitles': opts.sleep_interval_subtitles,
@@ -541,7 +583,6 @@ def _real_main(argv=None):
         'postprocessor_args': opts.postprocessor_args,
         'cn_verification_proxy': opts.cn_verification_proxy,
         'geo_verification_proxy': opts.geo_verification_proxy,
-        'config_location': opts.config_location,
         'geo_bypass': opts.geo_bypass,
         'geo_bypass_country': opts.geo_bypass_country,
         'geo_bypass_ip_block': opts.geo_bypass_ip_block,

yt_dlp/compat.py

@@ -78,6 +78,15 @@ try:
 except ImportError:  # Python 2
     import Cookie as compat_cookies
 
+if sys.version_info[0] == 2:
+    class compat_cookies_SimpleCookie(compat_cookies.SimpleCookie):
+        def load(self, rawdata):
+            if isinstance(rawdata, compat_str):
+                rawdata = str(rawdata)
+            return super(compat_cookies_SimpleCookie, self).load(rawdata)
+else:
+    compat_cookies_SimpleCookie = compat_cookies.SimpleCookie
+
 try:
     import html.entities as compat_html_entities
 except ImportError:  # Python 2
@@ -3020,6 +3029,7 @@ __all__ = [
     'compat_cookiejar',
     'compat_cookiejar_Cookie',
     'compat_cookies',
+    'compat_cookies_SimpleCookie',
     'compat_ctypes_WINFUNCTYPE',
     'compat_etree_Element',
     'compat_etree_fromstring',

yt_dlp/downloader/__init__.py

@@ -1,5 +1,6 @@
 from __future__ import unicode_literals
 
+from ..compat import compat_str
 from ..utils import (
     determine_protocol,
 )
@@ -42,6 +43,23 @@ PROTOCOL_MAP = {
 }
 
 
+def shorten_protocol_name(proto, simplify=False):
+    short_protocol_names = {
+        'm3u8_native': 'm3u8_n',
+        'http_dash_segments': 'dash',
+        'niconico_dmc': 'dmc',
+    }
+    if simplify:
+        short_protocol_names.update({
+            'https': 'http',
+            'ftps': 'ftp',
+            'm3u8_native': 'm3u8',
+            'm3u8_frag_urls': 'm3u8',
+            'dash_frag_urls': 'dash',
+        })
+    return short_protocol_names.get(proto, proto)
+
+
 def get_suitable_downloader(info_dict, params={}, default=HttpFD):
     """Get the downloader class that can handle the info dict."""
     protocol = determine_protocol(info_dict)
@@ -50,15 +68,23 @@ def get_suitable_downloader(info_dict, params={}, default=HttpFD):
     # if (info_dict.get('start_time') or info_dict.get('end_time')) and not info_dict.get('requested_formats') and FFmpegFD.can_download(info_dict):
     #     return FFmpegFD
 
-    external_downloader = params.get('external_downloader')
-    if external_downloader is not None:
+    downloaders = params.get('external_downloader')
+    external_downloader = (
+        downloaders if isinstance(downloaders, compat_str) or downloaders is None
+        else downloaders.get(shorten_protocol_name(protocol, True), downloaders.get('default')))
+    if external_downloader and external_downloader.lower() == 'native':
+        external_downloader = 'native'
+
+    if external_downloader not in (None, 'native'):
         ed = get_external_downloader(external_downloader)
-        if ed.can_download(info_dict):
+        if ed.can_download(info_dict, external_downloader):
             return ed
 
     if protocol.startswith('m3u8'):
         if info_dict.get('is_live'):
             return FFmpegFD
+        elif external_downloader == 'native':
+            return HlsFD
         elif _get_real_downloader(info_dict, 'frag_urls', params, None):
             return HlsFD
         elif params.get('hls_prefer_native') is True:
@@ -70,6 +96,7 @@ def get_suitable_downloader(info_dict, params={}, default=HttpFD):
 
 
 __all__ = [
-    'get_suitable_downloader',
     'FileDownloader',
+    'get_suitable_downloader',
+    'shorten_protocol_name',
 ]

yt_dlp/downloader/common.py

@@ -312,7 +312,7 @@ class FileDownloader(object):
     def report_retry(self, err, count, retries):
         """Report retry in case of HTTP error 5xx"""
         self.to_screen(
-            '[download] Got server HTTP error: %s. Retrying (attempt %d of %s)...'
+            '[download] Got server HTTP error: %s. Retrying (attempt %d of %s) ...'
             % (error_to_compat_str(err), count, self.format_retries(retries)))
 
     def report_file_already_downloaded(self, file_name):
@@ -326,6 +326,12 @@ class FileDownloader(object):
         """Report it was impossible to resume download."""
         self.to_screen('[download] Unable to resume')
 
+    @staticmethod
+    def supports_manifest(manifest):
+        """ Whether the downloader can download the fragments from the manifest.
+        Redefine in subclasses if needed. """
+        pass
+
     def download(self, filename, info_dict, subtitle=False):
         """Download to a filename using the info from info_dict
         Return True on success and False otherwise
@@ -359,7 +365,7 @@ class FileDownloader(object):
                 max_sleep_interval = self.params.get('max_sleep_interval', min_sleep_interval)
                 sleep_interval = random.uniform(min_sleep_interval, max_sleep_interval)
                 self.to_screen(
-                    '[download] Sleeping %s seconds...' % (
+                    '[download] Sleeping %s seconds ...' % (
                         int(sleep_interval) if sleep_interval.is_integer()
                         else '%.2f' % sleep_interval))
                 time.sleep(sleep_interval)
@@ -369,7 +375,7 @@ class FileDownloader(object):
                 sleep_interval_sub = self.params.get('sleep_interval_subtitles')
             if sleep_interval_sub > 0:
                 self.to_screen(
-                    '[download] Sleeping %s seconds...' % (
+                    '[download] Sleeping %s seconds ...' % (
                         sleep_interval_sub))
                 time.sleep(sleep_interval_sub)
         return self.real_download(filename, info_dict), True

yt_dlp/downloader/dash.py

@@ -1,18 +1,26 @@
 from __future__ import unicode_literals
 
+try:
+    import concurrent.futures
+    can_threaded_download = True
+except ImportError:
+    can_threaded_download = False
+
 from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
 
 from ..compat import compat_urllib_error
 from ..utils import (
     DownloadError,
+    sanitize_open,
     urljoin,
 )
 
 
 class DashSegmentsFD(FragmentFD):
     """
-    Download segments in a DASH manifest
+    Download segments in a DASH manifest. External downloaders can take over
+    the fragment downloads by supporting the 'dash_frag_urls' protocol
     """
 
     FD_NAME = 'dashsegments'
@@ -22,7 +30,7 @@ class DashSegmentsFD(FragmentFD):
         fragments = info_dict['fragments'][:1] if self.params.get(
             'test', False) else info_dict['fragments']
 
-        real_downloader = _get_real_downloader(info_dict, 'frag_urls', self.params, None)
+        real_downloader = _get_real_downloader(info_dict, 'dash_frag_urls', self.params, None)
 
         ctx = {
             'filename': filename,
@@ -37,7 +45,7 @@ class DashSegmentsFD(FragmentFD):
         fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        fragment_urls = []
+        fragments_to_download = []
         frag_index = 0
         for i, fragment in enumerate(fragments):
             frag_index += 1
@@ -48,49 +56,17 @@ class DashSegmentsFD(FragmentFD):
                 assert fragment_base_url
                 fragment_url = urljoin(fragment_base_url, fragment['path'])
 
-            if real_downloader:
-                fragment_urls.append(fragment_url)
-                continue
-
-            # In DASH, the first segment contains necessary headers to
-            # generate a valid MP4 file, so always abort for the first segment
-            fatal = i == 0 or not skip_unavailable_fragments
-            count = 0
-            while count <= fragment_retries:
-                try:
-                    success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
-                    if not success:
-                        return False
-                    self._append_fragment(ctx, frag_content)
-                    break
-                except compat_urllib_error.HTTPError as err:
-                    # YouTube may often return 404 HTTP error for a fragment causing the
-                    # whole download to fail. However if the same fragment is immediately
-                    # retried with the same request data this usually succeeds (1-2 attempts
-                    # is usually enough) thus allowing to download the whole file successfully.
-                    # To be future-proof we will retry all fragments that fail with any
-                    # HTTP error.
-                    count += 1
-                    if count <= fragment_retries:
-                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
-                except DownloadError:
-                    # Don't retry fragment if error occurred during HTTP downloading
-                    # itself since it has own retry settings
-                    if not fatal:
-                        self.report_skip_fragment(frag_index)
-                        break
-                    raise
-
-            if count > fragment_retries:
-                if not fatal:
-                    self.report_skip_fragment(frag_index)
-                    continue
-                self.report_error('giving up after %s fragment retries' % fragment_retries)
-                return False
+            fragments_to_download.append({
+                'frag_index': frag_index,
+                'index': i,
+                'url': fragment_url,
+            })
 
         if real_downloader:
+            self.to_screen(
+                '[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
             info_copy = info_dict.copy()
-            info_copy['url_list'] = fragment_urls
+            info_copy['fragments'] = fragments_to_download
             fd = real_downloader(self.ydl, self.params)
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
@@ -99,5 +75,104 @@ class DashSegmentsFD(FragmentFD):
             if not success:
                 return False
         else:
+            def download_fragment(fragment):
+                i = fragment['index']
+                frag_index = fragment['frag_index']
+                fragment_url = fragment['url']
+
+                ctx['fragment_index'] = frag_index
+
+                # In DASH, the first segment contains necessary headers to
+                # generate a valid MP4 file, so always abort for the first segment
+                fatal = i == 0 or not skip_unavailable_fragments
+                count = 0
+                while count <= fragment_retries:
+                    try:
+                        success, frag_content = self._download_fragment(ctx, fragment_url, info_dict)
+                        if not success:
+                            return False, frag_index
+                        break
+                    except compat_urllib_error.HTTPError as err:
+                        # YouTube may often return 404 HTTP error for a fragment causing the
+                        # whole download to fail. However if the same fragment is immediately
+                        # retried with the same request data this usually succeeds (1-2 attempts
+                        # is usually enough) thus allowing to download the whole file successfully.
+                        # To be future-proof we will retry all fragments that fail with any
+                        # HTTP error.
+                        count += 1
+                        if count <= fragment_retries:
+                            self.report_retry_fragment(err, frag_index, count, fragment_retries)
+                    except DownloadError:
+                        # Don't retry fragment if error occurred during HTTP downloading
+                        # itself since it has own retry settings
+                        if not fatal:
+                            break
+                        raise
+
+                if count > fragment_retries:
+                    if not fatal:
+                        return False, frag_index
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return False, frag_index
+
+                return frag_content, frag_index
+
+            def append_fragment(frag_content, frag_index):
+                if frag_content:
+                    fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], frag_index)
+                    try:
+                        file, frag_sanitized = sanitize_open(fragment_filename, 'rb')
+                        ctx['fragment_filename_sanitized'] = frag_sanitized
+                        file.close()
+                        self._append_fragment(ctx, frag_content)
+                        return True
+                    except FileNotFoundError:
+                        if skip_unavailable_fragments:
+                            self.report_skip_fragment(frag_index)
+                            return True
+                        else:
+                            self.report_error(
+                                'fragment %s not found, unable to continue' % frag_index)
+                            return False
+                else:
+                    if skip_unavailable_fragments:
+                        self.report_skip_fragment(frag_index)
+                        return True
+                    else:
+                        self.report_error(
+                            'fragment %s not found, unable to continue' % frag_index)
+                        return False
+
+            max_workers = self.params.get('concurrent_fragment_downloads', 1)
+            if can_threaded_download and max_workers > 1:
+                self.report_warning('The download speed shown is only of one thread. This is a known issue')
+                with concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
+                    futures = [pool.submit(download_fragment, fragment) for fragment in fragments_to_download]
+                    # timeout must be 0 to return instantly
+                    done, not_done = concurrent.futures.wait(futures, timeout=0)
+                    try:
+                        while not_done:
+                            # Check every 1 second for KeyboardInterrupt
+                            freshly_done, not_done = concurrent.futures.wait(not_done, timeout=1)
+                            done |= freshly_done
+                    except KeyboardInterrupt:
+                        for future in not_done:
+                            future.cancel()
+                        # timeout must be none to cancel
+                        concurrent.futures.wait(not_done, timeout=None)
+                        raise KeyboardInterrupt
+                results = [future.result() for future in futures]
+
+                for frag_content, frag_index in results:
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+            else:
+                for fragment in fragments_to_download:
+                    frag_content, frag_index = download_fragment(fragment)
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+
             self._finish_frag_download(ctx)
         return True

yt_dlp/downloader/external.py

@@ -24,7 +24,6 @@ from ..utils import (
     cli_bool_option,
     cli_configuration_args,
     encodeFilename,
-    error_to_compat_str,
     encodeArgument,
     handle_youtubedl_headers,
     check_executable,
@@ -82,19 +81,23 @@ class ExternalFD(FileDownloader):
 
     @property
     def exe(self):
-        return self.params.get('external_downloader')
+        return self.get_basename()
 
     @classmethod
-    def available(cls):
-        return check_executable(cls.get_basename(), [cls.AVAILABLE_OPT])
+    def available(cls, path=None):
+        path = check_executable(path or cls.get_basename(), [cls.AVAILABLE_OPT])
+        if path:
+            cls.exe = path
+            return path
+        return False
 
     @classmethod
     def supports(cls, info_dict):
         return info_dict['protocol'] in cls.SUPPORTED_PROTOCOLS
 
     @classmethod
-    def can_download(cls, info_dict):
-        return cls.available() and cls.supports(info_dict)
+    def can_download(cls, info_dict, path=None):
+        return cls.available(path) and cls.supports(info_dict)
 
     def _option(self, command_option, param):
         return cli_option(self.params, command_option, param)
@@ -108,7 +111,8 @@ class ExternalFD(FileDownloader):
     def _configuration_args(self, *args, **kwargs):
         return cli_configuration_args(
             self.params.get('external_downloader_args'),
-            self.get_basename(), *args, **kwargs)
+            [self.get_basename(), 'default'],
+            *args, **kwargs)
 
     def _call_downloader(self, tmpfilename, info_dict):
         """ Either overwrite this or implement _make_cmd """
@@ -116,24 +120,43 @@ class ExternalFD(FileDownloader):
 
         self._debug_cmd(cmd)
 
-        p = subprocess.Popen(
-            cmd, stderr=subprocess.PIPE)
-        _, stderr = process_communicate_or_kill(p)
-        if p.returncode != 0:
-            self.to_stderr(stderr.decode('utf-8', 'replace'))
+        if 'fragments' in info_dict:
+            fragment_retries = self.params.get('fragment_retries', 0)
+            skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
+
+            count = 0
+            while count <= fragment_retries:
+                p = subprocess.Popen(
+                    cmd, stderr=subprocess.PIPE)
+                _, stderr = process_communicate_or_kill(p)
+                if p.returncode == 0:
+                    break
+                # TODO: Decide whether to retry based on error code
+                # https://aria2.github.io/manual/en/html/aria2c.html#exit-status
+                self.to_stderr(stderr.decode('utf-8', 'replace'))
+                count += 1
+                if count <= fragment_retries:
+                    self.to_screen(
+                        '[%s] Got error. Retrying fragments (attempt %d of %s)...'
+                        % (self.get_basename(), count, self.format_retries(fragment_retries)))
+            if count > fragment_retries:
+                if not skip_unavailable_fragments:
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return -1
 
-        if 'url_list' in info_dict:
-            file_list = []
-            for [i, url] in enumerate(info_dict['url_list']):
-                tmpsegmentname = '%s_%s.frag' % (tmpfilename, i)
-                file_list.append(tmpsegmentname)
-            key_list = info_dict.get('key_list')
-            decrypt_info = None
             dest, _ = sanitize_open(tmpfilename, 'wb')
-            for i, file in enumerate(file_list):
-                src, _ = sanitize_open(file, 'rb')
-                if key_list:
-                    decrypt_info = next((x for x in key_list if x['INDEX'] == i), decrypt_info)
+            for frag_index, fragment in enumerate(info_dict['fragments']):
+                fragment_filename = '%s-Frag%d' % (tmpfilename, frag_index)
+                try:
+                    src, _ = sanitize_open(fragment_filename, 'rb')
+                except IOError:
+                    if skip_unavailable_fragments and frag_index > 1:
+                        self.to_screen('[%s] Skipping fragment %d ...' % (self.get_basename(), frag_index))
+                        continue
+                    self.report_error('Unable to open fragment %d' % frag_index)
+                    return -1
+                decrypt_info = fragment.get('decrypt_info')
+                if decrypt_info:
                     if decrypt_info['METHOD'] == 'AES-128':
                         iv = decrypt_info.get('IV')
                         decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
@@ -149,19 +172,16 @@ class ExternalFD(FileDownloader):
                     fragment_data = src.read()
                     dest.write(fragment_data)
                 src.close()
+                if not self.params.get('keep_fragments', False):
+                    os.remove(encodeFilename(fragment_filename))
             dest.close()
-            if not self.params.get('keep_fragments', False):
-                for file_path in file_list:
-                    try:
-                        os.remove(file_path)
-                    except OSError as ose:
-                        self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
-                try:
-                    file_path = '%s.frag.urls' % tmpfilename
-                    os.remove(file_path)
-                except OSError as ose:
-                    self.report_error("Unable to delete file %s; %s" % (file_path, error_to_compat_str(ose)))
-
+            os.remove(encodeFilename('%s.frag.urls' % tmpfilename))
+        else:
+            p = subprocess.Popen(
+                cmd, stderr=subprocess.PIPE)
+            _, stderr = process_communicate_or_kill(p)
+            if p.returncode != 0:
+                self.to_stderr(stderr.decode('utf-8', 'replace'))
         return p.returncode
 
     def _prepare_url(self, info_dict, url):
@@ -243,17 +263,24 @@ class WgetFD(ExternalFD):
 
 class Aria2cFD(ExternalFD):
     AVAILABLE_OPT = '-v'
-    SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'frag_urls')
+    SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'dash_frag_urls', 'm3u8_frag_urls')
+
+    @staticmethod
+    def supports_manifest(manifest):
+        UNSUPPORTED_FEATURES = [
+            r'#EXT-X-BYTERANGE',  # playlists composed of byte ranges of media files [1]
+            # 1. https://tools.ietf.org/html/draft-pantos-http-live-streaming-17#section-4.3.2.2
+        ]
+        check_results = (not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES)
+        return all(check_results)
 
     def _make_cmd(self, tmpfilename, info_dict):
-        cmd = [self.exe, '-c']
-        dn = os.path.dirname(tmpfilename)
-        if 'url_list' not in info_dict:
-            cmd += ['--out', os.path.basename(tmpfilename)]
-        verbose_level_args = ['--console-log-level=warn', '--summary-interval=0']
-        cmd += self._configuration_args(['--file-allocation=none', '-x16', '-j16', '-s16'] + verbose_level_args)
-        if dn:
-            cmd += ['--dir', dn]
+        cmd = [self.exe, '-c',
+               '--console-log-level=warn', '--summary-interval=0', '--download-result=hide',
+               '--file-allocation=none', '-x16', '-j16', '-s16']
+        if 'fragments' in info_dict:
+            cmd += ['--allow-overwrite=true', '--allow-piece-length-change=true']
+
         if info_dict.get('http_headers') is not None:
             for key, val in info_dict['http_headers'].items():
                 cmd += ['--header', '%s: %s' % (key, val)]
@@ -261,19 +288,25 @@ class Aria2cFD(ExternalFD):
         cmd += self._option('--all-proxy', 'proxy')
         cmd += self._bool_option('--check-certificate', 'nocheckcertificate', 'false', 'true', '=')
         cmd += self._bool_option('--remote-time', 'updatetime', 'true', 'false', '=')
+        cmd += self._configuration_args()
+
+        dn = os.path.dirname(tmpfilename)
+        if dn:
+            cmd += ['--dir', dn]
+        if 'fragments' not in info_dict:
+            cmd += ['--out', os.path.basename(tmpfilename)]
         cmd += ['--auto-file-renaming=false']
-        if 'url_list' in info_dict:
-            cmd += verbose_level_args
-            cmd += ['--uri-selector', 'inorder', '--download-result=hide']
+
+        if 'fragments' in info_dict:
+            cmd += ['--file-allocation=none', '--uri-selector=inorder']
             url_list_file = '%s.frag.urls' % tmpfilename
             url_list = []
-            for [i, url] in enumerate(info_dict['url_list']):
-                tmpsegmentname = '%s_%s.frag' % (os.path.basename(tmpfilename), i)
-                url_list.append('%s\n\tout=%s' % (url, tmpsegmentname))
+            for frag_index, fragment in enumerate(info_dict['fragments']):
+                fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
+                url_list.append('%s\n\tout=%s' % (fragment['url'], fragment_filename))
             stream, _ = sanitize_open(url_list_file, 'wb')
             stream.write('\n'.join(url_list).encode('utf-8'))
             stream.close()
-
             cmd += ['-i', url_list_file]
         else:
             cmd += ['--', info_dict['url']]
@@ -281,9 +314,11 @@ class Aria2cFD(ExternalFD):
 
 
 class HttpieFD(ExternalFD):
+    AVAILABLE_OPT = '--version'
+
     @classmethod
-    def available(cls):
-        return check_executable('http', ['--version'])
+    def available(cls, path=None):
+        return ExternalFD.available(cls, path or 'http')
 
     def _make_cmd(self, tmpfilename, info_dict):
         cmd = ['http', '--download', '--output', tmpfilename, info_dict['url']]
@@ -298,7 +333,8 @@ class FFmpegFD(ExternalFD):
     SUPPORTED_PROTOCOLS = ('http', 'https', 'ftp', 'ftps', 'm3u8', 'rtsp', 'rtmp', 'mms')
 
     @classmethod
-    def available(cls):
+    def available(cls, path=None):
+        # TODO: Fix path for ffmpeg
         return FFmpegPostProcessor().available
 
     def _call_downloader(self, tmpfilename, info_dict):
@@ -398,7 +434,10 @@ class FFmpegFD(ExternalFD):
             args += ['-fs', compat_str(self._TEST_FILE_SIZE)]
 
         if protocol in ('m3u8', 'm3u8_native'):
-            if self.params.get('hls_use_mpegts', False) or tmpfilename == '-':
+            use_mpegts = (tmpfilename == '-') or self.params.get('hls_use_mpegts')
+            if use_mpegts is None:
+                use_mpegts = info_dict.get('is_live')
+            if use_mpegts:
                 args += ['-f', 'mpegts']
             else:
                 args += ['-f', 'mp4']
@@ -452,4 +491,4 @@ def get_external_downloader(external_downloader):
         downloader . """
     # Drop .exe extension on Windows
     bn = os.path.splitext(os.path.basename(external_downloader))[0]
-    return _BY_NAME[bn]
+    return _BY_NAME.get(bn)

yt_dlp/downloader/fragment.py

@@ -55,11 +55,11 @@ class FragmentFD(FileDownloader):
 
     def report_retry_fragment(self, err, frag_index, count, retries):
         self.to_screen(
-            '[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s)...'
+            '[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s) ...'
             % (error_to_compat_str(err), frag_index, count, self.format_retries(retries)))
 
     def report_skip_fragment(self, frag_index):
-        self.to_screen('[download] Skipping fragment %d...' % frag_index)
+        self.to_screen('[download] Skipping fragment %d ...' % frag_index)
 
     def _prepare_url(self, info_dict, url):
         headers = info_dict.get('http_headers')
@@ -174,7 +174,7 @@ class FragmentFD(FileDownloader):
                         '.ytdl file is corrupt' if is_corrupt else
                         'Inconsistent state of incomplete fragment download')
                     self.report_warning(
-                        '%s. Restarting from the beginning...' % message)
+                        '%s. Restarting from the beginning ...' % message)
                     ctx['fragment_index'] = resume_len = 0
                     if 'ytdl_corrupt' in ctx:
                         del ctx['ytdl_corrupt']

yt_dlp/downloader/hls.py

@@ -7,6 +7,11 @@ try:
     can_decrypt_frag = True
 except ImportError:
     can_decrypt_frag = False
+try:
+    import concurrent.futures
+    can_threaded_download = True
+except ImportError:
+    can_threaded_download = False
 
 from ..downloader import _get_real_downloader
 from .fragment import FragmentFD
@@ -19,12 +24,17 @@ from ..compat import (
 )
 from ..utils import (
     parse_m3u8_attributes,
+    sanitize_open,
     update_url_query,
 )
 
 
 class HlsFD(FragmentFD):
-    """ A limited implementation that does not require ffmpeg """
+    """
+    Download segments in a m3u8 manifest. External downloaders can take over
+    the fragment downloads by supporting the 'm3u8_frag_urls' protocol and
+    re-defining 'supports_manifest' function
+    """
 
     FD_NAME = 'hlsnative'
 
@@ -53,12 +63,15 @@ class HlsFD(FragmentFD):
             UNSUPPORTED_FEATURES += [
                 r'#EXT-X-KEY:METHOD=(?!NONE|AES-128)',  # encrypted streams [1]
             ]
-        check_results = [not re.search(feature, manifest) for feature in UNSUPPORTED_FEATURES]
-        is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
-        check_results.append(with_crypto or not is_aes128_enc)
-        check_results.append(not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest))
-        check_results.append(not info_dict.get('is_live'))
-        return all(check_results)
+
+        def check_results():
+            yield not info_dict.get('is_live')
+            is_aes128_enc = '#EXT-X-KEY:METHOD=AES-128' in manifest
+            yield with_crypto or not is_aes128_enc
+            yield not (is_aes128_enc and r'#EXT-X-BYTERANGE' in manifest)
+            for feature in UNSUPPORTED_FEATURES:
+                yield not re.search(feature, manifest)
+        return all(check_results())
 
     def real_download(self, filename, info_dict):
         man_url = info_dict['url']
@@ -70,20 +83,24 @@ class HlsFD(FragmentFD):
 
         if not self.can_download(s, info_dict, self.params.get('allow_unplayable_formats')):
             if info_dict.get('extra_param_to_segment_url') or info_dict.get('_decryption_key_url'):
-                self.report_error('pycryptodome not found. Please install it.')
+                self.report_error('pycryptodome not found. Please install')
                 return False
             if self.can_download(s, info_dict, with_crypto=True):
-                self.report_warning('pycryptodome is needed to download this file with hlsnative')
-            self.report_warning(
-                'hlsnative has detected features it does not support, '
-                'extraction will be delegated to ffmpeg')
+                self.report_warning('pycryptodome is needed to download this file natively')
             fd = FFmpegFD(self.ydl, self.params)
+            self.report_warning(
+                '%s detected unsupported features; extraction will be delegated to %s' % (self.FD_NAME, fd.get_basename()))
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
             #     fd.add_progress_hook(ph)
             return fd.real_download(filename, info_dict)
 
-        real_downloader = _get_real_downloader(info_dict, 'frag_urls', self.params, None)
+        real_downloader = _get_real_downloader(info_dict, 'm3u8_frag_urls', self.params, None)
+        if real_downloader and not real_downloader.supports_manifest(s):
+            real_downloader = None
+        if real_downloader:
+            self.to_screen(
+                '[%s] Fragment downloads will be delegated to %s' % (self.FD_NAME, real_downloader.get_basename()))
 
         def is_ad_fragment_start(s):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=ad' in s
@@ -93,7 +110,7 @@ class HlsFD(FragmentFD):
             return (s.startswith('#ANVATO-SEGMENT-INFO') and 'type=master' in s
                     or s.startswith('#UPLYNK-SEGMENT') and s.endswith(',segment'))
 
-        fragment_urls = []
+        fragments = []
 
         media_frags = 0
         ad_frags = 0
@@ -136,14 +153,12 @@ class HlsFD(FragmentFD):
         i = 0
         media_sequence = 0
         decrypt_info = {'METHOD': 'NONE'}
-        key_list = []
         byte_range = {}
         discontinuity_count = 0
         frag_index = 0
         ad_frag_next = False
         for line in s.splitlines():
             line = line.strip()
-            download_frag = False
             if line:
                 if not line.startswith('#'):
                     if format_index and discontinuity_count != format_index:
@@ -160,17 +175,20 @@ class HlsFD(FragmentFD):
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
 
-                    if real_downloader:
-                        fragment_urls.append(frag_url)
-                        continue
-                    download_frag = True
+                    fragments.append({
+                        'frag_index': frag_index,
+                        'url': frag_url,
+                        'decrypt_info': decrypt_info,
+                        'byte_range': byte_range,
+                        'media_sequence': media_sequence,
+                    })
 
                 elif line.startswith('#EXT-X-MAP'):
                     if format_index and discontinuity_count != format_index:
                         continue
                     if frag_index > 0:
                         self.report_error(
-                            'initialization fragment found after media fragments, unable to download')
+                            'Initialization fragment found after media fragments, unable to download')
                         return False
                     frag_index += 1
                     map_info = parse_m3u8_attributes(line[11:])
@@ -180,9 +198,14 @@ class HlsFD(FragmentFD):
                         else compat_urlparse.urljoin(man_url, map_info.get('URI')))
                     if extra_query:
                         frag_url = update_url_query(frag_url, extra_query)
-                    if real_downloader:
-                        fragment_urls.append(frag_url)
-                        continue
+
+                    fragments.append({
+                        'frag_index': frag_index,
+                        'url': frag_url,
+                        'decrypt_info': decrypt_info,
+                        'byte_range': byte_range,
+                        'media_sequence': media_sequence
+                    })
 
                     if map_info.get('BYTERANGE'):
                         splitted_byte_range = map_info.get('BYTERANGE').split('@')
@@ -191,7 +214,6 @@ class HlsFD(FragmentFD):
                             'start': sub_range_start,
                             'end': sub_range_start + int(splitted_byte_range[0]),
                         }
-                    download_frag = True
 
                 elif line.startswith('#EXT-X-KEY'):
                     decrypt_url = decrypt_info.get('URI')
@@ -206,9 +228,6 @@ class HlsFD(FragmentFD):
                             decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
                         if decrypt_url != decrypt_info['URI']:
                             decrypt_info['KEY'] = None
-                    key_data = decrypt_info.copy()
-                    key_data['INDEX'] = frag_index
-                    key_list.append(key_data)
 
                 elif line.startswith('#EXT-X-MEDIA-SEQUENCE'):
                     media_sequence = int(line[22:])
@@ -225,58 +244,16 @@ class HlsFD(FragmentFD):
                     ad_frag_next = False
                 elif line.startswith('#EXT-X-DISCONTINUITY'):
                     discontinuity_count += 1
+                i += 1
+                media_sequence += 1
 
-                if download_frag:
-                    count = 0
-                    headers = info_dict.get('http_headers', {})
-                    if byte_range:
-                        headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
-                    while count <= fragment_retries:
-                        try:
-                            success, frag_content = self._download_fragment(
-                                ctx, frag_url, info_dict, headers)
-                            if not success:
-                                return False
-                            break
-                        except compat_urllib_error.HTTPError as err:
-                            # Unavailable (possibly temporary) fragments may be served.
-                            # First we try to retry then either skip or abort.
-                            # See https://github.com/ytdl-org/youtube-dl/issues/10165,
-                            # https://github.com/ytdl-org/youtube-dl/issues/10448).
-                            count += 1
-                            if count <= fragment_retries:
-                                self.report_retry_fragment(err, frag_index, count, fragment_retries)
-                    if count > fragment_retries:
-                        if skip_unavailable_fragments:
-                            i += 1
-                            media_sequence += 1
-                            self.report_skip_fragment(frag_index)
-                            continue
-                        self.report_error(
-                            'giving up after %s fragment retries' % fragment_retries)
-                        return False
-
-                    if decrypt_info['METHOD'] == 'AES-128':
-                        iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
-                        decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
-                            self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
-                        # Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
-                        # size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
-                        # not what it decrypts to.
-                        if not test:
-                            frag_content = AES.new(
-                                decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
-                    self._append_fragment(ctx, frag_content)
-                    # We only download the first fragment during the test
-                    if test:
-                        break
-                    i += 1
-                    media_sequence += 1
+        # We only download the first fragment during the test
+        if test:
+            fragments = [fragments[0] if fragments else None]
 
         if real_downloader:
             info_copy = info_dict.copy()
-            info_copy['url_list'] = fragment_urls
-            info_copy['key_list'] = key_list
+            info_copy['fragments'] = fragments
             fd = real_downloader(self.ydl, self.params)
             # TODO: Make progress updates work without hooking twice
             # for ph in self._progress_hooks:
@@ -285,5 +262,107 @@ class HlsFD(FragmentFD):
             if not success:
                 return False
         else:
+            def download_fragment(fragment):
+                frag_index = fragment['frag_index']
+                frag_url = fragment['url']
+                decrypt_info = fragment['decrypt_info']
+                byte_range = fragment['byte_range']
+                media_sequence = fragment['media_sequence']
+
+                ctx['fragment_index'] = frag_index
+
+                count = 0
+                headers = info_dict.get('http_headers', {})
+                if byte_range:
+                    headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
+                while count <= fragment_retries:
+                    try:
+                        success, frag_content = self._download_fragment(
+                            ctx, frag_url, info_dict, headers)
+                        if not success:
+                            return False, frag_index
+                        break
+                    except compat_urllib_error.HTTPError as err:
+                        # Unavailable (possibly temporary) fragments may be served.
+                        # First we try to retry then either skip or abort.
+                        # See https://github.com/ytdl-org/youtube-dl/issues/10165,
+                        # https://github.com/ytdl-org/youtube-dl/issues/10448).
+                        count += 1
+                        if count <= fragment_retries:
+                            self.report_retry_fragment(err, frag_index, count, fragment_retries)
+                if count > fragment_retries:
+                    self.report_error('Giving up after %s fragment retries' % fragment_retries)
+                    return False, frag_index
+
+                if decrypt_info['METHOD'] == 'AES-128':
+                    iv = decrypt_info.get('IV') or compat_struct_pack('>8xq', media_sequence)
+                    decrypt_info['KEY'] = decrypt_info.get('KEY') or self.ydl.urlopen(
+                        self._prepare_url(info_dict, info_dict.get('_decryption_key_url') or decrypt_info['URI'])).read()
+                    # Don't decrypt the content in tests since the data is explicitly truncated and it's not to a valid block
+                    # size (see https://github.com/ytdl-org/youtube-dl/pull/27660). Tests only care that the correct data downloaded,
+                    # not what it decrypts to.
+                    if not test:
+                        frag_content = AES.new(
+                            decrypt_info['KEY'], AES.MODE_CBC, iv).decrypt(frag_content)
+
+                return frag_content, frag_index
+
+            def append_fragment(frag_content, frag_index):
+                if frag_content:
+                    fragment_filename = '%s-Frag%d' % (ctx['tmpfilename'], frag_index)
+                    try:
+                        file, frag_sanitized = sanitize_open(fragment_filename, 'rb')
+                        ctx['fragment_filename_sanitized'] = frag_sanitized
+                        file.close()
+                        self._append_fragment(ctx, frag_content)
+                        return True
+                    except FileNotFoundError:
+                        if skip_unavailable_fragments:
+                            self.report_skip_fragment(frag_index)
+                            return True
+                        else:
+                            self.report_error(
+                                'fragment %s not found, unable to continue' % frag_index)
+                            return False
+                else:
+                    if skip_unavailable_fragments:
+                        self.report_skip_fragment(frag_index)
+                        return True
+                    else:
+                        self.report_error(
+                            'fragment %s not found, unable to continue' % frag_index)
+                        return False
+
+            max_workers = self.params.get('concurrent_fragment_downloads', 1)
+            if can_threaded_download and max_workers > 1:
+                self.report_warning('The download speed shown is only of one thread. This is a known issue')
+                with concurrent.futures.ThreadPoolExecutor(max_workers) as pool:
+                    futures = [pool.submit(download_fragment, fragment) for fragment in fragments]
+                    # timeout must be 0 to return instantly
+                    done, not_done = concurrent.futures.wait(futures, timeout=0)
+                    try:
+                        while not_done:
+                            # Check every 1 second for KeyboardInterrupt
+                            freshly_done, not_done = concurrent.futures.wait(not_done, timeout=1)
+                            done |= freshly_done
+                    except KeyboardInterrupt:
+                        for future in not_done:
+                            future.cancel()
+                        # timeout must be none to cancel
+                        concurrent.futures.wait(not_done, timeout=None)
+                        raise KeyboardInterrupt
+                results = [future.result() for future in futures]
+
+                for frag_content, frag_index in results:
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+            else:
+                for fragment in fragments:
+                    frag_content, frag_index = download_fragment(fragment)
+                    result = append_fragment(frag_content, frag_index)
+                    if not result:
+                        return False
+
             self._finish_frag_download(ctx)
         return True

yt_dlp/downloader/niconico.py

@@ -29,7 +29,7 @@ class NiconicoDmcFD(FileDownloader):
         heartbeat_url = heartbeat_info_dict['url']
         heartbeat_data = heartbeat_info_dict['data']
         heartbeat_interval = heartbeat_info_dict.get('interval', 30)
-        self.to_screen('[%s] Heartbeat with %s second interval...' % (self.FD_NAME, heartbeat_interval))
+        self.to_screen('[%s] Heartbeat with %s second interval ...' % (self.FD_NAME, heartbeat_interval))
 
         def heartbeat():
             try:

yt_dlp/downloader/rtmp.py

@@ -117,7 +117,7 @@ class RtmpFD(FileDownloader):
 
         # Check for rtmpdump first
         if not check_executable('rtmpdump', ['-h']):
-            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install it.')
+            self.report_error('RTMP download detected but "rtmpdump" could not be run. Please install')
             return False
 
         # Download using rtmpdump. rtmpdump returns exit code 2 when

yt_dlp/downloader/rtsp.py

@@ -24,7 +24,7 @@ class RtspFD(FileDownloader):
             args = [
                 'mpv', '-really-quiet', '--vo=null', '--stream-dump=' + tmpfilename, url]
         else:
-            self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install any.')
+            self.report_error('MMS or RTSP download detected but neither "mplayer" nor "mpv" could be run. Please install one')
             return False
 
         self._debug_cmd(args)

yt_dlp/downloader/youtube_live_chat.py

@@ -79,8 +79,7 @@ class YoutubeLiveChatReplayFD(FragmentFD):
 
         self._prepare_and_start_frag_download(ctx)
 
-        success, raw_fragment = dl_fragment(
-            'https://www.youtube.com/watch?v={}'.format(video_id))
+        success, raw_fragment = dl_fragment(info_dict['url'])
         if not success:
             return False
         try:

yt_dlp/extractor/amcnetworks.py

@@ -65,15 +65,35 @@ class AMCNetworksIE(ThePlatformIE):
     def _real_extract(self, url):
         site, display_id = re.match(self._VALID_URL, url).groups()
         requestor_id = self._REQUESTOR_ID_MAP[site]
-        properties = self._download_json(
-            'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s' % (requestor_id.lower(), display_id),
-            display_id)['data']['properties']
+        page_data = self._download_json(
+            'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/%s/url/%s'
+            % (requestor_id.lower(), display_id), display_id)['data']
+        properties = page_data.get('properties') or {}
         query = {
             'mbr': 'true',
             'manifest': 'm3u',
         }
-        tp_path = 'M_UwQC/media/' + properties['videoPid']
-        media_url = 'https://link.theplatform.com/s/' + tp_path
+
+        video_player_count = 0
+        try:
+            for v in page_data['children']:
+                if v.get('type') == 'video-player':
+                    releasePid = v['properties']['currentVideo']['meta']['releasePid']
+                    tp_path = 'M_UwQC/' + releasePid
+                    media_url = 'https://link.theplatform.com/s/' + tp_path
+                    video_player_count += 1
+        except KeyError:
+            pass
+        if video_player_count > 1:
+            self.report_warning(
+                'The JSON data has %d video players. Only one will be extracted' % video_player_count)
+
+        # Fall back to videoPid if releasePid not found.
+        # TODO: Fall back to videoPid if releasePid manifest uses DRM.
+        if not video_player_count:
+            tp_path = 'M_UwQC/media/' + properties['videoPid']
+            media_url = 'https://link.theplatform.com/s/' + tp_path
+
         theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
         info = self._parse_theplatform_metadata(theplatform_metadata)
         video_id = theplatform_metadata['pid']
@@ -90,30 +110,41 @@ class AMCNetworksIE(ThePlatformIE):
         formats, subtitles = self._extract_theplatform_smil(
             media_url, video_id)
         self._sort_formats(formats)
+
+        thumbnails = []
+        thumbnail_urls = [properties.get('imageDesktop')]
+        if 'thumbnail' in info:
+            thumbnail_urls.append(info.pop('thumbnail'))
+        for thumbnail_url in thumbnail_urls:
+            if not thumbnail_url:
+                continue
+            mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
+            thumbnails.append({
+                'url': thumbnail_url,
+                'width': int(mobj.group(1)) if mobj else None,
+                'height': int(mobj.group(2)) if mobj else None,
+            })
+
         info.update({
+            'age_limit': parse_age_limit(rating),
+            'formats': formats,
             'id': video_id,
             'subtitles': subtitles,
-            'formats': formats,
-            'age_limit': parse_age_limit(parse_age_limit(rating)),
+            'thumbnails': thumbnails,
         })
         ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
         if ns_keys:
             ns = list(ns_keys)[0]
-            series = theplatform_metadata.get(ns + '$show')
-            season_number = int_or_none(
-                theplatform_metadata.get(ns + '$season'))
-            episode = theplatform_metadata.get(ns + '$episodeTitle')
+            episode = theplatform_metadata.get(ns + '$episodeTitle') or None
             episode_number = int_or_none(
                 theplatform_metadata.get(ns + '$episode'))
-            if season_number:
-                title = 'Season %d - %s' % (season_number, title)
-            if series:
-                title = '%s - %s' % (series, title)
+            season_number = int_or_none(
+                theplatform_metadata.get(ns + '$season'))
+            series = theplatform_metadata.get(ns + '$show') or None
             info.update({
-                'title': title,
-                'series': series,
-                'season_number': season_number,
                 'episode': episode,
                 'episode_number': episode_number,
+                'season_number': season_number,
+                'series': series,
             })
         return info

yt_dlp/extractor/applepodcasts.py

@@ -42,6 +42,7 @@ class ApplePodcastsIE(InfoExtractor):
         ember_data = self._parse_json(self._search_regex(
             r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
             webpage, 'ember data'), episode_id)
+        ember_data = ember_data.get(episode_id) or ember_data
         episode = ember_data['data']['attributes']
         description = episode.get('description') or {}
 

yt_dlp/extractor/ard.py

@@ -272,7 +272,8 @@ class ARDMediathekIE(ARDMediathekBaseIE):
         else:  # request JSON file
             if not document_id:
                 video_id = self._search_regex(
-                    r'/play/(?:config|media)/(\d+)', webpage, 'media id')
+                    (r'/play/(?:config|media|sola)/(\d+)', r'contentId["\']\s*:\s*(\d+)'),
+                    webpage, 'media id', default=None)
             info = self._extract_media_info(
                 'http://www.ardmediathek.de/play/media/%s' % video_id,
                 webpage, video_id)

yt_dlp/extractor/arnes.py

@@ -0,0 +1,101 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+)
+from ..utils import (
+    float_or_none,
+    int_or_none,
+    parse_iso8601,
+    remove_start,
+)
+
+
+class ArnesIE(InfoExtractor):
+    IE_NAME = 'video.arnes.si'
+    IE_DESC = 'Arnes Video'
+    _VALID_URL = r'https?://video\.arnes\.si/(?:[a-z]{2}/)?(?:watch|embed|api/(?:asset|public/video))/(?P<id>[0-9a-zA-Z]{12})'
+    _TESTS = [{
+        'url': 'https://video.arnes.si/watch/a1qrWTOQfVoU?t=10',
+        'md5': '4d0f4d0a03571b33e1efac25fd4a065d',
+        'info_dict': {
+            'id': 'a1qrWTOQfVoU',
+            'ext': 'mp4',
+            'title': 'Linearna neodvisnost, definicija',
+            'description': 'Linearna neodvisnost, definicija',
+            'license': 'PRIVATE',
+            'creator': 'Polona Oblak',
+            'timestamp': 1585063725,
+            'upload_date': '20200324',
+            'channel': 'Polona Oblak',
+            'channel_id': 'q6pc04hw24cj',
+            'channel_url': 'https://video.arnes.si/?channel=q6pc04hw24cj',
+            'duration': 596.75,
+            'view_count': int,
+            'tags': ['linearna_algebra'],
+            'start_time': 10,
+        }
+    }, {
+        'url': 'https://video.arnes.si/api/asset/s1YjnV7hadlC/play.mp4',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/en/watch/s1YjnV7hadlC',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/embed/s1YjnV7hadlC?t=123&hideRelated=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.arnes.si/api/public/video/s1YjnV7hadlC',
+        'only_matching': True,
+    }]
+    _BASE_URL = 'https://video.arnes.si'
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        video = self._download_json(
+            self._BASE_URL + '/api/public/video/' + video_id, video_id)['data']
+        title = video['title']
+
+        formats = []
+        for media in (video.get('media') or []):
+            media_url = media.get('url')
+            if not media_url:
+                continue
+            formats.append({
+                'url': self._BASE_URL + media_url,
+                'format_id': remove_start(media.get('format'), 'FORMAT_'),
+                'format_note': media.get('formatTranslation'),
+                'width': int_or_none(media.get('width')),
+                'height': int_or_none(media.get('height')),
+            })
+        self._sort_formats(formats)
+
+        channel = video.get('channel') or {}
+        channel_id = channel.get('url')
+        thumbnail = video.get('thumbnailUrl')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnail': self._BASE_URL + thumbnail,
+            'description': video.get('description'),
+            'license': video.get('license'),
+            'creator': video.get('author'),
+            'timestamp': parse_iso8601(video.get('creationTime')),
+            'channel': channel.get('name'),
+            'channel_id': channel_id,
+            'channel_url': self._BASE_URL + '/?channel=' + channel_id if channel_id else None,
+            'duration': float_or_none(video.get('duration'), 1000),
+            'view_count': int_or_none(video.get('views')),
+            'tags': video.get('hashtags'),
+            'start_time': int_or_none(compat_parse_qs(
+                compat_urllib_parse_urlparse(url).query).get('t', [None])[0]),
+        }

yt_dlp/extractor/bandaichannel.py

@@ -0,0 +1,37 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .brightcove import BrightcoveNewIE
+from ..utils import extract_attributes
+
+
+class BandaiChannelIE(BrightcoveNewIE):
+    IE_NAME = 'bandaichannel'
+    _VALID_URL = r'https?://(?:www\.)?b-ch\.com/titles/(?P<id>\d+/\d+)'
+    _TESTS = [{
+        'url': 'https://www.b-ch.com/titles/514/001',
+        'md5': 'a0f2d787baa5729bed71108257f613a4',
+        'info_dict': {
+            'id': '6128044564001',
+            'ext': 'mp4',
+            'title': 'メタルファイターMIKU 第1話',
+            'timestamp': 1580354056,
+            'uploader_id': '5797077852001',
+            'upload_date': '20200130',
+            'duration': 1387.733,
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        attrs = extract_attributes(self._search_regex(
+            r'(<video-js[^>]+\bid="bcplayer"[^>]*>)', webpage, 'player'))
+        bc = self._download_json(
+            'https://pbifcd.b-ch.com/v1/playbackinfo/ST/70/' + attrs['data-info'],
+            video_id, headers={'X-API-KEY': attrs['data-auth'].strip()})['bc']
+        return self._parse_brightcove_metadata(bc, bc['id'])

yt_dlp/extractor/bandcamp.py

@@ -49,6 +49,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Ben Prunty',
             'timestamp': 1396508491,
             'upload_date': '20140403',
+            'release_timestamp': 1396483200,
             'release_date': '20140403',
             'duration': 260.877,
             'track': 'Lanius (Battle)',
@@ -69,6 +70,7 @@ class BandcampIE(InfoExtractor):
             'uploader': 'Mastodon',
             'timestamp': 1322005399,
             'upload_date': '20111122',
+            'release_timestamp': 1076112000,
             'release_date': '20040207',
             'duration': 120.79,
             'track': 'Hail to Fire',
@@ -197,7 +199,7 @@ class BandcampIE(InfoExtractor):
             'thumbnail': thumbnail,
             'uploader': artist,
             'timestamp': timestamp,
-            'release_date': unified_strdate(tralbum.get('album_release_date')),
+            'release_timestamp': unified_timestamp(tralbum.get('album_release_date')),
             'duration': duration,
             'track': track,
             'track_number': track_number,

yt_dlp/extractor/bbc.py

@@ -1,14 +1,24 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import functools
 import itertools
+import json
 import re
 
 from .common import InfoExtractor
+from ..compat import (
+    compat_etree_Element,
+    compat_HTTPError,
+    compat_parse_qs,
+    compat_urllib_parse_urlparse,
+    compat_urlparse,
+)
 from ..utils import (
+    ExtractorError,
+    OnDemandPagedList,
     clean_html,
     dict_get,
-    ExtractorError,
     float_or_none,
     get_element_by_class,
     int_or_none,
@@ -21,11 +31,6 @@ from ..utils import (
     urlencode_postdata,
     urljoin,
 )
-from ..compat import (
-    compat_etree_Element,
-    compat_HTTPError,
-    compat_urlparse,
-)
 
 
 class BBCCoUkIE(InfoExtractor):
@@ -793,11 +798,25 @@ class BBCIE(BBCCoUkIE):
             'description': 'Learn English words and phrases from this story',
         },
         'add_ie': [BBCCoUkIE.ie_key()],
+    }, {
+        # BBC Reel
+        'url': 'https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness',
+        'info_dict': {
+            'id': 'p07c6sb9',
+            'ext': 'mp4',
+            'title': 'How positive thinking is harming your happiness',
+            'alt_title': 'The downsides of positive thinking',
+            'description': 'md5:fad74b31da60d83b8265954ee42d85b4',
+            'duration': 235,
+            'thumbnail': r're:https?://.+/p07c9dsr.jpg',
+            'upload_date': '20190604',
+            'categories': ['Psychology'],
+        },
     }]
 
     @classmethod
     def suitable(cls, url):
-        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerPlaylistIE, BBCCoUkPlaylistIE)
+        EXCLUDE_IE = (BBCCoUkIE, BBCCoUkArticleIE, BBCCoUkIPlayerEpisodesIE, BBCCoUkIPlayerGroupIE, BBCCoUkPlaylistIE)
         return (False if any(ie.suitable(url) for ie in EXCLUDE_IE)
                 else super(BBCIE, cls).suitable(url))
 
@@ -929,7 +948,7 @@ class BBCIE(BBCCoUkIE):
                                     else:
                                         entry['title'] = info['title']
                                         entry['formats'].extend(info['formats'])
-                                except Exception as e:
+                                except ExtractorError as e:
                                     # Some playlist URL may fail with 500, at the same time
                                     # the other one may work fine (e.g.
                                     # http://www.bbc.com/turkce/haberler/2015/06/150615_telabyad_kentin_cogu)
@@ -980,6 +999,37 @@ class BBCIE(BBCCoUkIE):
                 'subtitles': subtitles,
             }
 
+        # bbc reel (e.g. https://www.bbc.com/reel/video/p07c6sb6/how-positive-thinking-is-harming-your-happiness)
+        initial_data = self._parse_json(self._html_search_regex(
+            r'<script[^>]+id=(["\'])initial-data\1[^>]+data-json=(["\'])(?P<json>(?:(?!\2).)+)',
+            webpage, 'initial data', default='{}', group='json'), playlist_id, fatal=False)
+        if initial_data:
+            init_data = try_get(
+                initial_data, lambda x: x['initData']['items'][0], dict) or {}
+            smp_data = init_data.get('smpData') or {}
+            clip_data = try_get(smp_data, lambda x: x['items'][0], dict) or {}
+            version_id = clip_data.get('versionID')
+            if version_id:
+                title = smp_data['title']
+                formats, subtitles = self._download_media_selector(version_id)
+                self._sort_formats(formats)
+                image_url = smp_data.get('holdingImageURL')
+                display_date = init_data.get('displayDate')
+                topic_title = init_data.get('topicTitle')
+
+                return {
+                    'id': version_id,
+                    'title': title,
+                    'formats': formats,
+                    'alt_title': init_data.get('shortTitle'),
+                    'thumbnail': image_url.replace('$recipe', 'raw') if image_url else None,
+                    'description': smp_data.get('summary') or init_data.get('shortSummary'),
+                    'upload_date': display_date.replace('-', '') if display_date else None,
+                    'subtitles': subtitles,
+                    'duration': int_or_none(clip_data.get('duration')),
+                    'categories': [topic_title] if topic_title else None,
+                }
+
         # Morph based embed (e.g. http://www.bbc.co.uk/sport/live/olympics/36895975)
         # There are several setPayload calls may be present but the video
         # seems to be always related to the first one
@@ -1041,7 +1091,7 @@ class BBCIE(BBCCoUkIE):
                 thumbnail = None
                 image_url = current_programme.get('image_url')
                 if image_url:
-                    thumbnail = image_url.replace('{recipe}', '1920x1920')
+                    thumbnail = image_url.replace('{recipe}', 'raw')
                 return {
                     'id': programme_id,
                     'title': title,
@@ -1293,21 +1343,149 @@ class BBCCoUkPlaylistBaseIE(InfoExtractor):
             playlist_id, title, description)
 
 
-class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
-    IE_NAME = 'bbc.co.uk:iplayer:playlist'
-    _VALID_URL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/(?:episodes|group)/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
-    _URL_TEMPLATE = 'http://www.bbc.co.uk/iplayer/episode/%s'
-    _VIDEO_ID_TEMPLATE = r'data-ip-id=["\'](%s)'
+class BBCCoUkIPlayerPlaylistBaseIE(InfoExtractor):
+    _VALID_URL_TMPL = r'https?://(?:www\.)?bbc\.co\.uk/iplayer/%%s/(?P<id>%s)' % BBCCoUkIE._ID_REGEX
+
+    @staticmethod
+    def _get_default(episode, key, default_key='default'):
+        return try_get(episode, lambda x: x[key][default_key])
+
+    def _get_description(self, data):
+        synopsis = data.get(self._DESCRIPTION_KEY) or {}
+        return dict_get(synopsis, ('large', 'medium', 'small'))
+
+    def _fetch_page(self, programme_id, per_page, series_id, page):
+        elements = self._get_elements(self._call_api(
+            programme_id, per_page, page + 1, series_id))
+        for element in elements:
+            episode = self._get_episode(element)
+            episode_id = episode.get('id')
+            if not episode_id:
+                continue
+            thumbnail = None
+            image = self._get_episode_image(episode)
+            if image:
+                thumbnail = image.replace('{recipe}', 'raw')
+            category = self._get_default(episode, 'labels', 'category')
+            yield {
+                '_type': 'url',
+                'id': episode_id,
+                'title': self._get_episode_field(episode, 'subtitle'),
+                'url': 'https://www.bbc.co.uk/iplayer/episode/' + episode_id,
+                'thumbnail': thumbnail,
+                'description': self._get_description(episode),
+                'categories': [category] if category else None,
+                'series': self._get_episode_field(episode, 'title'),
+                'ie_key': BBCCoUkIE.ie_key(),
+            }
+
+    def _real_extract(self, url):
+        pid = self._match_id(url)
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        series_id = qs.get('seriesId', [None])[0]
+        page = qs.get('page', [None])[0]
+        per_page = 36 if page else self._PAGE_SIZE
+        fetch_page = functools.partial(self._fetch_page, pid, per_page, series_id)
+        entries = fetch_page(int(page) - 1) if page else OnDemandPagedList(fetch_page, self._PAGE_SIZE)
+        playlist_data = self._get_playlist_data(self._call_api(pid, 1))
+        return self.playlist_result(
+            entries, pid, self._get_playlist_title(playlist_data),
+            self._get_description(playlist_data))
+
+
+class BBCCoUkIPlayerEpisodesIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:episodes'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'episodes'
     _TESTS = [{
         'url': 'http://www.bbc.co.uk/iplayer/episodes/b05rcz9v',
         'info_dict': {
             'id': 'b05rcz9v',
             'title': 'The Disappearance',
-            'description': 'French thriller serial about a missing teenager.',
+            'description': 'md5:58eb101aee3116bad4da05f91179c0cb',
         },
-        'playlist_mincount': 6,
-        'skip': 'This programme is not currently available on BBC iPlayer',
+        'playlist_mincount': 8,
     }, {
+        # all seasons
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 10,
+    }, {
+        # explicit season
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/b094m5t9/doctor-foster?seriesId=b094m6nv',
+        'info_dict': {
+            'id': 'b094m5t9',
+            'title': 'Doctor Foster',
+            'description': 'md5:5aa9195fad900e8e14b52acd765a9fd6',
+        },
+        'playlist_mincount': 5,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 37,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/episodes/m0004c4v/beechgrove?page=2',
+        'info_dict': {
+            'id': 'm0004c4v',
+            'title': 'Beechgrove',
+            'description': 'Gardening show that celebrates Scottish horticulture and growing conditions.',
+        },
+        'playlist_mincount': 1,
+    }]
+    _PAGE_SIZE = 100
+    _DESCRIPTION_KEY = 'synopsis'
+
+    def _get_episode_image(self, episode):
+        return self._get_default(episode, 'image')
+
+    def _get_episode_field(self, episode, field):
+        return self._get_default(episode, field)
+
+    @staticmethod
+    def _get_elements(data):
+        return data['entities']['results']
+
+    @staticmethod
+    def _get_episode(element):
+        return element.get('episode') or {}
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        variables = {
+            'id': pid,
+            'page': page,
+            'perPage': per_page,
+        }
+        if series_id:
+            variables['sliceId'] = series_id
+        return self._download_json(
+            'https://graph.ibl.api.bbc.co.uk/', pid, headers={
+                'Content-Type': 'application/json'
+            }, data=json.dumps({
+                'id': '5692d93d5aac8d796a0305e895e61551',
+                'variables': variables,
+            }).encode('utf-8'))['data']['programme']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data
+
+    def _get_playlist_title(self, data):
+        return self._get_default(data, 'title')
+
+
+class BBCCoUkIPlayerGroupIE(BBCCoUkIPlayerPlaylistBaseIE):
+    IE_NAME = 'bbc.co.uk:iplayer:group'
+    _VALID_URL = BBCCoUkIPlayerPlaylistBaseIE._VALID_URL_TMPL % 'group'
+    _TESTS = [{
         # Available for over a year unlike 30 days for most other programmes
         'url': 'http://www.bbc.co.uk/iplayer/group/p02tcc32',
         'info_dict': {
@@ -1316,14 +1494,56 @@ class BBCCoUkIPlayerPlaylistIE(BBCCoUkPlaylistBaseIE):
             'description': 'md5:683e901041b2fe9ba596f2ab04c4dbe7',
         },
         'playlist_mincount': 10,
+    }, {
+        # all pages
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 47,
+    }, {
+        # explicit page
+        'url': 'https://www.bbc.co.uk/iplayer/group/p081d7j7?page=2',
+        'info_dict': {
+            'id': 'p081d7j7',
+            'title': 'Music in Scotland',
+            'description': 'Perfomances in Scotland and programmes featuring Scottish acts.',
+        },
+        'playlist_mincount': 11,
     }]
+    _PAGE_SIZE = 200
+    _DESCRIPTION_KEY = 'synopses'
 
-    def _extract_title_and_description(self, webpage):
-        title = self._search_regex(r'<h1>([^<]+)</h1>', webpage, 'title', fatal=False)
-        description = self._search_regex(
-            r'<p[^>]+class=(["\'])subtitle\1[^>]*>(?P<value>[^<]+)</p>',
-            webpage, 'description', fatal=False, group='value')
-        return title, description
+    def _get_episode_image(self, episode):
+        return self._get_default(episode, 'images', 'standard')
+
+    def _get_episode_field(self, episode, field):
+        return episode.get(field)
+
+    @staticmethod
+    def _get_elements(data):
+        return data['elements']
+
+    @staticmethod
+    def _get_episode(element):
+        return element
+
+    def _call_api(self, pid, per_page, page=1, series_id=None):
+        return self._download_json(
+            'http://ibl.api.bbc.co.uk/ibl/v1/groups/%s/episodes' % pid,
+            pid, query={
+                'page': page,
+                'per_page': per_page,
+            })['group_episodes']
+
+    @staticmethod
+    def _get_playlist_data(data):
+        return data['group']
+
+    def _get_playlist_title(self, data):
+        return data.get('title')
 
 
 class BBCCoUkPlaylistIE(BBCCoUkPlaylistBaseIE):

yt_dlp/extractor/bilibili.py

@@ -7,6 +7,7 @@ import re
 
 from .common import InfoExtractor, SearchInfoExtractor
 from ..compat import (
+    compat_str,
     compat_parse_qs,
     compat_urlparse,
 )
@@ -15,6 +16,7 @@ from ..utils import (
     int_or_none,
     float_or_none,
     parse_iso8601,
+    try_get,
     smuggle_url,
     str_or_none,
     strip_jsonp,
@@ -113,6 +115,14 @@ class BiliBiliIE(InfoExtractor):
         # new BV video id format
         'url': 'https://www.bilibili.com/video/BV1JE411F741',
         'only_matching': True,
+    }, {
+        # Anthology
+        'url': 'https://www.bilibili.com/video/BV1bK411W797',
+        'info_dict': {
+            'id': 'BV1bK411W797',
+            'title': '物语中的人物是如何吐槽自己的OP的'
+        },
+        'playlist_count': 17,
     }]
 
     _APP_KEY = 'iVGUTjsxvpLeuDCf'
@@ -139,9 +149,20 @@ class BiliBiliIE(InfoExtractor):
         page_id = mobj.group('page')
         webpage = self._download_webpage(url, video_id)
 
+        # Bilibili anthologies are similar to playlists but all videos share the same video ID as the anthology itself.
+        # If the video has no page argument, check to see if it's an anthology
+        if page_id is None:
+            if not self._downloader.params.get('noplaylist'):
+                r = self._extract_anthology_entries(bv_id, video_id, webpage)
+                if r is not None:
+                    self.to_screen('Downloading anthology %s - add --no-playlist to just download video' % video_id)
+                    return r
+            else:
+                self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
+
         if 'anime/' not in url:
             cid = self._search_regex(
-                r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + str(page_id), webpage, 'cid',
+                r'\bcid(?:["\']:|=)(\d+),["\']page(?:["\']:|=)' + compat_str(page_id), webpage, 'cid',
                 default=None
             ) or self._search_regex(
                 r'\bcid(?:["\']:|=)(\d+)', webpage, 'cid',
@@ -170,6 +191,7 @@ class BiliBiliIE(InfoExtractor):
             cid = js['result']['cid']
 
         headers = {
+            'Accept': 'application/json',
             'Referer': url
         }
         headers.update(self.geo_verification_headers())
@@ -223,7 +245,18 @@ class BiliBiliIE(InfoExtractor):
         title = self._html_search_regex(
             (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
              r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
-            group='title') + ('_p' + str(page_id) if page_id is not None else '')
+            group='title')
+
+        # Get part title for anthologies
+        if page_id is not None:
+            # TODO: The json is already downloaded by _extract_anthology_entries. Don't redownload for each video
+            part_title = try_get(
+                self._download_json(
+                    "https://api.bilibili.com/x/player/pagelist?bvid=%s&jsonp=jsonp" % bv_id,
+                    video_id, note='Extracting videos in anthology'),
+                lambda x: x['data'][int(page_id) - 1]['part'])
+            title = part_title or title
+
         description = self._html_search_meta('description', webpage)
         timestamp = unified_timestamp(self._html_search_regex(
             r'<time[^>]+datetime="([^"]+)"', webpage, 'upload time',
@@ -233,7 +266,7 @@ class BiliBiliIE(InfoExtractor):
 
         # TODO 'view_count' requires deobfuscating Javascript
         info = {
-            'id': str(video_id) if page_id is None else '%s_p%s' % (video_id, page_id),
+            'id': compat_str(video_id) if page_id is None else '%s_p%s' % (video_id, page_id),
             'cid': cid,
             'title': title,
             'description': description,
@@ -243,7 +276,7 @@ class BiliBiliIE(InfoExtractor):
         }
 
         uploader_mobj = re.search(
-            r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>(?P<name>[^<]+)',
+            r'<a[^>]+href="(?:https?:)?//space\.bilibili\.com/(?P<id>\d+)"[^>]*>\s*(?P<name>[^<]+?)\s*<',
             webpage)
         if uploader_mobj:
             info.update({
@@ -255,10 +288,6 @@ class BiliBiliIE(InfoExtractor):
             info['uploader'] = self._html_search_meta(
                 'author', webpage, 'uploader', default=None)
 
-        comments = None
-        if self._downloader.params.get('getcomments', False):
-            comments = self._get_all_comment_pages(video_id)
-
         raw_danmaku = self._get_raw_danmaku(video_id, cid)
 
         raw_tags = self._get_tags(video_id)
@@ -266,11 +295,18 @@ class BiliBiliIE(InfoExtractor):
 
         top_level_info = {
             'raw_danmaku': raw_danmaku,
-            'comments': comments,
-            'comment_count': len(comments) if comments is not None else None,
             'tags': tags,
             'raw_tags': raw_tags,
         }
+        if self._downloader.params.get('getcomments', False):
+            def get_comments():
+                comments = self._get_all_comment_pages(video_id)
+                return {
+                    'comments': comments,
+                    'comment_count': len(comments)
+                }
+
+            top_level_info['__post_extractor'] = get_comments
 
         '''
         # Requires https://github.com/m13253/danmaku2ass which is licenced under GPL3
@@ -296,7 +332,7 @@ class BiliBiliIE(InfoExtractor):
 
             global_info = {
                 '_type': 'multi_video',
-                'id': video_id,
+                'id': compat_str(video_id),
                 'bv_id': bv_id,
                 'title': title,
                 'description': description,
@@ -308,6 +344,20 @@ class BiliBiliIE(InfoExtractor):
 
             return global_info
 
+    def _extract_anthology_entries(self, bv_id, video_id, webpage):
+        title = self._html_search_regex(
+            (r'<h1[^>]+\btitle=(["\'])(?P<title>(?:(?!\1).)+)\1',
+             r'(?s)<h1[^>]*>(?P<title>.+?)</h1>'), webpage, 'title',
+            group='title')
+        json_data = self._download_json(
+            "https://api.bilibili.com/x/player/pagelist?bvid=%s&jsonp=jsonp" % bv_id,
+            video_id, note='Extracting videos in anthology')
+
+        if len(json_data['data']) > 1:
+            return self.playlist_from_matches(
+                json_data['data'], bv_id, title, ie=BiliBiliIE.ie_key(),
+                getter=lambda entry: 'https://www.bilibili.com/video/%s?p=%d' % (bv_id, entry['page']))
+
     def _get_video_id_set(self, id, is_bv):
         query = {'bvid': id} if is_bv else {'aid': id}
         response = self._download_json(
@@ -502,7 +552,7 @@ class BiliBiliSearchIE(SearchInfoExtractor):
 
             videos = data['result']
             for video in videos:
-                e = self.url_result(video['arcurl'], 'BiliBili', str(video['aid']))
+                e = self.url_result(video['arcurl'], 'BiliBili', compat_str(video['aid']))
                 entries.append(e)
 
             if(len(entries) >= n or len(videos) >= BiliBiliSearchIE.MAX_NUMBER_OF_RESULTS):
@@ -555,6 +605,7 @@ class BilibiliAudioIE(BilibiliAudioBaseIE):
         formats = [{
             'url': play_data['cdns'][0],
             'filesize': int_or_none(play_data.get('size')),
+            'vcodec': 'none'
         }]
 
         song = self._call_api('song/info', au_id)

yt_dlp/extractor/cbs.py

@@ -27,10 +27,10 @@ class CBSBaseIE(ThePlatformFeedIE):
 
 
 class CBSIE(CBSBaseIE):
-    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:cbs\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
+    _VALID_URL = r'(?:cbs:|https?://(?:www\.)?(?:(?:cbs|paramountplus)\.com/shows/[^/]+/video|colbertlateshow\.com/(?:video|podcasts))/)(?P<id>[\w-]+)'
 
     _TESTS = [{
-        'url': 'http://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
+        'url': 'https://www.cbs.com/shows/garth-brooks/video/_u7W953k6la293J7EPTd9oHkSPs6Xn6_/connect-chat-feat-garth-brooks/',
         'info_dict': {
             'id': '_u7W953k6la293J7EPTd9oHkSPs6Xn6_',
             'ext': 'mp4',
@@ -52,16 +52,19 @@ class CBSIE(CBSBaseIE):
     }, {
         'url': 'http://www.colbertlateshow.com/podcasts/dYSwjqPs_X1tvbV_P2FcPWRa_qT6akTC/in-the-bad-room-with-stephen/',
         'only_matching': True,
+    }, {
+        'url': 'https://www.paramountplus.com/shows/all-rise/video/QmR1WhNkh1a_IrdHZrbcRklm176X_rVc/all-rise-space/',
+        'only_matching': True,
     }]
 
     def _extract_video_info(self, content_id, site='cbs', mpx_acc=2198311517):
         items_data = self._download_xml(
-            'http://can.cbs.com/thunder/player/videoPlayerService.php',
+            'https://can.cbs.com/thunder/player/videoPlayerService.php',
             content_id, query={'partner': site, 'contentId': content_id})
         video_data = xpath_element(items_data, './/item')
         title = xpath_text(video_data, 'videoTitle', 'title') or xpath_text(video_data, 'videotitle', 'title')
         tp_path = 'dJ5BDC/media/guid/%d/%s' % (mpx_acc, content_id)
-        tp_release_url = 'http://link.theplatform.com/s/' + tp_path
+        tp_release_url = 'https://link.theplatform.com/s/' + tp_path
 
         asset_types = []
         subtitles = {}

yt_dlp/extractor/cbssports.py

@@ -1,38 +1,113 @@
 from __future__ import unicode_literals
 
-from .cbs import CBSBaseIE
+import re
+
+# from .cbs import CBSBaseIE
+from .common import InfoExtractor
+from ..utils import (
+    int_or_none,
+    try_get,
+)
 
 
-class CBSSportsIE(CBSBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/(?:video|news)/(?P<id>[^/?#&]+)'
-
+# class CBSSportsEmbedIE(CBSBaseIE):
+class CBSSportsEmbedIE(InfoExtractor):
+    IE_NAME = 'cbssports:embed'
+    _VALID_URL = r'''(?ix)https?://(?:(?:www\.)?cbs|embed\.247)sports\.com/player/embed.+?
+        (?:
+            ids%3D(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})|
+            pcid%3D(?P<pcid>\d+)
+        )'''
     _TESTS = [{
-        'url': 'https://www.cbssports.com/nba/video/donovan-mitchell-flashes-star-potential-in-game-2-victory-over-thunder/',
-        'info_dict': {
-            'id': '1214315075735',
-            'ext': 'mp4',
-            'title': 'Donovan Mitchell flashes star potential in Game 2 victory over Thunder',
-            'description': 'md5:df6f48622612c2d6bd2e295ddef58def',
-            'timestamp': 1524111457,
-            'upload_date': '20180419',
-            'uploader': 'CBSI-NEW',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        }
+        'url': 'https://www.cbssports.com/player/embed/?args=player_id%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26ids%3Db56c03a6-231a-4bbe-9c55-af3c8a8e9636%26resizable%3D1%26autoplay%3Dtrue%26domain%3Dcbssports.com%26comp_ads_enabled%3Dfalse%26watchAndRead%3D0%26startTime%3D0%26env%3Dprod',
+        'only_matching': True,
     }, {
-        'url': 'https://www.cbssports.com/nba/news/nba-playoffs-2018-watch-76ers-vs-heat-game-3-series-schedule-tv-channel-online-stream/',
+        'url': 'https://embed.247sports.com/player/embed/?args=%3fplayer_id%3d1827823171591%26channel%3dcollege-football-recruiting%26pcid%3d1827823171591%26width%3d640%26height%3d360%26autoplay%3dTrue%26comp_ads_enabled%3dFalse%26uvpc%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_v4%2526partner%253d247%26uvpc_m%3dhttps%253a%252f%252fwww.cbssports.com%252fapi%252fcontent%252fvideo%252fconfig%252f%253fcfg%253duvp_247sports_m_v4%2526partner_m%253d247_mobile%26utag%3d247sportssite%26resizable%3dTrue',
         'only_matching': True,
     }]
 
-    def _extract_video_info(self, filter_query, video_id):
-        return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
+    # def _extract_video_info(self, filter_query, video_id):
+    #     return self._extract_feed_info('dJ5BDC', 'VxxJg8Ymh8sE', filter_query, video_id)
 
+    def _real_extract(self, url):
+        uuid, pcid = re.match(self._VALID_URL, url).groups()
+        query = {'id': uuid} if uuid else {'pcid': pcid}
+        video = self._download_json(
+            'https://www.cbssports.com/api/content/video/',
+            uuid or pcid, query=query)[0]
+        video_id = video['id']
+        title = video['title']
+        metadata = video.get('metaData') or {}
+        # return self._extract_video_info('byId=%d' % metadata['mpxOutletId'], video_id)
+        # return self._extract_video_info('byGuid=' + metadata['mpxRefId'], video_id)
+
+        formats = self._extract_m3u8_formats(
+            metadata['files'][0]['url'], video_id, 'mp4',
+            'm3u8_native', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+
+        image = video.get('image')
+        thumbnails = None
+        if image:
+            image_path = image.get('path')
+            if image_path:
+                thumbnails = [{
+                    'url': image_path,
+                    'width': int_or_none(image.get('width')),
+                    'height': int_or_none(image.get('height')),
+                    'filesize': int_or_none(image.get('size')),
+                }]
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'thumbnails': thumbnails,
+            'description': video.get('description'),
+            'timestamp': int_or_none(try_get(video, lambda x: x['dateCreated']['epoch'])),
+            'duration': int_or_none(metadata.get('duration')),
+        }
+
+
+class CBSSportsBaseIE(InfoExtractor):
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        video_id = self._search_regex(
-            [r'(?:=|%26)pcid%3D(\d+)', r'embedVideo(?:Container)?_(\d+)'],
-            webpage, 'video id')
-        return self._extract_video_info('byId=%s' % video_id, video_id)
+        iframe_url = self._search_regex(
+            r'<iframe[^>]+(?:data-)?src="(https?://[^/]+/player/embed[^"]+)"',
+            webpage, 'embed url')
+        return self.url_result(iframe_url, CBSSportsEmbedIE.ie_key())
+
+
+class CBSSportsIE(CBSSportsBaseIE):
+    IE_NAME = 'cbssports'
+    _VALID_URL = r'https?://(?:www\.)?cbssports\.com/[^/]+/video/(?P<id>[^/?#&]+)'
+    _TESTS = [{
+        'url': 'https://www.cbssports.com/college-football/video/cover-3-stanford-spring-gleaning/',
+        'info_dict': {
+            'id': 'b56c03a6-231a-4bbe-9c55-af3c8a8e9636',
+            'ext': 'mp4',
+            'title': 'Cover 3: Stanford Spring Gleaning',
+            'description': 'The Cover 3 crew break down everything you need to know about the Stanford Cardinal this spring.',
+            'timestamp': 1617218398,
+            'upload_date': '20210331',
+            'duration': 502,
+        },
+    }]
+
+
+class TwentyFourSevenSportsIE(CBSSportsBaseIE):
+    IE_NAME = '247sports'
+    _VALID_URL = r'https?://(?:www\.)?247sports\.com/Video/(?:[^/?#&]+-)?(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://247sports.com/Video/2021-QB-Jake-Garcia-senior-highlights-through-five-games-10084854/',
+        'info_dict': {
+            'id': '4f1265cb-c3b5-44a8-bb1d-1914119a0ccc',
+            'ext': 'mp4',
+            'title': '2021 QB Jake Garcia senior highlights through five games',
+            'description': 'md5:8cb67ebed48e2e6adac1701e0ff6e45b',
+            'timestamp': 1607114223,
+            'upload_date': '20201204',
+            'duration': 208,
+        },
+    }]

yt_dlp/extractor/common.py

@@ -17,7 +17,7 @@ import math
 
 from ..compat import (
     compat_cookiejar_Cookie,
-    compat_cookies,
+    compat_cookies_SimpleCookie,
     compat_etree_Element,
     compat_etree_fromstring,
     compat_getpass,
@@ -231,8 +231,9 @@ class InfoExtractor(object):
     uploader:       Full name of the video uploader.
     license:        License name the video is licensed under.
     creator:        The creator of the video.
+    release_timestamp: UNIX timestamp of the moment the video was released.
     release_date:   The date (YYYYMMDD) when the video was released.
-    timestamp:      UNIX timestamp of the moment the video became available.
+    timestamp:      UNIX timestamp of the moment the video was uploaded
     upload_date:    Video upload date (YYYYMMDD).
                     If not explicitly set, calculated from timestamp.
     uploader_id:    Nickname or id of the video uploader.
@@ -251,8 +252,8 @@ class InfoExtractor(object):
                         * "data": The subtitles file contents
                         * "url": A URL pointing to the subtitles file
                     "ext" will be calculated from URL if missing
-    automatic_captions: Like 'subtitles', used by the YoutubeIE for
-                    automatically generated captions
+    automatic_captions: Like 'subtitles'; contains automatically generated
+                    captions instead of normal subtitles
     duration:       Length of the video in seconds, as an integer or float.
     view_count:     How many users have watched the video on the platform.
     like_count:     Number of positive ratings of the video
@@ -264,6 +265,7 @@ class InfoExtractor(object):
                     properties (all but one of text or html optional):
                         * "author" - human-readable name of the comment author
                         * "author_id" - user ID of the comment author
+                        * "author_thumbnail" - The thumbnail of the comment author
                         * "id" - Comment ID
                         * "html" - Comment as HTML
                         * "text" - Plain text of the comment
@@ -271,6 +273,12 @@ class InfoExtractor(object):
                         * "parent" - ID of the comment this one is replying to.
                                      Set to "root" to indicate that this is a
                                      comment to the original video.
+                        * "like_count" - Number of positive ratings of the comment
+                        * "dislike_count" - Number of negative ratings of the comment
+                        * "is_favorited" - Whether the comment is marked as
+                                           favorite by the video uploader
+                        * "author_is_uploader" - Whether the comment is made by
+                                                 the video uploader
     age_limit:      Age restriction for the video, as an integer (years)
     webpage_url:    The URL to the video webpage, if given to yt-dlp it
                     should allow to get the same result again. (It will be set
@@ -293,7 +301,19 @@ class InfoExtractor(object):
     playable_in_embed: Whether this video is allowed to play in embedded
                     players on other sites. Can be True (=always allowed),
                     False (=never allowed), None (=unknown), or a string
-                    specifying the criteria for embedability (Eg: 'whitelist').
+                    specifying the criteria for embedability (Eg: 'whitelist')
+    availability:   Under what condition the video is available. One of
+                    'private', 'premium_only', 'subscriber_only', 'needs_auth',
+                    'unlisted' or 'public'. Use 'InfoExtractor._availability'
+                    to set it
+    __post_extractor: A function to be called just before the metadata is
+                    written to either disk, logger or console. The function
+                    must return a dict which will be added to the info_dict.
+                    This is usefull for additional information that is
+                    time-consuming to extract. Note that the fields thus
+                    extracted will not be available to output template and
+                    match_filter. So, only "comments" and "comment_count" are
+                    currently allowed to be extracted via this method.
 
     The following fields should only be used when the video belongs to some logical
     chapter or section:
@@ -606,6 +626,14 @@ class InfoExtractor(object):
 
         See _download_webpage docstring for arguments specification.
         """
+        if not self._downloader._first_webpage_request:
+            sleep_interval = float_or_none(self._downloader.params.get('sleep_interval_requests')) or 0
+            if sleep_interval > 0:
+                self.to_screen('Sleeping %s seconds ...' % sleep_interval)
+                time.sleep(sleep_interval)
+        else:
+            self._downloader._first_webpage_request = False
+
         if note is None:
             self.report_download_webpage(video_id)
         elif note is not False:
@@ -1280,6 +1308,7 @@ class InfoExtractor(object):
 
         def extract_video_object(e):
             assert e['@type'] == 'VideoObject'
+            author = e.get('author')
             info.update({
                 'url': url_or_none(e.get('contentUrl')),
                 'title': unescapeHTML(e.get('name')),
@@ -1287,7 +1316,11 @@ class InfoExtractor(object):
                 'thumbnail': url_or_none(e.get('thumbnailUrl') or e.get('thumbnailURL')),
                 'duration': parse_duration(e.get('duration')),
                 'timestamp': unified_timestamp(e.get('uploadDate')),
-                'uploader': str_or_none(e.get('author')),
+                # author can be an instance of 'Organization' or 'Person' types.
+                # both types can have 'name' property(inherited from 'Thing' type). [1]
+                # however some websites are using 'Text' type instead.
+                # 1. https://schema.org/VideoObject
+                'uploader': author.get('name') if isinstance(author, dict) else author if isinstance(author, compat_str) else None,
                 'filesize': float_or_none(e.get('contentSize')),
                 'tbr': int_or_none(e.get('bitrate')),
                 'width': int_or_none(e.get('width')),
@@ -1370,7 +1403,7 @@ class InfoExtractor(object):
         return self._hidden_inputs(form)
 
     class FormatSort:
-        regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<seperator>[~:])(?P<limit>.*?))?)? *$'
+        regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'
 
         default = ('hidden', 'hasvid', 'ie_pref', 'lang', 'quality',
                    'res', 'fps', 'codec:vp9.2', 'size', 'br', 'asr',
@@ -1393,8 +1426,8 @@ class InfoExtractor(object):
             'ie_pref': {'priority': True, 'type': 'extractor'},
             'hasvid': {'priority': True, 'field': 'vcodec', 'type': 'boolean', 'not_in_list': ('none',)},
             'hasaud': {'field': 'acodec', 'type': 'boolean', 'not_in_list': ('none',)},
-            'lang': {'priority': True, 'convert': 'ignore', 'type': 'extractor', 'field': 'language_preference'},
-            'quality': {'convert': 'float_none', 'type': 'extractor'},
+            'lang': {'priority': True, 'convert': 'ignore', 'field': 'language_preference'},
+            'quality': {'convert': 'float_none'},
             'filesize': {'convert': 'bytes'},
             'fs_approx': {'convert': 'bytes', 'field': 'filesize_approx'},
             'id': {'convert': 'string', 'field': 'format_id'},
@@ -1405,7 +1438,7 @@ class InfoExtractor(object):
             'vbr': {'convert': 'float_none'},
             'abr': {'convert': 'float_none'},
             'asr': {'convert': 'float_none'},
-            'source': {'convert': 'ignore', 'type': 'extractor', 'field': 'source_preference'},
+            'source': {'convert': 'ignore', 'field': 'source_preference'},
 
             'codec': {'type': 'combined', 'field': ('vcodec', 'acodec')},
             'br': {'type': 'combined', 'field': ('tbr', 'vbr', 'abr'), 'same_limit': True},
@@ -1530,7 +1563,7 @@ class InfoExtractor(object):
                 if self._get_field_setting(field, 'type') == 'alias':
                     field = self._get_field_setting(field, 'field')
                 reverse = match.group('reverse') is not None
-                closest = match.group('seperator') == '~'
+                closest = match.group('separator') == '~'
                 limit_text = match.group('limit')
 
                 has_limit = limit_text is not None
@@ -1547,7 +1580,8 @@ class InfoExtractor(object):
                              else None)
 
         def print_verbose_info(self, to_screen):
-            to_screen('[debug] Sort order given by user: %s' % ','.join(self._sort_user))
+            if self._sort_user:
+                to_screen('[debug] Sort order given by user: %s' % ','.join(self._sort_user))
             if self._sort_extractor:
                 to_screen('[debug] Sort order given by extractor: %s' % ', '.join(self._sort_extractor))
             to_screen('[debug] Formats sorted by: %s' % ', '.join(['%s%s%s' % (
@@ -1833,8 +1867,9 @@ class InfoExtractor(object):
 
     def _extract_m3u8_formats(self, m3u8_url, video_id, ext=None,
                               entry_protocol='m3u8', preference=None, quality=None,
-                              m3u8_id=None, live=False, note=None, errnote=None,
-                              fatal=True, data=None, headers={}, query={}):
+                              m3u8_id=None, note=None, errnote=None,
+                              fatal=True, live=False, data=None, headers={},
+                              query={}):
         res = self._download_webpage_handle(
             m3u8_url, video_id,
             note=note or 'Downloading m3u8 information',
@@ -1860,7 +1895,8 @@ class InfoExtractor(object):
         if '#EXT-X-FAXS-CM:' in m3u8_doc:  # Adobe Flash Access
             return []
 
-        if re.search(r'#EXT-X-SESSION-KEY:.*?URI="skd://', m3u8_doc):  # Apple FairPlay
+        if (not self._downloader.params.get('allow_unplayable_formats')
+                and re.search(r'#EXT-X-SESSION-KEY:.*?URI="skd://', m3u8_doc)):  # Apple FairPlay
             return []
 
         formats = []
@@ -1888,13 +1924,16 @@ class InfoExtractor(object):
         # media playlist and MUST NOT appear in master playlist thus we can
         # clearly detect media playlist with this criterion.
 
-        def _extract_m3u8_playlist_formats(format_url, m3u8_doc=None):
+        def _extract_m3u8_playlist_formats(format_url=None, m3u8_doc=None, video_id=None,
+                                           fatal=True, data=None, headers={}):
             if not m3u8_doc:
+                if not format_url:
+                    return []
                 res = self._download_webpage_handle(
                     format_url, video_id,
                     note=False,
-                    errnote=errnote or 'Failed to download m3u8 playlist information',
-                    fatal=fatal, data=data, headers=headers, query=query)
+                    errnote='Failed to download m3u8 playlist information',
+                    fatal=fatal, data=data, headers=headers)
 
                 if res is False:
                     return []
@@ -1928,7 +1967,7 @@ class InfoExtractor(object):
 
         if '#EXT-X-TARGETDURATION' in m3u8_doc:  # media playlist, return as is
 
-            playlist_formats = _extract_m3u8_playlist_formats(m3u8_doc, True)
+            playlist_formats = _extract_m3u8_playlist_formats(m3u8_doc=m3u8_doc)
 
             for format in playlist_formats:
                 format_id = []
@@ -1966,7 +2005,8 @@ class InfoExtractor(object):
             if media_url:
                 manifest_url = format_url(media_url)
                 format_id = []
-                playlist_formats = _extract_m3u8_playlist_formats(manifest_url)
+                playlist_formats = _extract_m3u8_playlist_formats(manifest_url, video_id=video_id,
+                                                                  fatal=fatal, data=data, headers=headers)
 
                 for format in playlist_formats:
                     format_index = format.get('index')
@@ -2027,13 +2067,14 @@ class InfoExtractor(object):
                     or last_stream_inf.get('BANDWIDTH'), scale=1000)
                 manifest_url = format_url(line.strip())
 
-                playlist_formats = _extract_m3u8_playlist_formats(manifest_url)
+                playlist_formats = _extract_m3u8_playlist_formats(manifest_url, video_id=video_id,
+                                                                  fatal=fatal, data=data, headers=headers)
 
-                for format in playlist_formats:
+                for frmt in playlist_formats:
                     format_id = []
                     if m3u8_id:
                         format_id.append(m3u8_id)
-                    format_index = format.get('index')
+                    format_index = frmt.get('index')
                     stream_name = build_stream_name()
                     # Bandwidth of live streams may differ over time thus making
                     # format_id unpredictable. So it's better to keep provided
@@ -2088,6 +2129,8 @@ class InfoExtractor(object):
                             # TODO: update acodec for audio only formats with
                             # the same GROUP-ID
                             f['acodec'] = 'none'
+                    if not f.get('ext'):
+                        f['ext'] = 'm4a' if f.get('vcodec') == 'none' else 'mp4'
                     formats.append(f)
 
                     # for DailyMotion
@@ -2370,7 +2413,7 @@ class InfoExtractor(object):
             http://standards.iso.org/ittf/PubliclyAvailableStandards/c065274_ISO_IEC_23009-1_2014.zip
          2. https://en.wikipedia.org/wiki/Dynamic_Adaptive_Streaming_over_HTTP
         """
-        if not self._downloader.params.get('dynamic_mpd'):
+        if not self._downloader.params.get('dynamic_mpd', True):
             if mpd_doc.get('type') == 'dynamic':
                 return []
 
@@ -3182,10 +3225,10 @@ class InfoExtractor(object):
         self._downloader.cookiejar.set_cookie(cookie)
 
     def _get_cookies(self, url):
-        """ Return a compat_cookies.SimpleCookie with the cookies for the url """
+        """ Return a compat_cookies_SimpleCookie with the cookies for the url """
         req = sanitized_Request(url)
         self._downloader.cookiejar.add_cookie_header(req)
-        return compat_cookies.SimpleCookie(req.get_header('Cookie'))
+        return compat_cookies_SimpleCookie(req.get_header('Cookie'))
 
     def _apply_first_set_cookie_header(self, url_handle, cookie):
         """
@@ -3300,6 +3343,20 @@ class InfoExtractor(object):
     def _generic_title(self, url):
         return compat_urllib_parse_unquote(os.path.splitext(url_basename(url))[0])
 
+    @staticmethod
+    def _availability(is_private, needs_premium, needs_subscription, needs_auth, is_unlisted):
+        all_known = all(map(
+            lambda x: x is not None,
+            (is_private, needs_premium, needs_subscription, needs_auth, is_unlisted)))
+        return (
+            'private' if is_private
+            else 'premium_only' if needs_premium
+            else 'subscriber_only' if needs_subscription
+            else 'needs_auth' if needs_auth
+            else 'unlisted' if is_unlisted
+            else 'public' if all_known
+            else None)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """

yt_dlp/extractor/commonprotocols.py

@@ -1,5 +1,7 @@
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..compat import (
     compat_urlparse,
@@ -58,3 +60,16 @@ class MmsIE(InfoExtractor):
             'title': title,
             'url': url,
         }
+
+
+class ViewSourceIE(InfoExtractor):
+    IE_DESC = False
+    _VALID_URL = r'view-source:(?P<url>.+)'
+
+    _TEST = {
+        'url': 'view-source:https://www.youtube.com/watch?v=BaW_jenozKc',
+        'only_matching': True
+    }
+
+    def _real_extract(self, url):
+        return self.url_result(re.match(self._VALID_URL, url).group('url'))

yt_dlp/extractor/curiositystream.py

@@ -25,12 +25,12 @@ class CuriosityStreamBaseIE(InfoExtractor):
             raise ExtractorError(
                 '%s said: %s' % (self.IE_NAME, error), expected=True)
 
-    def _call_api(self, path, video_id):
+    def _call_api(self, path, video_id, query=None):
         headers = {}
         if self._auth_token:
             headers['X-Auth-Token'] = self._auth_token
         result = self._download_json(
-            self._API_BASE_URL + path, video_id, headers=headers)
+            self._API_BASE_URL + path, video_id, headers=headers, query=query)
         self._handle_errors(result)
         return result['data']
 
@@ -52,62 +52,75 @@ class CuriosityStreamIE(CuriosityStreamBaseIE):
     _VALID_URL = r'https?://(?:app\.)?curiositystream\.com/video/(?P<id>\d+)'
     _TEST = {
         'url': 'https://app.curiositystream.com/video/2',
-        'md5': '262bb2f257ff301115f1973540de8983',
         'info_dict': {
             'id': '2',
             'ext': 'mp4',
             'title': 'How Did You Develop The Internet?',
             'description': 'Vint Cerf, Google\'s Chief Internet Evangelist, describes how he and Bob Kahn created the internet.',
-        }
+        },
+        'params': {
+            'format': 'bestvideo',
+            # m3u8 download
+            'skip_download': True,
+        },
     }
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        media = self._call_api('media/' + video_id, video_id)
-        title = media['title']
 
         formats = []
-        for encoding in media.get('encodings', []):
-            m3u8_url = encoding.get('master_playlist_url')
-            if m3u8_url:
-                formats.extend(self._extract_m3u8_formats(
-                    m3u8_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id='hls', fatal=False))
-            encoding_url = encoding.get('url')
-            file_url = encoding.get('file_url')
-            if not encoding_url and not file_url:
-                continue
-            f = {
-                'width': int_or_none(encoding.get('width')),
-                'height': int_or_none(encoding.get('height')),
-                'vbr': int_or_none(encoding.get('video_bitrate')),
-                'abr': int_or_none(encoding.get('audio_bitrate')),
-                'filesize': int_or_none(encoding.get('size_in_bytes')),
-                'vcodec': encoding.get('video_codec'),
-                'acodec': encoding.get('audio_codec'),
-                'container': encoding.get('container_type'),
-            }
-            for f_url in (encoding_url, file_url):
-                if not f_url:
+        for encoding_format in ('m3u8', 'mpd'):
+            media = self._call_api('media/' + video_id, video_id, query={
+                'encodingsNew': 'true',
+                'encodingsFormat': encoding_format,
+            })
+            for encoding in media.get('encodings', []):
+                playlist_url = encoding.get('master_playlist_url')
+                if encoding_format == 'm3u8':
+                    # use `m3u8` entry_protocol until EXT-X-MAP is properly supported by `m3u8_native` entry_protocol
+                    formats.extend(self._extract_m3u8_formats(
+                        playlist_url, video_id, 'mp4',
+                        m3u8_id='hls', fatal=False))
+                elif encoding_format == 'mpd':
+                    formats.extend(self._extract_mpd_formats(
+                        playlist_url, video_id, mpd_id='dash', fatal=False))
+                encoding_url = encoding.get('url')
+                file_url = encoding.get('file_url')
+                if not encoding_url and not file_url:
                     continue
-                fmt = f.copy()
-                rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
-                if rtmp:
-                    fmt.update({
-                        'url': rtmp.group('url'),
-                        'play_path': rtmp.group('playpath'),
-                        'app': rtmp.group('app'),
-                        'ext': 'flv',
-                        'format_id': 'rtmp',
-                    })
-                else:
-                    fmt.update({
-                        'url': f_url,
-                        'format_id': 'http',
-                    })
-                formats.append(fmt)
+                f = {
+                    'width': int_or_none(encoding.get('width')),
+                    'height': int_or_none(encoding.get('height')),
+                    'vbr': int_or_none(encoding.get('video_bitrate')),
+                    'abr': int_or_none(encoding.get('audio_bitrate')),
+                    'filesize': int_or_none(encoding.get('size_in_bytes')),
+                    'vcodec': encoding.get('video_codec'),
+                    'acodec': encoding.get('audio_codec'),
+                    'container': encoding.get('container_type'),
+                }
+                for f_url in (encoding_url, file_url):
+                    if not f_url:
+                        continue
+                    fmt = f.copy()
+                    rtmp = re.search(r'^(?P<url>rtmpe?://(?P<host>[^/]+)/(?P<app>.+))/(?P<playpath>mp[34]:.+)$', f_url)
+                    if rtmp:
+                        fmt.update({
+                            'url': rtmp.group('url'),
+                            'play_path': rtmp.group('playpath'),
+                            'app': rtmp.group('app'),
+                            'ext': 'flv',
+                            'format_id': 'rtmp',
+                        })
+                    else:
+                        fmt.update({
+                            'url': f_url,
+                            'format_id': 'http',
+                        })
+                    formats.append(fmt)
         self._sort_formats(formats)
 
+        title = media['title']
+
         subtitles = {}
         for closed_caption in media.get('closed_captions', []):
             sub_url = closed_caption.get('file')
@@ -140,7 +153,7 @@ class CuriosityStreamCollectionIE(CuriosityStreamBaseIE):
             'title': 'Curious Minds: The Internet',
             'description': 'How is the internet shaping our lives in the 21st Century?',
         },
-        'playlist_mincount': 17,
+        'playlist_mincount': 16,
     }, {
         'url': 'https://curiositystream.com/series/2',
         'only_matching': True,

yt_dlp/extractor/discoveryplusindia.py

@@ -0,0 +1,100 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from ..compat import compat_str
+from ..utils import try_get
+from .common import InfoExtractor
+from .dplay import DPlayIE
+
+
+class DiscoveryPlusIndiaIE(DPlayIE):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/videos?' + DPlayIE._PATH_REGEX
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.in/videos/how-do-they-do-it/fugu-and-more?seasonId=8&type=EPISODE',
+        'info_dict': {
+            'id': '27104',
+            'ext': 'mp4',
+            'display_id': 'how-do-they-do-it/fugu-and-more',
+            'title': 'Fugu and More',
+            'description': 'The Japanese catch, prepare and eat the deadliest fish on the planet.',
+            'duration': 1319,
+            'timestamp': 1582309800,
+            'upload_date': '20200221',
+            'series': 'How Do They Do It?',
+            'season_number': 8,
+            'episode_number': 2,
+            'creator': 'Discovery Channel',
+        },
+        'params': {
+            'format': 'bestvideo',
+            'skip_download': True,
+        },
+        'skip': 'Cookies (not necessarily logged in) are needed'
+    }]
+
+    def _update_disco_api_headers(self, headers, disco_base, display_id, realm):
+        headers['x-disco-params'] = 'realm=%s' % realm
+        headers['x-disco-client'] = 'WEB:UNKNOWN:dplus-india:17.0.0'
+
+    def _download_video_playback_info(self, disco_base, video_id, headers):
+        return self._download_json(
+            disco_base + 'playback/v3/videoPlaybackInfo',
+            video_id, headers=headers, data=json.dumps({
+                'deviceInfo': {
+                    'adBlocker': False,
+                },
+                'videoId': video_id,
+            }).encode('utf-8'))['data']['attributes']['streaming']
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        return self._get_disco_api_info(
+            url, display_id, 'ap2-prod-direct.discoveryplus.in', 'dplusindia', 'in')
+
+
+class DiscoveryPlusIndiaShowIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?discoveryplus\.in/show/(?P<show_name>[^/]+)/?(?:[?#]|$)'
+    _TESTS = [{
+        'url': 'https://www.discoveryplus.in/show/how-do-they-do-it',
+        'playlist_mincount': 140,
+        'info_dict': {
+            'id': 'how-do-they-do-it',
+        },
+    }
+    ]
+
+    def _entries(self, show_name):
+        headers = {
+            'x-disco-client': 'WEB:UNKNOWN:dplus-india:prod',
+            'x-disco-params': 'realm=dplusindia',
+            'referer': 'https://www.discoveryplus.in/',
+        }
+        show_url = 'https://ap2-prod-direct.discoveryplus.in/cms/routes/show/{}?include=default'.format(show_name)
+        show_json = self._download_json(show_url,
+                                        video_id=show_name,
+                                        headers=headers)['included'][4]['attributes']['component']
+        show_id = show_json['mandatoryParams'].split('=')[-1]
+        season_url = 'https://ap2-prod-direct.discoveryplus.in/content/videos?sort=episodeNumber&filter[seasonNumber]={}&filter[show.id]={}&page[size]=100&page[number]={}'
+        for season in show_json['filters'][0]['options']:
+            season_id = season['id']
+            total_pages, page_num = 1, 0
+            while page_num < total_pages:
+                season_json = self._download_json(season_url.format(season_id, show_id, compat_str(page_num + 1)),
+                                                  video_id=show_id, headers=headers,
+                                                  note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
+                if page_num == 0:
+                    total_pages = try_get(season_json, lambda x: x['meta']['totalPages'], int) or 1
+                episodes_json = season_json['data']
+                for episode in episodes_json:
+                    video_id = episode['attributes']['path']
+                    yield self.url_result(
+                        'https://discoveryplus.in/videos/%s' % video_id,
+                        ie=DiscoveryPlusIndiaIE.ie_key(), video_id=video_id)
+                page_num += 1
+
+    def _real_extract(self, url):
+        show_name = re.match(self._VALID_URL, url).group('show_name')
+        return self.playlist_result(self._entries(show_name), playlist_id=show_name)

yt_dlp/extractor/dreisat.py

@@ -1,193 +1,43 @@
 from __future__ import unicode_literals
 
-import re
-
-from .common import InfoExtractor
-from ..utils import (
-    int_or_none,
-    unified_strdate,
-    xpath_text,
-    determine_ext,
-    float_or_none,
-    ExtractorError,
-)
+from .zdf import ZDFIE
 
 
-class DreiSatIE(InfoExtractor):
+class DreiSatIE(ZDFIE):
     IE_NAME = '3sat'
-    _GEO_COUNTRIES = ['DE']
-    _VALID_URL = r'https?://(?:www\.)?3sat\.de/mediathek/(?:(?:index|mediathek)\.php)?\?(?:(?:mode|display)=[^&]+&)*obj=(?P<id>[0-9]+)'
-    _TESTS = [
-        {
-            'url': 'http://www.3sat.de/mediathek/index.php?mode=play&obj=45918',
-            'md5': 'be37228896d30a88f315b638900a026e',
-            'info_dict': {
-                'id': '45918',
-                'ext': 'mp4',
-                'title': 'Waidmannsheil',
-                'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
-                'uploader': 'SCHWEIZWEIT',
-                'uploader_id': '100000210',
-                'upload_date': '20140913'
-            },
-            'params': {
-                'skip_download': True,  # m3u8 downloads
-            }
+    _VALID_URL = r'https?://(?:www\.)?3sat\.de/(?:[^/]+/)*(?P<id>[^/?#&]+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/dokumentation/ab-18/10-wochen-sommer-102.html
+        'url': 'https://www.3sat.de/film/ab-18/10-wochen-sommer-108.html',
+        'md5': '0aff3e7bc72c8813f5e0fae333316a1d',
+        'info_dict': {
+            'id': '141007_ab18_10wochensommer_film',
+            'ext': 'mp4',
+            'title': 'Ab 18! - 10 Wochen Sommer',
+            'description': 'md5:8253f41dc99ce2c3ff892dac2d65fe26',
+            'duration': 2660,
+            'timestamp': 1608604200,
+            'upload_date': '20201222',
         },
-        {
-            'url': 'http://www.3sat.de/mediathek/mediathek.php?mode=play&obj=51066',
-            'only_matching': True,
+    }, {
+        'url': 'https://www.3sat.de/gesellschaft/schweizweit/waidmannsheil-100.html',
+        'info_dict': {
+            'id': '140913_sendung_schweizweit',
+            'ext': 'mp4',
+            'title': 'Waidmannsheil',
+            'description': 'md5:cce00ca1d70e21425e72c86a98a56817',
+            'timestamp': 1410623100,
+            'upload_date': '20140913'
         },
-    ]
-
-    def _parse_smil_formats(self, smil, smil_url, video_id, namespace=None, f4m_params=None, transform_rtmp_url=None):
-        param_groups = {}
-        for param_group in smil.findall(self._xpath_ns('./head/paramGroup', namespace)):
-            group_id = param_group.get(self._xpath_ns(
-                'id', 'http://www.w3.org/XML/1998/namespace'))
-            params = {}
-            for param in param_group:
-                params[param.get('name')] = param.get('value')
-            param_groups[group_id] = params
-
-        formats = []
-        for video in smil.findall(self._xpath_ns('.//video', namespace)):
-            src = video.get('src')
-            if not src:
-                continue
-            bitrate = int_or_none(self._search_regex(r'_(\d+)k', src, 'bitrate', None)) or float_or_none(video.get('system-bitrate') or video.get('systemBitrate'), 1000)
-            group_id = video.get('paramGroup')
-            param_group = param_groups[group_id]
-            for proto in param_group['protocols'].split(','):
-                formats.append({
-                    'url': '%s://%s' % (proto, param_group['host']),
-                    'app': param_group['app'],
-                    'play_path': src,
-                    'ext': 'flv',
-                    'format_id': '%s-%d' % (proto, bitrate),
-                    'tbr': bitrate,
-                })
-        self._sort_formats(formats)
-        return formats
-
-    def extract_from_xml_url(self, video_id, xml_url):
-        doc = self._download_xml(
-            xml_url, video_id,
-            note='Downloading video info',
-            errnote='Failed to download video info')
-
-        status_code = xpath_text(doc, './status/statuscode')
-        if status_code and status_code != 'ok':
-            if status_code == 'notVisibleAnymore':
-                message = 'Video %s is not available' % video_id
-            else:
-                message = '%s returned error: %s' % (self.IE_NAME, status_code)
-            raise ExtractorError(message, expected=True)
-
-        title = xpath_text(doc, './/information/title', 'title', True)
-
-        urls = []
-        formats = []
-        for fnode in doc.findall('.//formitaeten/formitaet'):
-            video_url = xpath_text(fnode, 'url')
-            if not video_url or video_url in urls:
-                continue
-            urls.append(video_url)
-
-            is_available = 'http://www.metafilegenerator' not in video_url
-            geoloced = 'static_geoloced_online' in video_url
-            if not is_available or geoloced:
-                continue
-
-            format_id = fnode.attrib['basetype']
-            format_m = re.match(r'''(?x)
-                (?P<vcodec>[^_]+)_(?P<acodec>[^_]+)_(?P<container>[^_]+)_
-                (?P<proto>[^_]+)_(?P<index>[^_]+)_(?P<indexproto>[^_]+)
-            ''', format_id)
-
-            ext = determine_ext(video_url, None) or format_m.group('container')
-
-            if ext == 'meta':
-                continue
-            elif ext == 'smil':
-                formats.extend(self._extract_smil_formats(
-                    video_url, video_id, fatal=False))
-            elif ext == 'm3u8':
-                # the certificates are misconfigured (see
-                # https://github.com/ytdl-org/youtube-dl/issues/8665)
-                if video_url.startswith('https://'):
-                    continue
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', 'm3u8_native',
-                    m3u8_id=format_id, fatal=False))
-            elif ext == 'f4m':
-                formats.extend(self._extract_f4m_formats(
-                    video_url, video_id, f4m_id=format_id, fatal=False))
-            else:
-                quality = xpath_text(fnode, './quality')
-                if quality:
-                    format_id += '-' + quality
-
-                abr = int_or_none(xpath_text(fnode, './audioBitrate'), 1000)
-                vbr = int_or_none(xpath_text(fnode, './videoBitrate'), 1000)
-
-                tbr = int_or_none(self._search_regex(
-                    r'_(\d+)k', video_url, 'bitrate', None))
-                if tbr and vbr and not abr:
-                    abr = tbr - vbr
-
-                formats.append({
-                    'format_id': format_id,
-                    'url': video_url,
-                    'ext': ext,
-                    'acodec': format_m.group('acodec'),
-                    'vcodec': format_m.group('vcodec'),
-                    'abr': abr,
-                    'vbr': vbr,
-                    'tbr': tbr,
-                    'width': int_or_none(xpath_text(fnode, './width')),
-                    'height': int_or_none(xpath_text(fnode, './height')),
-                    'filesize': int_or_none(xpath_text(fnode, './filesize')),
-                    'protocol': format_m.group('proto').lower(),
-                })
-
-        geolocation = xpath_text(doc, './/details/geolocation')
-        if not formats and geolocation and geolocation != 'none':
-            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
-
-        self._sort_formats(formats)
-
-        thumbnails = []
-        for node in doc.findall('.//teaserimages/teaserimage'):
-            thumbnail_url = node.text
-            if not thumbnail_url:
-                continue
-            thumbnail = {
-                'url': thumbnail_url,
-            }
-            thumbnail_key = node.get('key')
-            if thumbnail_key:
-                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
-                if m:
-                    thumbnail['width'] = int(m.group(1))
-                    thumbnail['height'] = int(m.group(2))
-            thumbnails.append(thumbnail)
-
-        upload_date = unified_strdate(xpath_text(doc, './/details/airtime'))
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': xpath_text(doc, './/information/detail'),
-            'duration': int_or_none(xpath_text(doc, './/details/lengthSec')),
-            'thumbnails': thumbnails,
-            'uploader': xpath_text(doc, './/details/originChannelTitle'),
-            'uploader_id': xpath_text(doc, './/details/originChannelId'),
-            'upload_date': upload_date,
-            'formats': formats,
+        'params': {
+            'skip_download': True,
         }
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        details_url = 'http://www.3sat.de/mediathek/xmlservice/web/beitragsDetails?id=%s' % video_id
-        return self.extract_from_xml_url(video_id, details_url)
+    }, {
+        # Same as https://www.zdf.de/filme/filme-sonstige/der-hauptmann-112.html
+        'url': 'https://www.3sat.de/film/spielfilm/der-hauptmann-100.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/wissen/nano/nano-21-mai-2019-102.html, equal media ids
+        'url': 'https://www.3sat.de/wissen/nano/nano-21-mai-2019-102.html',
+        'only_matching': True,
+    }]

yt_dlp/extractor/extractors.py

@@ -80,6 +80,7 @@ from .arte import (
     ArteTVEmbedIE,
     ArteTVPlaylistIE,
 )
+from .arnes import ArnesIE
 from .asiancrush import (
     AsianCrushIE,
     AsianCrushPlaylistIE,
@@ -103,11 +104,13 @@ from .awaan import (
 )
 from .azmedien import AZMedienIE
 from .baidu import BaiduVideoIE
+from .bandaichannel import BandaiChannelIE
 from .bandcamp import BandcampIE, BandcampAlbumIE, BandcampWeeklyIE
 from .bbc import (
     BBCCoUkIE,
     BBCCoUkArticleIE,
-    BBCCoUkIPlayerPlaylistIE,
+    BBCCoUkIPlayerEpisodesIE,
+    BBCCoUkIPlayerGroupIE,
     BBCCoUkPlaylistIE,
     BBCIE,
 )
@@ -207,7 +210,11 @@ from .cbsnews import (
     CBSNewsIE,
     CBSNewsLiveVideoIE,
 )
-from .cbssports import CBSSportsIE
+from .cbssports import (
+    CBSSportsEmbedIE,
+    CBSSportsIE,
+    TwentyFourSevenSportsIE,
+)
 from .ccc import (
     CCCIE,
     CCCPlaylistIE,
@@ -262,6 +269,7 @@ from .commonmistakes import CommonMistakesIE, UnicodeBOMIE
 from .commonprotocols import (
     MmsIE,
     RtmpIE,
+    ViewSourceIE,
 )
 from .condenast import CondeNastIE
 from .contv import CONtvIE
@@ -305,6 +313,10 @@ from .democracynow import DemocracynowIE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
+from .discoveryplusindia import (
+    DiscoveryPlusIndiaIE,
+    DiscoveryPlusIndiaShowIE,
+)
 from .dotsub import DotsubIE
 from .douyutv import (
     DouyuShowIE,
@@ -449,10 +461,7 @@ from .gamestar import GameStarIE
 from .gaskrank import GaskrankIE
 from .gazeta import GazetaIE
 from .gdcvault import GDCVaultIE
-from .gedi import (
-    GediIE,
-    GediEmbedsIE,
-)
+from .gedidigital import GediDigitalIE
 from .generic import GenericIE
 from .gfycat import GfycatIE
 from .giantbomb import GiantBombIE
@@ -583,7 +592,11 @@ from .kuwo import (
     KuwoCategoryIE,
     KuwoMvIE,
 )
-from .la7 import LA7IE
+from .la7 import (
+    LA7IE,
+    LA7PodcastEpisodeIE,
+    LA7PodcastIE,
+)
 from .laola1tv import (
     Laola1TvEmbedIE,
     Laola1TvIE,
@@ -624,7 +637,11 @@ from .limelight import (
     LimelightChannelIE,
     LimelightChannelListIE,
 )
-from .line import LineTVIE
+from .line import (
+    LineTVIE,
+    LineLiveIE,
+    LineLiveChannelIE,
+)
 from .linkedin import (
     LinkedInLearningIE,
     LinkedInLearningCourseIE,
@@ -662,6 +679,7 @@ from .mangomolo import (
     MangomoloLiveIE,
 )
 from .manyvids import ManyVidsIE
+from .maoritv import MaoriTVIE
 from .markiza import (
     MarkizaIE,
     MarkizaPageIE,
@@ -710,7 +728,10 @@ from .mixcloud import (
     MixcloudUserIE,
     MixcloudPlaylistIE,
 )
-from .mlb import MLBIE
+from .mlb import (
+    MLBIE,
+    MLBVideoIE,
+)
 from .mnet import MnetIE
 from .moevideo import MoeVideoIE
 from .mofosex import (
@@ -734,9 +755,12 @@ from .mtv import (
     MTVServicesEmbeddedIE,
     MTVDEIE,
     MTVJapanIE,
+    MTVItaliaIE,
+    MTVItaliaProgrammaIE,
 )
 from .muenchentv import MuenchenTVIE
 from .mwave import MwaveIE, MwaveMeetGreetIE
+from .mxplayer import MxplayerIE
 from .mychannels import MyChannelsIE
 from .myspace import MySpaceIE, MySpaceAlbumIE
 from .myspass import MySpassIE
@@ -779,8 +803,9 @@ from .ndr import (
     NJoyEmbedIE,
 )
 from .ndtv import NDTVIE
-from .netzkino import NetzkinoIE
+from .nebula import NebulaIE
 from .nerdcubed import NerdCubedFeedIE
+from .netzkino import NetzkinoIE
 from .neteasemusic import (
     NetEaseMusicIE,
     NetEaseMusicAlbumIE,
@@ -805,6 +830,7 @@ from .nexx import (
     NexxIE,
     NexxEmbedIE,
 )
+from .nfhsnetwork import NFHSNetworkIE
 from .nfl import (
     NFLIE,
     NFLArticleIE,
@@ -821,7 +847,7 @@ from .nick import (
     NickNightIE,
     NickRuIE,
 )
-from .niconico import NiconicoIE, NiconicoPlaylistIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE, NiconicoUserIE
 from .ninecninemedia import NineCNineMediaIE
 from .ninegag import NineGagIE
 from .ninenow import NineNowIE
@@ -916,6 +942,11 @@ from .packtpub import (
     PacktPubIE,
     PacktPubCourseIE,
 )
+from .palcomp3 import (
+    PalcoMP3IE,
+    PalcoMP3ArtistIE,
+    PalcoMP3VideoIE,
+)
 from .pandoratv import PandoraTVIE
 from .parliamentliveuk import ParliamentLiveUKIE
 from .patreon import PatreonIE
@@ -952,6 +983,7 @@ from .plays import PlaysTVIE
 from .playtvak import PlaytvakIE
 from .playvid import PlayvidIE
 from .playwire import PlaywireIE
+from .plutotv import PlutoTVIE
 from .pluralsight import (
     PluralsightIE,
     PluralsightCourseIE,
@@ -1177,7 +1209,10 @@ from .spike import (
     BellatorIE,
     ParamountNetworkIE,
 )
-from .stitcher import StitcherIE
+from .stitcher import (
+    StitcherIE,
+    StitcherShowIE,
+)
 from .sport5 import Sport5IE
 from .sportbox import SportBoxIE
 from .sportdeutschland import SportDeutschlandIE
@@ -1558,6 +1593,7 @@ from .weibo import (
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
+from .wimtv import WimTVIE
 from .wistia import (
     WistiaIE,
     WistiaPlaylistIE,
@@ -1664,8 +1700,14 @@ from .zattoo import (
     ZattooLiveIE,
 )
 from .zdf import ZDFIE, ZDFChannelIE
+from .zee5 import (
+    Zee5IE,
+    Zee5SeriesIE,
+)
 from .zhihu import ZhihuIE
-from .zingmp3 import ZingMp3IE
-from .zee5 import Zee5IE
+from .zingmp3 import (
+    ZingMp3IE,
+    ZingMp3AlbumIE,
+)
 from .zoom import ZoomIE
 from .zype import ZypeIE

yt_dlp/extractor/francetv.py

@@ -401,7 +401,7 @@ class FranceTVInfoIE(FranceTVBaseInfoExtractor):
             (r'player\.load[^;]+src:\s*["\']([^"\']+)',
              r'id-video=([^@]+@[^"]+)',
              r'<a[^>]+href="(?:https?:)?//videos\.francetv\.fr/video/([^@]+@[^"]+)"',
-             r'data-id="([^"]+)"'),
+             r'data-id=["\']([\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'),
             webpage, 'video id')
 
         return self._make_url_result(video_id)

yt_dlp/extractor/fujitv.py

@@ -17,7 +17,7 @@ class FujiTVFODPlus7IE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
         formats = self._extract_m3u8_formats(
-            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id)
+            self._BASE_URL + 'abr/pc_html5/%s.m3u8' % video_id, video_id, 'mp4')
         for f in formats:
             wh = self._BITRATE_MAP.get(f.get('tbr'))
             if wh:

yt_dlp/extractor/gedi.py

@@ -1,266 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
-    base_url,
-    url_basename,
-    urljoin,
-)
-
-
-class GediBaseIE(InfoExtractor):
-    @staticmethod
-    def _clean_audio_fmts(formats):
-        unique_formats = []
-        for f in formats:
-            if 'acodec' in f:
-                unique_formats.append(f)
-        formats[:] = unique_formats
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-        player_data = re.findall(
-            r'PlayerFactory\.setParam\(\'(?P<type>.+?)\',\s*\'(?P<name>.+?)\',\s*\'(?P<val>.+?)\'\);',
-            webpage)
-
-        formats = []
-        audio_fmts = []
-        hls_fmts = []
-        http_fmts = []
-        title = ''
-        thumb = ''
-
-        fmt_reg = r'(?P<t>video|audio)-(?P<p>rrtv|hls)-(?P<h>[\w\d]+)(?:-(?P<br>[\w\d]+))?$'
-        br_reg = r'video-rrtv-(?P<br>\d+)-'
-
-        for t, n, v in player_data:
-            if t == 'format':
-                m = re.match(fmt_reg, n)
-                if m:
-                    # audio formats
-                    if m.group('t') == 'audio':
-                        if m.group('p') == 'hls':
-                            audio_fmts.extend(self._extract_m3u8_formats(
-                                v, video_id, 'm4a', m3u8_id='hls', fatal=False))
-                        elif m.group('p') == 'rrtv':
-                            audio_fmts.append({
-                                'format_id': 'mp3',
-                                'url': v,
-                                'tbr': 128,
-                                'ext': 'mp3',
-                                'vcodec': 'none',
-                                'acodec': 'mp3',
-                            })
-
-                    # video formats
-                    elif m.group('t') == 'video':
-                        # hls manifest video
-                        if m.group('p') == 'hls':
-                            hls_fmts.extend(self._extract_m3u8_formats(
-                                v, video_id, 'mp4', m3u8_id='hls', fatal=False))
-                        # direct mp4 video
-                        elif m.group('p') == 'rrtv':
-                            if not m.group('br'):
-                                mm = re.search(br_reg, v)
-                            http_fmts.append({
-                                'format_id': 'https-' + m.group('h'),
-                                'protocol': 'https',
-                                'url': v,
-                                'tbr': int(m.group('br')) if m.group('br') else
-                                (int(mm.group('br')) if mm.group('br') else 0),
-                                'height': int(m.group('h'))
-                            })
-
-            elif t == 'param':
-                if n == 'videotitle':
-                    title = v
-                if n == 'image_full_play':
-                    thumb = v
-
-        title = self._og_search_title(webpage) if title == '' else title
-
-        # clean weird char
-        title = compat_str(title).encode('utf8', 'replace').replace(b'\xc3\x82', b'').decode('utf8', 'replace')
-
-        if audio_fmts:
-            self._clean_audio_fmts(audio_fmts)
-            self._sort_formats(audio_fmts)
-        if hls_fmts:
-            self._sort_formats(hls_fmts)
-        if http_fmts:
-            self._sort_formats(http_fmts)
-
-        formats.extend(audio_fmts)
-        formats.extend(hls_fmts)
-        formats.extend(http_fmts)
-
-        return {
-            'id': video_id,
-            'title': title,
-            'description': self._html_search_meta('twitter:description', webpage),
-            'thumbnail': thumb,
-            'formats': formats,
-        }
-
-
-class GediIE(GediBaseIE):
-    _VALID_URL = r'''(?x)https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/(?!embed/).+?/(?P<id>[\d/]+)(?:\?|\&|$)'''
-    _TESTS = [{
-        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
-        'md5': '84658d7fb9e55a6e57ecc77b73137494',
-        'info_dict': {
-            'id': '121559/121683',
-            'ext': 'mp4',
-            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
-            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
-        'md5': 'e763b94b7920799a0e0e23ffefa2d157',
-        'info_dict': {
-            'id': '367415/367963',
-            'ext': 'mp4',
-            'title': 'Record della pista a Spa Francorchamps, la Pagani Huayra Roadster BC stupisce',
-            'description': 'md5:5deb503cefe734a3eb3f07ed74303920',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
-        'md5': 'e48108e97b1af137d22a8469f2019057',
-        'info_dict': {
-            'id': '66184/66267',
-            'ext': 'mp4',
-            'title': 'Cassani e i brividi azzurri ai Mondiali di Imola: \\"Qui mi sono innamorato del ciclismo da ragazzino, incredibile tornarci da ct\\"',
-            'description': 'md5:fc9c50894f70a2469bb9b54d3d0a3d3b',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
-        'md5': 'a6e39f3bdc1842bbd92abbbbef230817',
-        'info_dict': {
-            'id': '141059/142723',
-            'ext': 'mp4',
-            'title': 'Dentro la notizia - Ferrari, cosa succede a Maranello',
-            'description': 'md5:9907d65b53765681fa3a0b3122617c1f',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }]
-
-
-class GediEmbedsIE(GediBaseIE):
-    _VALID_URL = r'''(?x)https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/embed/.+?/(?P<id>[\d/]+)(?:\?|\&|$)'''
-    _TESTS = [{
-        'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
-        'md5': 'f4ac23cadfea7fef89bea536583fa7ed',
-        'info_dict': {
-            'id': '29312/29276',
-            'ext': 'mp4',
-            'title': 'Cotticelli: \\"Non so cosa mi sia successo. Sto cercando di capire se ho avuto un malore\\"',
-            'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }, {
-        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
-        'md5': '0391c2c83c6506581003aaf0255889c0',
-        'info_dict': {
-            'id': '14772/14870',
-            'ext': 'mp4',
-            'title': 'Festival EMERGENCY, Villa: «La buona informazione aiuta la salute» (14772-14870)',
-            'description': 'md5:2bce954d278248f3c950be355b7c2226',
-            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-social-play\.jpg$',
-        },
-    }]
-
-    @staticmethod
-    def _sanitize_urls(urls):
-        # add protocol if missing
-        for i, e in enumerate(urls):
-            if e.startswith('//'):
-                urls[i] = 'https:%s' % e
-        # clean iframes urls
-        for i, e in enumerate(urls):
-            urls[i] = urljoin(base_url(e), url_basename(e))
-        return urls
-
-    @staticmethod
-    def _extract_urls(webpage):
-        entries = [
-            mobj.group('url')
-            for mobj in re.finditer(r'''(?x)
-            (?:
-                data-frame-src=|
-                <iframe[^\n]+src=
-            )
-            (["'])
-                (?P<url>https?://video\.
-                    (?:
-                        (?:espresso\.)?repubblica
-                        |lastampa
-                        |huffingtonpost
-                        |ilsecoloxix
-                        |iltirreno
-                        |messaggeroveneto
-                        |ilpiccolo
-                        |gazzettadimantova
-                        |mattinopadova
-                        |laprovinciapavese
-                        |tribunatreviso
-                        |nuovavenezia
-                        |gazzettadimodena
-                        |lanuovaferrara
-                        |corrierealpi
-                        |lasentinella
-                    )
-                    (?:\.gelocal)?\.it/embed/.+?)
-            \1''', webpage)]
-        return GediEmbedsIE._sanitize_urls(entries)
-
-    @staticmethod
-    def _extract_url(webpage):
-        urls = GediEmbedsIE._extract_urls(webpage)
-        return urls[0] if urls else None

yt_dlp/extractor/gedidigital.py

@@ -0,0 +1,210 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    base_url,
+    determine_ext,
+    int_or_none,
+    url_basename,
+    urljoin,
+)
+
+
+class GediDigitalIE(InfoExtractor):
+    _VALID_URL = r'''(?x)(?P<url>(?:https?:)//video\.
+        (?:
+            (?:
+                (?:espresso\.)?repubblica
+                |lastampa
+                |ilsecoloxix
+                |huffingtonpost
+            )|
+            (?:
+                iltirreno
+                |messaggeroveneto
+                |ilpiccolo
+                |gazzettadimantova
+                |mattinopadova
+                |laprovinciapavese
+                |tribunatreviso
+                |nuovavenezia
+                |gazzettadimodena
+                |lanuovaferrara
+                |corrierealpi
+                |lasentinella
+            )\.gelocal
+        )\.it(?:/[^/]+){2,4}/(?P<id>\d+))(?:$|[?&].*)'''
+    _TESTS = [{
+        'url': 'https://video.lastampa.it/politica/il-paradosso-delle-regionali-la-lega-vince-ma-sembra-aver-perso/121559/121683',
+        'md5': '84658d7fb9e55a6e57ecc77b73137494',
+        'info_dict': {
+            'id': '121683',
+            'ext': 'mp4',
+            'title': 'Il paradosso delle Regionali: ecco perché la Lega vince ma sembra aver perso',
+            'description': 'md5:de7f4d6eaaaf36c153b599b10f8ce7ca',
+            'thumbnail': r're:^https://www\.repstatic\.it/video/photo/.+?-thumb-full-.+?\.jpg$',
+            'duration': 125,
+        },
+    }, {
+        'url': 'https://video.huffingtonpost.it/embed/politica/cotticelli-non-so-cosa-mi-sia-successo-sto-cercando-di-capire-se-ho-avuto-un-malore/29312/29276?responsive=true&el=video971040871621586700',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/embed/tutti-i-video/01-ted-villa/14772/14870&width=640&height=360',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.repubblica.it/motori/record-della-pista-a-spa-francorchamps-la-pagani-huayra-roadster-bc-stupisce/367415/367963',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilsecoloxix.it/sport/cassani-e-i-brividi-azzurri-ai-mondiali-di-imola-qui-mi-sono-innamorato-del-ciclismo-da-ragazzino-incredibile-tornarci-da-ct/66184/66267',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.iltirreno.gelocal.it/sport/dentro-la-notizia-ferrari-cosa-succede-a-maranello/141059/142723',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.messaggeroveneto.gelocal.it/locale/maria-giovanna-elmi-covid-vaccino/138155/139268',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.ilpiccolo.gelocal.it/dossier/big-john/dinosauro-big-john-al-via-le-visite-guidate-a-trieste/135226/135751',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimantova.gelocal.it/locale/dal-ponte-visconteo-di-valeggio-l-and-8217sos-dei-ristoratori-aprire-anche-a-cena/137310/137818',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.mattinopadova.gelocal.it/dossier/coronavirus-in-veneto/covid-a-vo-un-anno-dopo-un-cuore-tricolore-per-non-dimenticare/138402/138964',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.laprovinciapavese.gelocal.it/locale/mede-zona-rossa-via-alle-vaccinazioni-per-gli-over-80/137545/138120',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.tribunatreviso.gelocal.it/dossier/coronavirus-in-veneto/ecco-le-prima-vaccinazioni-di-massa-nella-marca/134485/135024',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.nuovavenezia.gelocal.it/locale/camion-troppo-alto-per-il-ponte-ferroviario-perde-il-carico/135734/136266',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.gazzettadimodena.gelocal.it/locale/modena-scoperta-la-proteina-che-predice-il-livello-di-gravita-del-covid/139109/139796',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lanuovaferrara.gelocal.it/locale/due-bombole-di-gpl-aperte-e-abbandonate-i-vigili-bruciano-il-gas/134391/134957',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.corrierealpi.gelocal.it/dossier/cortina-2021-i-mondiali-di-sci-alpino/mondiali-di-sci-il-timelapse-sulla-splendida-olympia/133760/134331',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.lasentinella.gelocal.it/locale/vestigne-centra-un-auto-e-si-ribalta/138931/139466',
+        'only_matching': True,
+    }, {
+        'url': 'https://video.espresso.repubblica.it/tutti-i-video/01-ted-villa/14772',
+        'only_matching': True,
+    }]
+
+    @staticmethod
+    def _sanitize_urls(urls):
+        # add protocol if missing
+        for i, e in enumerate(urls):
+            if e.startswith('//'):
+                urls[i] = 'https:%s' % e
+        # clean iframes urls
+        for i, e in enumerate(urls):
+            urls[i] = urljoin(base_url(e), url_basename(e))
+        return urls
+
+    @staticmethod
+    def _extract_urls(webpage):
+        entries = [
+            mobj.group('eurl')
+            for mobj in re.finditer(r'''(?x)
+            (?:
+                data-frame-src=|
+                <iframe[^\n]+src=
+            )
+            (["'])(?P<eurl>%s)\1''' % GediDigitalIE._VALID_URL, webpage)]
+        return GediDigitalIE._sanitize_urls(entries)
+
+    @staticmethod
+    def _extract_url(webpage):
+        urls = GediDigitalIE._extract_urls(webpage)
+        return urls[0] if urls else None
+
+    @staticmethod
+    def _clean_formats(formats):
+        format_urls = set()
+        clean_formats = []
+        for f in formats:
+            if f['url'] not in format_urls:
+                if f.get('audio_ext') != 'none' and not f.get('acodec'):
+                    continue
+                format_urls.add(f['url'])
+                clean_formats.append(f)
+        formats[:] = clean_formats
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        url = re.match(self._VALID_URL, url).group('url')
+        webpage = self._download_webpage(url, video_id)
+        title = self._html_search_meta(
+            ['twitter:title', 'og:title'], webpage, fatal=True)
+        player_data = re.findall(
+            r"PlayerFactory\.setParam\('(?P<type>format|param)',\s*'(?P<name>[^']+)',\s*'(?P<val>[^']+)'\);",
+            webpage)
+
+        formats = []
+        duration = thumb = None
+        for t, n, v in player_data:
+            if t == 'format':
+                if n in ('video-hds-vod-ec', 'video-hls-vod-ec', 'video-viralize', 'video-youtube-pfp'):
+                    continue
+                elif n.endswith('-vod-ak'):
+                    formats.extend(self._extract_akamai_formats(
+                        v, video_id, {'http': 'media.gedidigital.it'}))
+                else:
+                    ext = determine_ext(v)
+                    if ext == 'm3u8':
+                        formats.extend(self._extract_m3u8_formats(
+                            v, video_id, 'mp4', 'm3u8_native', m3u8_id=n, fatal=False))
+                        continue
+                    f = {
+                        'format_id': n,
+                        'url': v,
+                    }
+                    if ext == 'mp3':
+                        abr = int_or_none(self._search_regex(
+                            r'-mp3-audio-(\d+)', v, 'abr', default=None))
+                        f.update({
+                            'abr': abr,
+                            'tbr': abr,
+                            'acodec': ext,
+                            'vcodec': 'none'
+                        })
+                    else:
+                        mobj = re.match(r'^video-rrtv-(\d+)(?:-(\d+))?$', n)
+                        if mobj:
+                            f.update({
+                                'height': int(mobj.group(1)),
+                                'vbr': int_or_none(mobj.group(2)),
+                            })
+                        if not f.get('vbr'):
+                            f['vbr'] = int_or_none(self._search_regex(
+                                r'-video-rrtv-(\d+)', v, 'abr', default=None))
+                    formats.append(f)
+            elif t == 'param':
+                if n in ['image_full', 'image']:
+                    thumb = v
+                elif n == 'videoDuration':
+                    duration = int_or_none(v)
+
+        self._clean_formats(formats)
+        self._sort_formats(formats)
+
+        return {
+            'id': video_id,
+            'title': title,
+            'description': self._html_search_meta(
+                ['twitter:description', 'og:description', 'description'], webpage),
+            'thumbnail': thumb or self._og_search_thumbnail(webpage),
+            'formats': formats,
+            'duration': duration,
+        }

yt_dlp/extractor/generic.py

@@ -127,13 +127,14 @@ from .expressen import ExpressenIE
 from .zype import ZypeIE
 from .odnoklassniki import OdnoklassnikiIE
 from .kinja import KinjaEmbedIE
-from .gedi import GediEmbedsIE
+from .gedidigital import GediDigitalIE
 from .rcs import RCSEmbedsIE
 from .bitchute import BitChuteIE
 from .rumble import RumbleEmbedIE
 from .arcpublishing import ArcPublishingIE
 from .medialaan import MedialaanIE
 from .simplecast import SimplecastIE
+from .wimtv import WimTVIE
 
 
 class GenericIE(InfoExtractor):
@@ -2250,6 +2251,15 @@ class GenericIE(InfoExtractor):
             },
             'playlist_mincount': 52,
         },
+        {
+            # WimTv embed player
+            'url': 'http://www.msmotor.tv/wearefmi-pt-2-2021/',
+            'info_dict': {
+                'id': 'wearefmi-pt-2-2021',
+                'title': '#WEAREFMI – PT.2 – 2021 – MsMotorTV',
+            },
+            'playlist_count': 1,
+        },
     ]
 
     def report_following_redirect(self, new_url):
@@ -2649,6 +2659,15 @@ class GenericIE(InfoExtractor):
         if vid_me_embed_url is not None:
             return self.url_result(vid_me_embed_url, 'Vidme')
 
+        # Invidious Instances
+        # https://github.com/yt-dlp/yt-dlp/issues/195
+        # https://github.com/iv-org/invidious/pull/1730
+        youtube_url = self._search_regex(
+            r'<link rel="alternate" href="(https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
+            webpage, 'youtube link', default=None)
+        if youtube_url:
+            return self.url_result(youtube_url, YoutubeIE.ie_key())
+
         # Look for YouTube embeds
         youtube_urls = YoutubeIE._extract_urls(webpage)
         if youtube_urls:
@@ -2955,7 +2974,7 @@ class GenericIE(InfoExtractor):
             webpage)
         if not mobj:
             mobj = re.search(
-                r'data-video-link=["\'](?P<url>http://m.mlb.com/video/[^"\']+)',
+                r'data-video-link=["\'](?P<url>http://m\.mlb\.com/video/[^"\']+)',
                 webpage)
         if mobj is not None:
             return self.url_result(mobj.group('url'), 'MLB')
@@ -3339,17 +3358,22 @@ class GenericIE(InfoExtractor):
             return self.playlist_from_matches(
                 zype_urls, video_id, video_title, ie=ZypeIE.ie_key())
 
-        # Look for RCS media group embeds
-        gedi_urls = GediEmbedsIE._extract_urls(webpage)
+        gedi_urls = GediDigitalIE._extract_urls(webpage)
         if gedi_urls:
             return self.playlist_from_matches(
-                gedi_urls, video_id, video_title, ie=GediEmbedsIE.ie_key())
+                gedi_urls, video_id, video_title, ie=GediDigitalIE.ie_key())
 
+        # Look for RCS media group embeds
         rcs_urls = RCSEmbedsIE._extract_urls(webpage)
         if rcs_urls:
             return self.playlist_from_matches(
                 rcs_urls, video_id, video_title, ie=RCSEmbedsIE.ie_key())
 
+        wimtv_urls = WimTVIE._extract_urls(webpage)
+        if wimtv_urls:
+            return self.playlist_from_matches(
+                wimtv_urls, video_id, video_title, ie=WimTVIE.ie_key())
+
         bitchute_urls = BitChuteIE._extract_urls(webpage)
         if bitchute_urls:
             return self.playlist_from_matches(

yt_dlp/extractor/hrfensehen.py

@@ -4,7 +4,7 @@ from __future__ import unicode_literals
 import json
 import re
 
-from yt_dlp.utils import int_or_none, unified_timestamp, unescapeHTML
+from ..utils import int_or_none, unified_timestamp, unescapeHTML
 from .common import InfoExtractor
 
 

yt_dlp/extractor/instagram.py

@@ -12,6 +12,7 @@ from ..compat import (
 )
 from ..utils import (
     ExtractorError,
+    float_or_none,
     get_element_by_attribute,
     int_or_none,
     lowercase_escape,
@@ -32,6 +33,7 @@ class InstagramIE(InfoExtractor):
             'title': 'Video by naomipq',
             'description': 'md5:1f17f0ab29bd6fe2bfad705f58de3cb8',
             'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 0,
             'timestamp': 1371748545,
             'upload_date': '20130620',
             'uploader_id': 'naomipq',
@@ -48,6 +50,7 @@ class InstagramIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Video by britneyspears',
             'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 0,
             'timestamp': 1453760977,
             'upload_date': '20160125',
             'uploader_id': 'britneyspears',
@@ -86,6 +89,24 @@ class InstagramIE(InfoExtractor):
             'title': 'Post by instagram',
             'description': 'md5:0f9203fc6a2ce4d228da5754bcf54957',
         },
+    }, {
+        # IGTV
+        'url': 'https://www.instagram.com/tv/BkfuX9UB-eK/',
+        'info_dict': {
+            'id': 'BkfuX9UB-eK',
+            'ext': 'mp4',
+            'title': 'Fingerboarding Tricks with @cass.fb',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'duration': 53.83,
+            'timestamp': 1530032919,
+            'upload_date': '20180626',
+            'uploader_id': 'instagram',
+            'uploader': 'Instagram',
+            'like_count': int,
+            'comment_count': int,
+            'comments': list,
+            'description': 'Meet Cass Hirst (@cass.fb), a fingerboarding pro who can perform tiny ollies and kickflips while blindfolded.',
+        }
     }, {
         'url': 'https://instagram.com/p/-Cmh1cukG2/',
         'only_matching': True,
@@ -159,7 +180,9 @@ class InstagramIE(InfoExtractor):
             description = try_get(
                 media, lambda x: x['edge_media_to_caption']['edges'][0]['node']['text'],
                 compat_str) or media.get('caption')
+            title = media.get('title')
             thumbnail = media.get('display_src') or media.get('display_url')
+            duration = float_or_none(media.get('video_duration'))
             timestamp = int_or_none(media.get('taken_at_timestamp') or media.get('date'))
             uploader = media.get('owner', {}).get('full_name')
             uploader_id = media.get('owner', {}).get('username')
@@ -200,9 +223,10 @@ class InstagramIE(InfoExtractor):
                             continue
                         entries.append({
                             'id': node.get('shortcode') or node['id'],
-                            'title': 'Video %d' % edge_num,
+                            'title': node.get('title') or 'Video %d' % edge_num,
                             'url': node_video_url,
                             'thumbnail': node.get('display_url'),
+                            'duration': float_or_none(node.get('video_duration')),
                             'width': int_or_none(try_get(node, lambda x: x['dimensions']['width'])),
                             'height': int_or_none(try_get(node, lambda x: x['dimensions']['height'])),
                             'view_count': int_or_none(node.get('video_view_count')),
@@ -239,8 +263,9 @@ class InstagramIE(InfoExtractor):
             'id': video_id,
             'formats': formats,
             'ext': 'mp4',
-            'title': 'Video by %s' % uploader_id,
+            'title': title or 'Video by %s' % uploader_id,
             'description': description,
+            'duration': duration,
             'thumbnail': thumbnail,
             'timestamp': timestamp,
             'uploader_id': uploader_id,

yt_dlp/extractor/ivi.py

@@ -146,7 +146,7 @@ class IviIE(InfoExtractor):
                         expected=True)
                 elif not pycryptodomex_found:
                     raise ExtractorError(
-                        'pycryptodomex not found. Please install it.',
+                        'pycryptodomex not found. Please install',
                         expected=True)
                 elif message:
                     extractor_msg += ': ' + message

yt_dlp/extractor/jamendo.py

@@ -29,34 +29,51 @@ class JamendoIE(InfoExtractor):
             'id': '196219',
             'display_id': 'stories-from-emona-i',
             'ext': 'flac',
-            'title': 'Maya Filipič - Stories from Emona I',
-            'artist': 'Maya Filipič',
+            # 'title': 'Maya Filipič - Stories from Emona I',
+            'title': 'Stories from Emona I',
+            # 'artist': 'Maya Filipič',
             'track': 'Stories from Emona I',
             'duration': 210,
             'thumbnail': r're:^https?://.*\.jpg',
             'timestamp': 1217438117,
             'upload_date': '20080730',
+            'license': 'by-nc-nd',
+            'view_count': int,
+            'like_count': int,
+            'average_rating': int,
+            'tags': ['piano', 'peaceful', 'newage', 'strings', 'upbeat'],
         }
     }, {
         'url': 'https://licensing.jamendo.com/en/track/1496667/energetic-rock',
         'only_matching': True,
     }]
 
+    def _call_api(self, resource, resource_id):
+        path = '/api/%ss' % resource
+        rand = compat_str(random.random())
+        return self._download_json(
+            'https://www.jamendo.com' + path, resource_id, query={
+                'id[]': resource_id,
+            }, headers={
+                'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
+            })[0]
+
     def _real_extract(self, url):
         track_id, display_id = self._VALID_URL_RE.match(url).groups()
-        webpage = self._download_webpage(
-            'https://www.jamendo.com/track/' + track_id, track_id)
-        models = self._parse_json(self._html_search_regex(
-            r"data-bundled-models='([^']+)",
-            webpage, 'bundled models'), track_id)
-        track = models['track']['models'][0]
+        # webpage = self._download_webpage(
+        #     'https://www.jamendo.com/track/' + track_id, track_id)
+        # models = self._parse_json(self._html_search_regex(
+        #     r"data-bundled-models='([^']+)",
+        #     webpage, 'bundled models'), track_id)
+        # track = models['track']['models'][0]
+        track = self._call_api('track', track_id)
         title = track_name = track['name']
-        get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
-        artist = get_model('artist')
-        artist_name = artist.get('name')
-        if artist_name:
-            title = '%s - %s' % (artist_name, title)
-        album = get_model('album')
+        # get_model = lambda x: try_get(models, lambda y: y[x]['models'][0], dict) or {}
+        # artist = get_model('artist')
+        # artist_name = artist.get('name')
+        # if artist_name:
+        #     title = '%s - %s' % (artist_name, title)
+        # album = get_model('album')
 
         formats = [{
             'url': 'https://%s.jamendo.com/?trackid=%s&format=%s&from=app-97dab294'
@@ -74,7 +91,7 @@ class JamendoIE(InfoExtractor):
 
         urls = []
         thumbnails = []
-        for _, covers in track.get('cover', {}).items():
+        for covers in (track.get('cover') or {}).values():
             for cover_id, cover_url in covers.items():
                 if not cover_url or cover_url in urls:
                     continue
@@ -88,13 +105,14 @@ class JamendoIE(InfoExtractor):
                 })
 
         tags = []
-        for tag in track.get('tags', []):
+        for tag in (track.get('tags') or []):
             tag_name = tag.get('name')
             if not tag_name:
                 continue
             tags.append(tag_name)
 
         stats = track.get('stats') or {}
+        license = track.get('licenseCC') or []
 
         return {
             'id': track_id,
@@ -103,11 +121,11 @@ class JamendoIE(InfoExtractor):
             'title': title,
             'description': track.get('description'),
             'duration': int_or_none(track.get('duration')),
-            'artist': artist_name,
+            # 'artist': artist_name,
             'track': track_name,
-            'album': album.get('name'),
+            # 'album': album.get('name'),
             'formats': formats,
-            'license': '-'.join(track.get('licenseCC', [])) or None,
+            'license': '-'.join(license) if license else None,
             'timestamp': int_or_none(track.get('dateCreated')),
             'view_count': int_or_none(stats.get('listenedAll')),
             'like_count': int_or_none(stats.get('favorited')),
@@ -116,9 +134,9 @@ class JamendoIE(InfoExtractor):
         }
 
 
-class JamendoAlbumIE(InfoExtractor):
+class JamendoAlbumIE(JamendoIE):
     _VALID_URL = r'https?://(?:www\.)?jamendo\.com/album/(?P<id>[0-9]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'https://www.jamendo.com/album/121486/duck-on-cover',
         'info_dict': {
             'id': '121486',
@@ -151,17 +169,7 @@ class JamendoAlbumIE(InfoExtractor):
         'params': {
             'playlistend': 2
         }
-    }
-
-    def _call_api(self, resource, resource_id):
-        path = '/api/%ss' % resource
-        rand = compat_str(random.random())
-        return self._download_json(
-            'https://www.jamendo.com' + path, resource_id, query={
-                'id[]': resource_id,
-            }, headers={
-                'X-Jam-Call': '$%s*%s~' % (hashlib.sha1((path + rand).encode()).hexdigest(), rand)
-            })[0]
+    }]
 
     def _real_extract(self, url):
         album_id = self._match_id(url)
@@ -169,7 +177,7 @@ class JamendoAlbumIE(InfoExtractor):
         album_name = album.get('name')
 
         entries = []
-        for track in album.get('tracks', []):
+        for track in (album.get('tracks') or []):
             track_id = track.get('id')
             if not track_id:
                 continue

yt_dlp/extractor/la7.py

@@ -1,9 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
+import re
+
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
+    float_or_none,
+    parse_duration,
     smuggle_url,
+    unified_strdate,
 )
 
 
@@ -57,3 +63,141 @@ class LA7IE(InfoExtractor):
             'thumbnail': self._og_search_thumbnail(webpage, default=None),
             'ie_key': 'Kaltura',
         }
+
+
+class LA7PodcastEpisodeIE(InfoExtractor):
+    IE_NAME = 'la7.it:pod:episode'
+    _VALID_URL = r'''(?x)(https?://)?
+        (?:www\.)?la7\.it/[^/]+/podcast/([^/]+-)?(?P<id>\d+)'''
+
+    _TESTS = [{
+        'url': 'https://www.la7.it/voicetown/podcast/la-carezza-delle-memoria-di-carlo-verdone-23-03-2021-371497',
+        'md5': '7737d4d79b3c1a34b3de3e16297119ed',
+        'info_dict': {
+            'id': '371497',
+            'ext': 'mp3',
+            'title': '"La carezza delle memoria" di Carlo Verdone',
+            'description': 'md5:5abf07c3c551a687db80af3f9ceb7d52',
+            'thumbnail': 'https://www.la7.it/sites/default/files/podcast/371497.jpg',
+            'upload_date': '20210323',
+        },
+    }, {
+        # embed url
+        'url': 'https://www.la7.it/embed/podcast/371497',
+        'only_matching': True,
+    }, {
+        # date already in the title
+        'url': 'https://www.la7.it/propagandalive/podcast/lintervista-di-diego-bianchi-ad-annalisa-cuzzocrea-puntata-del-1932021-20-03-2021-371130',
+        'only_matching': True,
+    }, {
+        # title same as show_title
+        'url': 'https://www.la7.it/otto-e-mezzo/podcast/otto-e-mezzo-26-03-2021-372340',
+        'only_matching': True,
+    }]
+
+    def _extract_info(self, webpage, video_id=None, ppn=None):
+        if not video_id:
+            video_id = self._search_regex(
+                r'data-nid=([\'"])(?P<vid>\d+)\1',
+                webpage, 'video_id', group='vid')
+
+        media_url = self._search_regex(
+            (r'src:\s*([\'"])(?P<url>.+?mp3.+?)\1',
+             r'data-podcast=([\'"])(?P<url>.+?mp3.+?)\1'),
+            webpage, 'media_url', group='url')
+        ext = determine_ext(media_url)
+        formats = [{
+            'url': media_url,
+            'format_id': ext,
+            'ext': ext,
+        }]
+        self._sort_formats(formats)
+
+        title = self._html_search_regex(
+            (r'<div class="title">(?P<title>.+?)</',
+             r'<title>(?P<title>[^<]+)</title>',
+             r'title:\s*([\'"])(?P<title>.+?)\1'),
+            webpage, 'title', group='title')
+
+        description = (
+            self._html_search_regex(
+                (r'<div class="description">(.+?)</div>',
+                 r'<div class="description-mobile">(.+?)</div>',
+                 r'<div class="box-txt">([^<]+?)</div>',
+                 r'<div class="field-content"><p>(.+?)</p></div>'),
+                webpage, 'description', default=None)
+            or self._html_search_meta('description', webpage))
+
+        thumb = self._html_search_regex(
+            (r'<div class="podcast-image"><img src="(.+?)"></div>',
+             r'<div class="container-embed"[^<]+url\((.+?)\);">',
+             r'<div class="field-content"><img src="(.+?)"'),
+            webpage, 'thumbnail', fatal=False, default=None)
+
+        duration = parse_duration(self._html_search_regex(
+            r'<span class="(?:durata|duration)">([\d:]+)</span>',
+            webpage, 'duration', fatal=False, default=None))
+
+        date = self._html_search_regex(
+            r'class="data">\s*(?:<span>)?([\d\.]+)\s*</',
+            webpage, 'date', default=None)
+
+        date_alt = self._search_regex(
+            r'(\d+[\./]\d+[\./]\d+)', title, 'date_alt', default=None)
+        ppn = ppn or self._search_regex(
+            r'ppN:\s*([\'"])(?P<ppn>.+?)\1',
+            webpage, 'ppn', group='ppn', default=None)
+        # if the date is not in the title
+        # and title is the same as the show_title
+        # add the date to the title
+        if date and not date_alt and ppn and ppn.lower() == title.lower():
+            title += ' del %s' % date
+        return {
+            'id': video_id,
+            'title': title,
+            'description': description,
+            'duration': float_or_none(duration),
+            'formats': formats,
+            'thumbnail': thumb,
+            'upload_date': unified_strdate(date),
+        }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        return self._extract_info(webpage, video_id)
+
+
+class LA7PodcastIE(LA7PodcastEpisodeIE):
+    IE_NAME = 'la7.it:podcast'
+    _VALID_URL = r'(https?://)?(www\.)?la7\.it/(?P<id>[^/]+)/podcast/?(?:$|[#?])'
+
+    _TESTS = [{
+        'url': 'https://www.la7.it/propagandalive/podcast',
+        'info_dict': {
+            'id': 'propagandalive',
+            'title': "Propaganda Live",
+        },
+        'playlist_count': 10,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        title = (
+            self._html_search_regex(
+                r'<h1.*?>(.+?)</h1>', webpage, 'title', fatal=False, default=None)
+            or self._og_search_title(webpage))
+        ppn = self._search_regex(
+            r'window\.ppN\s*=\s*([\'"])(?P<ppn>.+?)\1',
+            webpage, 'ppn', group='ppn', default=None)
+
+        entries = []
+        for episode in re.finditer(
+                r'<div class="container-podcast-property">([\s\S]+?)(?:</div>\s*){3}',
+                webpage):
+            entries.append(self._extract_info(episode.group(1), ppn=ppn))
+
+        return self.playlist_result(entries, playlist_id, title)

yt_dlp/extractor/lbry.py

@@ -6,8 +6,10 @@ import json
 
 from .common import InfoExtractor
 from ..compat import (
+    compat_parse_qs,
     compat_str,
     compat_urllib_parse_unquote,
+    compat_urllib_parse_urlparse,
 )
 from ..utils import (
     determine_ext,
@@ -21,9 +23,9 @@ from ..utils import (
 
 
 class LBRYBaseIE(InfoExtractor):
-    _BASE_URL_REGEX = r'https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/'
+    _BASE_URL_REGEX = r'(?:https?://(?:www\.)?(?:lbry\.tv|odysee\.com)/|lbry://)'
     _CLAIM_ID_REGEX = r'[0-9a-f]{1,40}'
-    _OPT_CLAIM_ID = '[^:/?#&]+(?::%s)?' % _CLAIM_ID_REGEX
+    _OPT_CLAIM_ID = '[^:/?#&]+(?:[:#]%s)?' % _CLAIM_ID_REGEX
     _SUPPORTED_STREAM_TYPES = ['video', 'audio']
 
     def _call_api_proxy(self, method, display_id, params, resource):
@@ -41,7 +43,9 @@ class LBRYBaseIE(InfoExtractor):
             'resolve', display_id, {'urls': url}, resource)[url]
 
     def _permanent_url(self, url, claim_name, claim_id):
-        return urljoin(url, '/%s:%s' % (claim_name, claim_id))
+        return urljoin(
+            url.replace('lbry://', 'https://lbry.tv/'),
+            '/%s:%s' % (claim_name, claim_id))
 
     def _parse_stream(self, stream, url):
         stream_value = stream.get('value') or {}
@@ -60,6 +64,7 @@ class LBRYBaseIE(InfoExtractor):
             'description': stream_value.get('description'),
             'license': stream_value.get('license'),
             'timestamp': int_or_none(stream.get('timestamp')),
+            'release_timestamp': int_or_none(stream_value.get('release_time')),
             'tags': stream_value.get('tags'),
             'duration': int_or_none(media.get('duration')),
             'channel': try_get(signing_channel, lambda x: x['value']['title']),
@@ -92,6 +97,8 @@ class LBRYIE(LBRYBaseIE):
             'description': 'md5:f6cb5c704b332d37f5119313c2c98f51',
             'timestamp': 1595694354,
             'upload_date': '20200725',
+            'release_timestamp': 1595340697,
+            'release_date': '20200721',
             'width': 1280,
             'height': 720,
         }
@@ -106,6 +113,8 @@ class LBRYIE(LBRYBaseIE):
             'description': 'md5:661ac4f1db09f31728931d7b88807a61',
             'timestamp': 1591312601,
             'upload_date': '20200604',
+            'release_timestamp': 1591312421,
+            'release_date': '20200604',
             'tags': list,
             'duration': 2570,
             'channel': 'The LBRY Foundation',
@@ -137,6 +146,9 @@ class LBRYIE(LBRYBaseIE):
     }, {
         'url': 'https://lbry.tv/@lacajadepandora:a/TRUMP-EST%C3%81-BIEN-PUESTO-con-Pilar-Baselga,-Carlos-Senra,-Luis-Palacios-(720p_30fps_H264-192kbit_AAC):1',
         'only_matching': True,
+    }, {
+        'url': 'lbry://@lbry#3f/odysee#7',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -166,7 +178,7 @@ class LBRYIE(LBRYBaseIE):
 
 class LBRYChannelIE(LBRYBaseIE):
     IE_NAME = 'lbry:channel'
-    _VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?#&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
+    _VALID_URL = LBRYBaseIE._BASE_URL_REGEX + r'(?P<id>@%s)/?(?:[?&]|$)' % LBRYBaseIE._OPT_CLAIM_ID
     _TESTS = [{
         'url': 'https://lbry.tv/@LBRYFoundation:0',
         'info_dict': {
@@ -178,20 +190,24 @@ class LBRYChannelIE(LBRYBaseIE):
     }, {
         'url': 'https://lbry.tv/@LBRYFoundation',
         'only_matching': True,
+    }, {
+        'url': 'lbry://@lbry#3f',
+        'only_matching': True,
     }]
     _PAGE_SIZE = 50
 
-    def _fetch_page(self, claim_id, url, page):
+    def _fetch_page(self, claim_id, url, params, page):
         page += 1
+        page_params = {
+            'channel_ids': [claim_id],
+            'claim_type': 'stream',
+            'no_totals': True,
+            'page': page,
+            'page_size': self._PAGE_SIZE,
+        }
+        page_params.update(params)
         result = self._call_api_proxy(
-            'claim_search', claim_id, {
-                'channel_ids': [claim_id],
-                'claim_type': 'stream',
-                'no_totals': True,
-                'page': page,
-                'page_size': self._PAGE_SIZE,
-                'stream_types': self._SUPPORTED_STREAM_TYPES,
-            }, 'page %d' % page)
+            'claim_search', claim_id, page_params, 'page %d' % page)
         for item in (result.get('items') or []):
             stream_claim_name = item.get('name')
             stream_claim_id = item.get('claim_id')
@@ -212,8 +228,31 @@ class LBRYChannelIE(LBRYBaseIE):
         result = self._resolve_url(
             'lbry://' + display_id, display_id, 'channel')
         claim_id = result['claim_id']
+        qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
+        content = qs.get('content', [None])[0]
+        params = {
+            'fee_amount': qs.get('fee_amount', ['>=0'])[0],
+            'order_by': {
+                'new': ['release_time'],
+                'top': ['effective_amount'],
+                'trending': ['trending_group', 'trending_mixed'],
+            }[qs.get('order', ['new'])[0]],
+            'stream_types': [content] if content in ['audio', 'video'] else self._SUPPORTED_STREAM_TYPES,
+        }
+        duration = qs.get('duration', [None])[0]
+        if duration:
+            params['duration'] = {
+                'long': '>=1200',
+                'short': '<=240',
+            }[duration]
+        language = qs.get('language', ['all'])[0]
+        if language != 'all':
+            languages = [language]
+            if language == 'en':
+                languages.append('none')
+            params['any_languages'] = languages
         entries = OnDemandPagedList(
-            functools.partial(self._fetch_page, claim_id, url),
+            functools.partial(self._fetch_page, claim_id, url, params),
             self._PAGE_SIZE)
         result_value = result.get('value') or {}
         return self.playlist_result(

yt_dlp/extractor/line.py

@@ -4,7 +4,13 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..utils import js_to_json
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    js_to_json,
+    str_or_none,
+)
 
 
 class LineTVIE(InfoExtractor):
@@ -88,3 +94,137 @@ class LineTVIE(InfoExtractor):
                            for thumbnail in video_info.get('thumbnails', {}).get('list', [])],
             'view_count': video_info.get('meta', {}).get('count'),
         }
+
+
+class LineLiveBaseIE(InfoExtractor):
+    _API_BASE_URL = 'https://live-api.line-apps.com/web/v4.0/channel/'
+
+    def _parse_broadcast_item(self, item):
+        broadcast_id = compat_str(item['id'])
+        title = item['title']
+        is_live = item.get('isBroadcastingNow')
+
+        thumbnails = []
+        for thumbnail_id, thumbnail_url in (item.get('thumbnailURLs') or {}).items():
+            if not thumbnail_url:
+                continue
+            thumbnails.append({
+                'id': thumbnail_id,
+                'url': thumbnail_url,
+            })
+
+        channel = item.get('channel') or {}
+        channel_id = str_or_none(channel.get('id'))
+
+        return {
+            'id': broadcast_id,
+            'title': self._live_title(title) if is_live else title,
+            'thumbnails': thumbnails,
+            'timestamp': int_or_none(item.get('createdAt')),
+            'channel': channel.get('name'),
+            'channel_id': channel_id,
+            'channel_url': 'https://live.line.me/channels/' + channel_id if channel_id else None,
+            'duration': int_or_none(item.get('archiveDuration')),
+            'view_count': int_or_none(item.get('viewerCount')),
+            'comment_count': int_or_none(item.get('chatCount')),
+            'is_live': is_live,
+        }
+
+
+class LineLiveIE(LineLiveBaseIE):
+    _VALID_URL = r'https?://live\.line\.me/channels/(?P<channel_id>\d+)/broadcast/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://live.line.me/channels/4867368/broadcast/16331360',
+        'md5': 'bc931f26bf1d4f971e3b0982b3fab4a3',
+        'info_dict': {
+            'id': '16331360',
+            'title': '振りコピ講座😙😙😙',
+            'ext': 'mp4',
+            'timestamp': 1617095132,
+            'upload_date': '20210330',
+            'channel': '白川ゆめか',
+            'channel_id': '4867368',
+            'view_count': int,
+            'comment_count': int,
+            'is_live': False,
+        }
+    }, {
+        # archiveStatus == 'DELETED'
+        'url': 'https://live.line.me/channels/4778159/broadcast/16378488',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        channel_id, broadcast_id = re.match(self._VALID_URL, url).groups()
+        broadcast = self._download_json(
+            self._API_BASE_URL + '%s/broadcast/%s' % (channel_id, broadcast_id),
+            broadcast_id)
+        item = broadcast['item']
+        info = self._parse_broadcast_item(item)
+        protocol = 'm3u8' if info['is_live'] else 'm3u8_native'
+        formats = []
+        for k, v in (broadcast.get(('live' if info['is_live'] else 'archived') + 'HLSURLs') or {}).items():
+            if not v:
+                continue
+            if k == 'abr':
+                formats.extend(self._extract_m3u8_formats(
+                    v, broadcast_id, 'mp4', protocol,
+                    m3u8_id='hls', fatal=False))
+                continue
+            f = {
+                'ext': 'mp4',
+                'format_id': 'hls-' + k,
+                'protocol': protocol,
+                'url': v,
+            }
+            if not k.isdigit():
+                f['vcodec'] = 'none'
+            formats.append(f)
+        if not formats:
+            archive_status = item.get('archiveStatus')
+            if archive_status != 'ARCHIVED':
+                raise ExtractorError('this video has been ' + archive_status.lower(), expected=True)
+        self._sort_formats(formats)
+        info['formats'] = formats
+        return info
+
+
+class LineLiveChannelIE(LineLiveBaseIE):
+    _VALID_URL = r'https?://live\.line\.me/channels/(?P<id>\d+)(?!/broadcast/\d+)(?:[/?&#]|$)'
+    _TEST = {
+        'url': 'https://live.line.me/channels/5893542',
+        'info_dict': {
+            'id': '5893542',
+            'title': 'いくらちゃん',
+            'description': 'md5:c3a4af801f43b2fac0b02294976580be',
+        },
+        'playlist_mincount': 29
+    }
+
+    def _archived_broadcasts_entries(self, archived_broadcasts, channel_id):
+        while True:
+            for row in (archived_broadcasts.get('rows') or []):
+                share_url = str_or_none(row.get('shareURL'))
+                if not share_url:
+                    continue
+                info = self._parse_broadcast_item(row)
+                info.update({
+                    '_type': 'url',
+                    'url': share_url,
+                    'ie_key': LineLiveIE.ie_key(),
+                })
+                yield info
+            if not archived_broadcasts.get('hasNextPage'):
+                return
+            archived_broadcasts = self._download_json(
+                self._API_BASE_URL + channel_id + '/archived_broadcasts',
+                channel_id, query={
+                    'lastId': info['id'],
+                })
+
+    def _real_extract(self, url):
+        channel_id = self._match_id(url)
+        channel = self._download_json(self._API_BASE_URL + channel_id, channel_id)
+        return self.playlist_result(
+            self._archived_broadcasts_entries(channel.get('archivedBroadcasts') or {}, channel_id),
+            channel_id, channel.get('title'), channel.get('information'))

yt_dlp/extractor/linuxacademy.py

@@ -38,8 +38,8 @@ class LinuxAcademyIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'What Is Data Science',
             'description': 'md5:c574a3c20607144fb36cb65bdde76c99',
-            'timestamp': 1607387907,
-            'upload_date': '20201208',
+            'timestamp': int,  # The timestamp and upload date changes
+            'upload_date': r're:\d+',
             'duration': 304,
         },
         'params': {
@@ -59,6 +59,16 @@ class LinuxAcademyIE(InfoExtractor):
         },
         'playlist_count': 41,
         'skip': 'Requires Linux Academy account credentials',
+    }, {
+        'url': 'https://linuxacademy.com/cp/modules/view/id/39',
+        'info_dict': {
+            'id': '39',
+            'title': 'Red Hat Certified Systems Administrator - RHCSA (EX200) Exam Prep  (legacy)',
+            'description': 'md5:0f1d3369e90c3fb14a79813b863c902f',
+            'duration': 89280,
+        },
+        'playlist_count': 73,
+        'skip': 'Requires Linux Academy account credentials',
     }]
 
     _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
@@ -102,7 +112,7 @@ class LinuxAcademyIE(InfoExtractor):
             'client_id': self._CLIENT_ID,
             'redirect_uri': self._ORIGIN_URL,
             'tenant': 'lacausers',
-            'connection': 'Username-Password-Authentication',
+            'connection': 'Username-Password-ACG-Proxy',
             'username': username,
             'password': password,
             'sso': 'true',
@@ -162,7 +172,7 @@ class LinuxAcademyIE(InfoExtractor):
         if course_id:
             module = self._parse_json(
                 self._search_regex(
-                    r'window\.module\s*=\s*({.+?})\s*;', webpage, 'module'),
+                    r'window\.module\s*=\s*({(?:(?!};)[^"]|"([^"]|\\")*")+})\s*;', webpage, 'module'),
                 item_id)
             entries = []
             chapter_number = None

yt_dlp/extractor/maoritv.py

@@ -0,0 +1,31 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class MaoriTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?maoritelevision\.com/shows/(?:[^/]+/)+(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://www.maoritelevision.com/shows/korero-mai/S01E054/korero-mai-series-1-episode-54',
+        'md5': '5ade8ef53851b6a132c051b1cd858899',
+        'info_dict': {
+            'id': '4774724855001',
+            'ext': 'mp4',
+            'title': 'Kōrero Mai, Series 1 Episode 54',
+            'upload_date': '20160226',
+            'timestamp': 1456455018,
+            'description': 'md5:59bde32fd066d637a1a55794c56d8dcb',
+            'uploader_id': '1614493167001',
+        },
+    }
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1614493167001/HJlhIQhQf_default/index.html?videoId=%s'
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        brightcove_id = self._search_regex(
+            r'data-main-video-id=["\'](\d+)', webpage, 'brightcove id')
+        return self.url_result(
+            self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+            'BrightcoveNew', brightcove_id)

yt_dlp/extractor/mildom.py

@@ -5,6 +5,7 @@ from datetime import datetime
 import itertools
 import json
 import base64
+import re
 
 from .common import InfoExtractor
 from ..utils import (
@@ -68,7 +69,7 @@ class MildomBaseIE(InfoExtractor):
                 self._DISPATCHER_CONFIG = self._parse_json(base64.b64decode(tmp['data']), 'initialization')
             except ExtractorError:
                 self._DISPATCHER_CONFIG = self._download_json(
-                    'https://bookish-octo-barnacle.vercel.app/api/dispatcher_config', 'initialization',
+                    'https://bookish-octo-barnacle.vercel.app/api/mildom/dispatcher_config', 'initialization',
                     note='Downloading dispatcher_config fallback')
         return self._DISPATCHER_CONFIG
 
@@ -110,6 +111,7 @@ class MildomIE(MildomBaseIE):
         enterstudio = self._call_api(
             'https://cloudac.mildom.com/nonolive/gappserv/live/enterstudio', video_id,
             note='Downloading live metadata', query={'user_id': video_id})
+        result_video_id = enterstudio.get('log_id', video_id)
 
         title = try_get(
             enterstudio, (
@@ -128,7 +130,7 @@ class MildomIE(MildomBaseIE):
             ), compat_str)
 
         servers = self._call_api(
-            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', video_id,
+            'https://cloudac.mildom.com/nonolive/gappserv/live/liveserver', result_video_id,
             note='Downloading live server list', query={
                 'user_id': video_id,
                 'live_server_type': 'hls',
@@ -139,7 +141,7 @@ class MildomIE(MildomBaseIE):
             'is_lhls': '0',
         })
         m3u8_url = update_url_query(servers['stream_server'] + '/%s_master.m3u8' % video_id, stream_query)
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', headers={
+        formats = self._extract_m3u8_formats(m3u8_url, result_video_id, 'mp4', headers={
             'Referer': 'https://www.mildom.com/',
             'Origin': 'https://www.mildom.com',
         }, note='Downloading m3u8 information')
@@ -150,13 +152,13 @@ class MildomIE(MildomBaseIE):
             parsed = parsed._replace(
                 netloc='bookish-octo-barnacle.vercel.app',
                 query=compat_urllib_parse_urlencode(stream_query, True),
-                path='/api' + parsed.path)
+                path='/api/mildom' + parsed.path)
             fmt['url'] = compat_urlparse.urlunparse(parsed)
 
         self._sort_formats(formats)
 
         return {
-            'id': video_id,
+            'id': result_video_id,
             'title': title,
             'description': description,
             'uploader': uploader,
@@ -172,9 +174,8 @@ class MildomVodIE(MildomBaseIE):
     _VALID_URL = r'https?://(?:(?:www|m)\.)mildom\.com/playback/(?P<user_id>\d+)/(?P<id>(?P=user_id)-[a-zA-Z0-9]+)'
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
-        m = self._VALID_URL_RE.match(url)
-        user_id = m.group('user_id')
+        m = re.match(self._VALID_URL, url)
+        user_id, video_id = m.group('user_id'), m.group('id')
         url = 'https://www.mildom.com/playback/%s/%s' % (user_id, video_id)
 
         webpage = self._download_webpage(url, video_id)
@@ -230,7 +231,7 @@ class MildomVodIE(MildomBaseIE):
             parsed = parsed._replace(
                 netloc='bookish-octo-barnacle.vercel.app',
                 query=compat_urllib_parse_urlencode(stream_query, True),
-                path='/api/vod2/proxy')
+                path='/api/mildom/vod2/proxy')
             fmt['url'] = compat_urlparse.urlunparse(parsed)
 
         self._sort_formats(formats)

yt_dlp/extractor/mlb.py

@@ -1,15 +1,91 @@
 from __future__ import unicode_literals
 
-from .nhl import NHLBaseIE
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    determine_ext,
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+    try_get,
+)
 
 
-class MLBIE(NHLBaseIE):
+class MLBBaseIE(InfoExtractor):
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        video = self._download_video_data(display_id)
+        video_id = video['id']
+        title = video['title']
+        feed = self._get_feed(video)
+
+        formats = []
+        for playback in (feed.get('playbacks') or []):
+            playback_url = playback.get('url')
+            if not playback_url:
+                continue
+            name = playback.get('name')
+            ext = determine_ext(playback_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    playback_url, video_id, 'mp4',
+                    'm3u8_native', m3u8_id=name, fatal=False))
+            else:
+                f = {
+                    'format_id': name,
+                    'url': playback_url,
+                }
+                mobj = re.search(r'_(\d+)K_(\d+)X(\d+)', name)
+                if mobj:
+                    f.update({
+                        'height': int(mobj.group(3)),
+                        'tbr': int(mobj.group(1)),
+                        'width': int(mobj.group(2)),
+                    })
+                mobj = re.search(r'_(\d+)x(\d+)_(\d+)_(\d+)K\.mp4', playback_url)
+                if mobj:
+                    f.update({
+                        'fps': int(mobj.group(3)),
+                        'height': int(mobj.group(2)),
+                        'tbr': int(mobj.group(4)),
+                        'width': int(mobj.group(1)),
+                    })
+                formats.append(f)
+        self._sort_formats(formats)
+
+        thumbnails = []
+        for cut in (try_get(feed, lambda x: x['image']['cuts'], list) or []):
+            src = cut.get('src')
+            if not src:
+                continue
+            thumbnails.append({
+                'height': int_or_none(cut.get('height')),
+                'url': src,
+                'width': int_or_none(cut.get('width')),
+            })
+
+        language = (video.get('language') or 'EN').lower()
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': video.get('description'),
+            'duration': parse_duration(feed.get('duration')),
+            'thumbnails': thumbnails,
+            'timestamp': parse_iso8601(video.get(self._TIMESTAMP_KEY)),
+            'subtitles': self._extract_mlb_subtitles(feed, language),
+        }
+
+
+class MLBIE(MLBBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
-                        (?:[\da-z_-]+\.)*(?P<site>mlb)\.com/
+                        (?:[\da-z_-]+\.)*mlb\.com/
                         (?:
                             (?:
-                                (?:[^/]+/)*c-|
+                                (?:[^/]+/)*video/[^/]+/c-|
                                 (?:
                                     shared/video/embed/(?:embed|m-internal-embed)\.html|
                                     (?:[^/]+/)+(?:play|index)\.jsp|
@@ -18,7 +94,6 @@ class MLBIE(NHLBaseIE):
                             (?P<id>\d+)
                         )
                     '''
-    _CONTENT_DOMAIN = 'content.mlb.com'
     _TESTS = [
         {
             'url': 'https://www.mlb.com/mariners/video/ackleys-spectacular-catch/c-34698933',
@@ -76,18 +151,6 @@ class MLBIE(NHLBaseIE):
                 'thumbnail': r're:^https?://.*\.jpg$',
             },
         },
-        {
-            'url': 'https://www.mlb.com/news/blue-jays-kevin-pillar-goes-spidey-up-the-wall-to-rob-tim-beckham-of-a-homer/c-118550098',
-            'md5': 'e09e37b552351fddbf4d9e699c924d68',
-            'info_dict': {
-                'id': '75609783',
-                'ext': 'mp4',
-                'title': 'Must C: Pillar climbs for catch',
-                'description': '4/15/15: Blue Jays outfielder Kevin Pillar continues his defensive dominance by climbing the wall in left to rob Tim Beckham of a home run',
-                'timestamp': 1429139220,
-                'upload_date': '20150415',
-            }
-        },
         {
             'url': 'https://www.mlb.com/video/hargrove-homers-off-caldwell/c-1352023483?tid=67793694',
             'only_matching': True,
@@ -113,8 +176,92 @@ class MLBIE(NHLBaseIE):
             'url': 'http://mlb.mlb.com/shared/video/embed/m-internal-embed.html?content_id=75609783&property=mlb&autoplay=true&hashmode=false&siteSection=mlb/multimedia/article_118550098/article_embed&club=mlb',
             'only_matching': True,
         },
-        {
-            'url': 'https://www.mlb.com/cut4/carlos-gomez-borrowed-sunglasses-from-an-as-fan/c-278912842',
-            'only_matching': True,
-        }
     ]
+    _TIMESTAMP_KEY = 'date'
+
+    @staticmethod
+    def _get_feed(video):
+        return video
+
+    @staticmethod
+    def _extract_mlb_subtitles(feed, language):
+        subtitles = {}
+        for keyword in (feed.get('keywordsAll') or []):
+            keyword_type = keyword.get('type')
+            if keyword_type and keyword_type.startswith('closed_captions_location_'):
+                cc_location = keyword.get('value')
+                if cc_location:
+                    subtitles.setdefault(language, []).append({
+                        'url': cc_location,
+                    })
+        return subtitles
+
+    def _download_video_data(self, display_id):
+        return self._download_json(
+            'http://content.mlb.com/mlb/item/id/v1/%s/details/web-v1.json' % display_id,
+            display_id)
+
+
+class MLBVideoIE(MLBBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?mlb\.com/(?:[^/]+/)*video/(?P<id>[^/?&#]+)'
+    _TEST = {
+        'url': 'https://www.mlb.com/mariners/video/ackley-s-spectacular-catch-c34698933',
+        'md5': '632358dacfceec06bad823b83d21df2d',
+        'info_dict': {
+            'id': 'c04a8863-f569-42e6-9f87-992393657614',
+            'ext': 'mp4',
+            'title': "Ackley's spectacular catch",
+            'description': 'md5:7f5a981eb4f3cbc8daf2aeffa2215bf0',
+            'duration': 66,
+            'timestamp': 1405995000,
+            'upload_date': '20140722',
+            'thumbnail': r're:^https?://.+',
+        },
+    }
+    _TIMESTAMP_KEY = 'timestamp'
+
+    @classmethod
+    def suitable(cls, url):
+        return False if MLBIE.suitable(url) else super(MLBVideoIE, cls).suitable(url)
+
+    @staticmethod
+    def _get_feed(video):
+        return video['feeds'][0]
+
+    @staticmethod
+    def _extract_mlb_subtitles(feed, language):
+        subtitles = {}
+        for cc_location in (feed.get('closedCaptions') or []):
+            subtitles.setdefault(language, []).append({
+                'url': cc_location,
+            })
+
+    def _download_video_data(self, display_id):
+        # https://www.mlb.com/data-service/en/videos/[SLUG]
+        return self._download_json(
+            'https://fastball-gateway.mlb.com/graphql',
+            display_id, query={
+                'query': '''{
+  mediaPlayback(ids: "%s") {
+    description
+    feeds(types: CMS) {
+      closedCaptions
+      duration
+      image {
+        cuts {
+          width
+          height
+          src
+        }
+      }
+      playbacks {
+        name
+        url
+      }
+    }
+    id
+    timestamp
+    title
+  }
+}''' % display_id,
+            })['data']['mediaPlayback'][0]

yt_dlp/extractor/mtv.py

@@ -7,7 +7,6 @@ from .common import InfoExtractor
 from ..compat import (
     compat_str,
     compat_xpath,
-    compat_urlparse,
 )
 from ..utils import (
     ExtractorError,
@@ -15,6 +14,7 @@ from ..utils import (
     fix_xml_ampersands,
     float_or_none,
     HEADRequest,
+    int_or_none,
     RegexNotFoundError,
     sanitized_Request,
     strip_or_none,
@@ -23,7 +23,6 @@ from ..utils import (
     unescapeHTML,
     update_url_query,
     url_basename,
-    get_domain,
     xpath_text,
 )
 
@@ -45,7 +44,7 @@ class MTVServicesInfoExtractor(InfoExtractor):
         # Remove the templates, like &device={device}
         return re.sub(r'&[^=]*?={.*?}(?=(&|$))', '', url)
 
-    def _get_feed_url(self, uri, url=None):
+    def _get_feed_url(self, uri):
         return self._FEED_URL
 
     def _get_thumbnail_url(self, uri, itemdoc):
@@ -178,6 +177,22 @@ class MTVServicesInfoExtractor(InfoExtractor):
             raise ExtractorError('Could not find video title')
         title = title.strip()
 
+        series = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:franchise')
+        season = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:seasonN')
+        episode = find_xpath_attr(
+            itemdoc, './/{http://search.yahoo.com/mrss/}category',
+            'scheme', 'urn:mtvn:episodeN')
+        series = series.text if series is not None else None
+        season = season.text if season is not None else None
+        episode = episode.text if episode is not None else None
+        if season and episode:
+            # episode number includes season, so remove it
+            episode = re.sub(r'^%s' % season, '', episode)
+
         # This a short id that's used in the webpage urls
         mtvn_id = None
         mtvn_id_node = find_xpath_attr(itemdoc, './/{http://search.yahoo.com/mrss/}category',
@@ -203,6 +218,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             'description': description,
             'duration': float_or_none(content_el.attrib.get('duration')),
             'timestamp': timestamp,
+            'series': series,
+            'season_number': int_or_none(season),
+            'episode_number': int_or_none(episode),
         }
 
     def _get_feed_query(self, uri):
@@ -211,9 +229,9 @@ class MTVServicesInfoExtractor(InfoExtractor):
             data['lang'] = self._LANG
         return data
 
-    def _get_videos_info(self, uri, use_hls=True, url=None):
+    def _get_videos_info(self, uri, use_hls=True):
         video_id = self._id_from_uri(uri)
-        feed_url = self._get_feed_url(uri, url)
+        feed_url = self._get_feed_url(uri)
         info_url = update_url_query(feed_url, self._get_feed_query(uri))
         return self._get_videos_info_from_url(info_url, video_id, use_hls)
 
@@ -257,43 +275,11 @@ class MTVServicesInfoExtractor(InfoExtractor):
 
     @staticmethod
     def _extract_child_with_type(parent, t):
-        return next(c for c in parent['children'] if c.get('type') == t)
+        for c in parent['children']:
+            if c.get('type') == t:
+                return c
 
-    def _extract_new_triforce_mgid(self, webpage, url='', video_id=None):
-        if url == '':
-            return
-        domain = get_domain(url)
-        if domain is None:
-            raise ExtractorError(
-                '[%s] could not get domain' % self.IE_NAME,
-                expected=True)
-        url = url.replace("https://", "http://")
-        enc_url = compat_urlparse.quote(url, safe='')
-        _TRIFORCE_V8_TEMPLATE = 'https://%s/feeds/triforce/manifest/v8?url=%s'
-        triforce_manifest_url = _TRIFORCE_V8_TEMPLATE % (domain, enc_url)
-
-        manifest = self._download_json(triforce_manifest_url, video_id, fatal=False)
-        if manifest:
-            if manifest.get('manifest').get('type') == 'redirect':
-                self.to_screen('Found a redirect. Downloading manifest from new location')
-                new_loc = manifest.get('manifest').get('newLocation')
-                new_loc = new_loc.replace("https://", "http://")
-                enc_new_loc = compat_urlparse.quote(new_loc, safe='')
-                triforce_manifest_new_loc = _TRIFORCE_V8_TEMPLATE % (domain, enc_new_loc)
-                manifest = self._download_json(triforce_manifest_new_loc, video_id, fatal=False)
-
-        item_id = try_get(manifest, lambda x: x['manifest']['reporting']['itemId'], compat_str)
-        if not item_id:
-            self.to_screen('No id found!')
-            return
-
-        # 'episode' can be anything. 'content' is used often as well
-        _MGID_TEMPLATE = 'mgid:arc:episode:%s:%s'
-        mgid = _MGID_TEMPLATE % (domain, item_id)
-
-        return mgid
-
-    def _extract_mgid(self, webpage, url, title=None, data_zone=None):
+    def _extract_mgid(self, webpage):
         try:
             # the url can be http://media.mtvnservices.com/fb/{mgid}.swf
             # or http://media.mtvnservices.com/{mgid}
@@ -304,21 +290,6 @@ class MTVServicesInfoExtractor(InfoExtractor):
         except RegexNotFoundError:
             mgid = None
 
-        if not title:
-            title = url_basename(url)
-
-        try:
-            window_data = self._parse_json(self._search_regex(
-                r'(?s)window.__DATA__ = (?P<json>{.+});', webpage,
-                'JSON Window Data', default=None, fatal=False, group='json'), title, fatal=False)
-            main_container = None
-            for i in range(len(window_data['children'])):
-                if window_data['children'][i]['type'] == 'MainContainer':
-                    main_container = window_data['children'][i]
-            mgid = main_container['children'][0]['props']['media']['video']['config']['uri']
-        except (KeyError, IndexError, TypeError):
-            pass
-
         if mgid is None or ':' not in mgid:
             mgid = self._search_regex(
                 [r'data-mgid="(.*?)"', r'swfobject\.embedSWF\(".*?(mgid:.*?)"'],
@@ -331,16 +302,14 @@ class MTVServicesInfoExtractor(InfoExtractor):
                 r'embed/(mgid:.+?)["\'&?/]', sm4_embed, 'mgid', default=None)
 
         if not mgid:
-            mgid = self._extract_new_triforce_mgid(webpage, url)
-
-        if not mgid:
-            mgid = self._extract_triforce_mgid(webpage, data_zone)
+            mgid = self._extract_triforce_mgid(webpage)
 
         if not mgid:
             data = self._parse_json(self._search_regex(
                 r'__DATA__\s*=\s*({.+?});', webpage, 'data'), None)
             main_container = self._extract_child_with_type(data, 'MainContainer')
-            video_player = self._extract_child_with_type(main_container, 'VideoPlayer')
+            ab_testing = self._extract_child_with_type(main_container, 'ABTesting')
+            video_player = self._extract_child_with_type(ab_testing or main_container, 'VideoPlayer')
             mgid = video_player['props']['media']['video']['config']['uri']
 
         return mgid
@@ -348,8 +317,8 @@ class MTVServicesInfoExtractor(InfoExtractor):
     def _real_extract(self, url):
         title = url_basename(url)
         webpage = self._download_webpage(url, title)
-        mgid = self._extract_mgid(webpage, url, title=title)
-        videos_info = self._get_videos_info(mgid, url=url)
+        mgid = self._extract_mgid(webpage)
+        videos_info = self._get_videos_info(mgid)
         return videos_info
 
 
@@ -374,7 +343,7 @@ class MTVServicesEmbeddedIE(MTVServicesInfoExtractor):
     @staticmethod
     def _extract_url(webpage):
         mobj = re.search(
-            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media.mtvnservices.com/embed/.+?)\1', webpage)
+            r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//media\.mtvnservices\.com/embed/.+?)\1', webpage)
         if mobj:
             return mobj.group('url')
 
@@ -537,3 +506,152 @@ class MTVDEIE(MTVServicesInfoExtractor):
             'arcEp': 'mtv.de',
             'mgid': uri,
         }
+
+
+class MTVItaliaIE(MTVServicesInfoExtractor):
+    IE_NAME = 'mtv.it'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:episodi|video|musica)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        'url': 'http://www.mtv.it/episodi/24bqab/mario-una-serie-di-maccio-capatonda-cavoli-amario-episodio-completo-S1-E1',
+        'info_dict': {
+            'id': '0f0fc78e-45fc-4cce-8f24-971c25477530',
+            'ext': 'mp4',
+            'title': 'Cavoli amario (episodio completo)',
+            'description': 'md5:4962bccea8fed5b7c03b295ae1340660',
+            'series': 'Mario - Una Serie Di Maccio Capatonda',
+            'season_number': 1,
+            'episode_number': 1,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    _GEO_COUNTRIES = ['IT']
+    _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
+
+    def _get_feed_query(self, uri):
+        return {
+            'arcEp': 'mtv.it',
+            'mgid': uri,
+        }
+
+
+class MTVItaliaProgrammaIE(MTVItaliaIE):
+    IE_NAME = 'mtv.it:programma'
+    _VALID_URL = r'https?://(?:www\.)?mtv\.it/(?:programmi|playlist)/(?P<id>[0-9a-z]+)'
+    _TESTS = [{
+        # program page: general
+        'url': 'http://www.mtv.it/programmi/s2rppv/mario-una-serie-di-maccio-capatonda',
+        'info_dict': {
+            'id': 'a6f155bc-8220-4640-aa43-9b95f64ffa3d',
+            'title': 'Mario - Una Serie Di Maccio Capatonda',
+            'description': 'md5:72fbffe1f77ccf4e90757dd4e3216153',
+        },
+        'playlist_count': 2,
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # program page: specific season
+        'url': 'http://www.mtv.it/programmi/d9ncjf/mario-una-serie-di-maccio-capatonda-S2',
+        'info_dict': {
+            'id': '4deeb5d8-f272-490c-bde2-ff8d261c6dd1',
+            'title': 'Mario - Una Serie Di Maccio Capatonda - Stagione 2',
+        },
+        'playlist_count': 34,
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        # playlist page + redirect
+        'url': 'http://www.mtv.it/playlist/sexy-videos/ilctal',
+        'info_dict': {
+            'id': 'dee8f9ee-756d-493b-bf37-16d1d2783359',
+            'title': 'Sexy Videos',
+        },
+        'playlist_mincount': 145,
+        'params': {
+            'skip_download': True,
+        },
+    }]
+    _GEO_COUNTRIES = ['IT']
+    _FEED_URL = 'http://www.mtv.it/feeds/triforce/manifest/v8'
+
+    def _get_entries(self, title, url):
+        while True:
+            pg = self._search_regex(r'/(\d+)$', url, 'entries', '1')
+            entries = self._download_json(url, title, 'page %s' % pg)
+            url = try_get(
+                entries, lambda x: x['result']['nextPageURL'], compat_str)
+            entries = try_get(
+                entries, (
+                    lambda x: x['result']['data']['items'],
+                    lambda x: x['result']['data']['seasons']),
+                list)
+            for entry in entries or []:
+                if entry.get('canonicalURL'):
+                    yield self.url_result(entry['canonicalURL'])
+            if not url:
+                break
+
+    def _real_extract(self, url):
+        query = {'url': url}
+        info_url = update_url_query(self._FEED_URL, query)
+        video_id = self._match_id(url)
+        info = self._download_json(info_url, video_id).get('manifest')
+
+        redirect = try_get(
+            info, lambda x: x['newLocation']['url'], compat_str)
+        if redirect:
+            return self.url_result(redirect)
+
+        title = info.get('title')
+        video_id = try_get(
+            info, lambda x: x['reporting']['itemId'], compat_str)
+        parent_id = try_get(
+            info, lambda x: x['reporting']['parentId'], compat_str)
+
+        playlist_url = current_url = None
+        for z in (info.get('zones') or {}).values():
+            if z.get('moduleName') in ('INTL_M304', 'INTL_M209'):
+                info_url = z.get('feed')
+            if z.get('moduleName') in ('INTL_M308', 'INTL_M317'):
+                playlist_url = playlist_url or z.get('feed')
+            if z.get('moduleName') in ('INTL_M300',):
+                current_url = current_url or z.get('feed')
+
+        if not info_url:
+            raise ExtractorError('No info found')
+
+        if video_id == parent_id:
+            video_id = self._search_regex(
+                r'([^\/]+)/[^\/]+$', info_url, 'video_id')
+
+        info = self._download_json(info_url, video_id, 'Show infos')
+        info = try_get(info, lambda x: x['result']['data'], dict)
+        title = title or try_get(
+            info, (
+                lambda x: x['title'],
+                lambda x: x['headline']),
+            compat_str)
+        description = try_get(info, lambda x: x['content'], compat_str)
+
+        if current_url:
+            season = try_get(
+                self._download_json(playlist_url, video_id, 'Seasons info'),
+                lambda x: x['result']['data'], dict)
+            current = try_get(
+                season, lambda x: x['currentSeason'], compat_str)
+            seasons = try_get(
+                season, lambda x: x['seasons'], list) or []
+
+            if current in [s.get('eTitle') for s in seasons]:
+                playlist_url = current_url
+
+        title = re.sub(
+            r'[-|]\s*(?:mtv\s*italia|programma|playlist)',
+            '', title, flags=re.IGNORECASE).strip()
+
+        return self.playlist_result(
+            self._get_entries(title, playlist_url),
+            video_id, title, description)

yt_dlp/extractor/mxplayer.py

@@ -0,0 +1,127 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+    ExtractorError,
+    js_to_json,
+    qualities,
+    try_get,
+    url_or_none,
+    urljoin,
+)
+
+
+class MxplayerIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?mxplayer\.in/(?:show|movie)/(?:(?P<display_id>[-/a-z0-9]+)-)?(?P<id>[a-z0-9]+)'
+    _TESTS = [{
+        'url': 'https://www.mxplayer.in/movie/watch-knock-knock-hindi-dubbed-movie-online-b9fa28df3bfb8758874735bbd7d2655a?watch=true',
+        'info_dict': {
+            'id': 'b9fa28df3bfb8758874735bbd7d2655a',
+            'ext': 'mp4',
+            'title': 'Knock Knock (Hindi Dubbed)',
+            'description': 'md5:b195ba93ff1987309cfa58e2839d2a5b'
+        },
+        'params': {
+            'skip_download': True,
+            'format': 'bestvideo'
+        }
+    }, {
+        'url': 'https://www.mxplayer.in/show/watch-shaitaan/season-1/the-infamous-taxi-gang-of-meerut-online-45055d5bcff169ad48f2ad7552a83d6c',
+        'info_dict': {
+            'id': '45055d5bcff169ad48f2ad7552a83d6c',
+            'ext': 'm3u8',
+            'title': 'The infamous taxi gang of Meerut',
+            'description': 'md5:033a0a7e3fd147be4fb7e07a01a3dc28',
+            'season': 'Season 1',
+            'series': 'Shaitaan'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        'url': 'https://www.mxplayer.in/show/watch-aashram/chapter-1/duh-swapna-online-d445579792b0135598ba1bc9088a84cb',
+        'info_dict': {
+            'id': 'd445579792b0135598ba1bc9088a84cb',
+            'ext': 'mp4',
+            'title': 'Duh Swapna',
+            'description': 'md5:35ff39c4bdac403c53be1e16a04192d8',
+            'season': 'Chapter 1',
+            'series': 'Aashram'
+        },
+        'expected_warnings': ['Unknown MIME type application/mp4 in DASH manifest'],
+        'params': {
+            'skip_download': True,
+            'format': 'bestvideo'
+        }
+    }]
+
+    def _get_stream_urls(self, video_dict):
+        stream_provider_dict = try_get(
+            video_dict,
+            lambda x: x['stream'][x['stream']['provider']])
+        if not stream_provider_dict:
+            raise ExtractorError('No stream provider found', expected=True)
+
+        for stream_name, stream in stream_provider_dict.items():
+            if stream_name in ('hls', 'dash', 'hlsUrl', 'dashUrl'):
+                stream_type = stream_name.replace('Url', '')
+                if isinstance(stream, dict):
+                    for quality, stream_url in stream.items():
+                        if stream_url:
+                            yield stream_type, quality, stream_url
+                else:
+                    yield stream_type, 'base', stream
+
+    def _real_extract(self, url):
+        display_id, video_id = re.match(self._VALID_URL, url).groups()
+        webpage = self._download_webpage(url, video_id)
+
+        source = self._parse_json(
+            js_to_json(self._html_search_regex(
+                r'(?s)<script>window\.state\s*[:=]\s(\{.+\})\n(\w+).*(</script>).*',
+                webpage, 'WindowState')),
+            video_id)
+        if not source:
+            raise ExtractorError('Cannot find source', expected=True)
+
+        config_dict = source['config']
+        video_dict = source['entities'][video_id]
+
+        thumbnails = []
+        for i in video_dict.get('imageInfo') or []:
+            thumbnails.append({
+                'url': urljoin(config_dict['imageBaseUrl'], i['url']),
+                'width': i['width'],
+                'height': i['height'],
+            })
+
+        formats = []
+        get_quality = qualities(['main', 'base', 'high'])
+        for stream_type, quality, stream_url in self._get_stream_urls(video_dict):
+            format_url = url_or_none(urljoin(config_dict['videoCdnBaseUrl'], stream_url))
+            if not format_url:
+                continue
+            if stream_type == 'dash':
+                dash_formats = self._extract_mpd_formats(
+                    format_url, video_id, mpd_id='dash-%s' % quality, headers={'Referer': url})
+                for frmt in dash_formats:
+                    frmt['quality'] = get_quality(quality)
+                formats.extend(dash_formats)
+            elif stream_type == 'hls':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, fatal=False,
+                    m3u8_id='hls-%s' % quality, quality=get_quality(quality)))
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'display_id': display_id.replace('/', '-'),
+            'title': video_dict['title'] or self._og_search_title(webpage),
+            'formats': formats,
+            'description': video_dict.get('description'),
+            'season': try_get(video_dict, lambda x: x['container']['title']),
+            'series': try_get(video_dict, lambda x: x['container']['container']['title']),
+            'thumbnails': thumbnails,
+        }

yt_dlp/extractor/nbc.py

@@ -10,6 +10,7 @@ from .adobepass import AdobePassIE
 from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     int_or_none,
+    parse_age_limit,
     parse_duration,
     smuggle_url,
     try_get,
@@ -18,7 +19,7 @@ from ..utils import (
 )
 
 
-class NBCIE(AdobePassIE):
+class NBCIE(ThePlatformIE):
     _VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>n?\d+))'
 
     _TESTS = [
@@ -132,7 +133,9 @@ class NBCIE(AdobePassIE):
             'manifest': 'm3u',
         }
         video_id = video_data['mpxGuid']
-        title = video_data['secondaryTitle']
+        tp_path = 'NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id)
+        tpm = self._download_theplatform_metadata(tp_path, video_id)
+        title = tpm.get('title') or video_data.get('secondaryTitle')
         if video_data.get('locked'):
             resource = self._get_mvpd_resource(
                 video_data.get('resourceId') or 'nbcentertainment',
@@ -142,18 +145,40 @@ class NBCIE(AdobePassIE):
         theplatform_url = smuggle_url(update_url_query(
             'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
             query), {'force_smil_url': True})
+
+        # Empty string or 0 can be valid values for these. So the check must be `is None`
+        description = video_data.get('description')
+        if description is None:
+            description = tpm.get('description')
+        episode_number = int_or_none(video_data.get('episodeNumber'))
+        if episode_number is None:
+            episode_number = int_or_none(tpm.get('nbcu$airOrder'))
+        rating = video_data.get('rating')
+        if rating is None:
+            try_get(tpm, lambda x: x['ratings'][0]['rating'])
+        season_number = int_or_none(video_data.get('seasonNumber'))
+        if season_number is None:
+            season_number = int_or_none(tpm.get('nbcu$seasonNumber'))
+        series = video_data.get('seriesShortTitle')
+        if series is None:
+            series = tpm.get('nbcu$seriesShortTitle')
+        tags = video_data.get('keywords')
+        if tags is None or len(tags) == 0:
+            tags = tpm.get('keywords')
+
         return {
             '_type': 'url_transparent',
+            'age_limit': parse_age_limit(rating),
+            'description': description,
+            'episode': title,
+            'episode_number': episode_number,
             'id': video_id,
+            'ie_key': 'ThePlatform',
+            'season_number': season_number,
+            'series': series,
+            'tags': tags,
             'title': title,
             'url': theplatform_url,
-            'description': video_data.get('description'),
-            'tags': video_data.get('keywords'),
-            'season_number': int_or_none(video_data.get('seasonNumber')),
-            'episode_number': int_or_none(video_data.get('episodeNumber')),
-            'episode': title,
-            'series': video_data.get('seriesShortTitle'),
-            'ie_key': 'ThePlatform',
         }
 
 

yt_dlp/extractor/nebula.py

@@ -0,0 +1,197 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    ExtractorError,
+    parse_iso8601,
+    try_get,
+    urljoin,
+)
+
+
+class NebulaIE(InfoExtractor):
+
+    _VALID_URL = r'https?://(?:www\.)?watchnebula\.com/videos/(?P<id>[-\w]+)'
+    _TESTS = [
+        {
+            'url': 'https://watchnebula.com/videos/that-time-disney-remade-beauty-and-the-beast',
+            'md5': 'fe79c4df8b3aa2fea98a93d027465c7e',
+            'info_dict': {
+                'id': '5c271b40b13fd613090034fd',
+                'ext': 'mp4',
+                'title': 'That Time Disney Remade Beauty and the Beast',
+                'description': 'Note: this video was originally posted on YouTube with the sponsor read included. We weren’t able to remove it without reducing video quality, so it’s presented here in its original context.',
+                'upload_date': '20180731',
+                'timestamp': 1533009600,
+                'channel': 'Lindsay Ellis',
+                'uploader': 'Lindsay Ellis',
+            },
+            'params': {
+                'usenetrc': True,
+            },
+            'skip': 'All Nebula content requires authentication',
+        },
+        {
+            'url': 'https://watchnebula.com/videos/the-logistics-of-d-day-landing-craft-how-the-allies-got-ashore',
+            'md5': '6d4edd14ce65720fa63aba5c583fb328',
+            'info_dict': {
+                'id': '5e7e78171aaf320001fbd6be',
+                'ext': 'mp4',
+                'title': 'Landing Craft - How The Allies Got Ashore',
+                'description': r're:^In this episode we explore the unsung heroes of D-Day, the landing craft.',
+                'upload_date': '20200327',
+                'timestamp': 1585348140,
+                'channel': 'The Logistics of D-Day',
+                'uploader': 'The Logistics of D-Day',
+            },
+            'params': {
+                'usenetrc': True,
+            },
+            'skip': 'All Nebula content requires authentication',
+        },
+        {
+            'url': 'https://watchnebula.com/videos/money-episode-1-the-draw',
+            'md5': '8c7d272910eea320f6f8e6d3084eecf5',
+            'info_dict': {
+                'id': '5e779ebdd157bc0001d1c75a',
+                'ext': 'mp4',
+                'title': 'Episode 1: The Draw',
+                'description': r'contains:There’s free money on offer… if the players can all work together.',
+                'upload_date': '20200323',
+                'timestamp': 1584980400,
+                'channel': 'Tom Scott Presents: Money',
+                'uploader': 'Tom Scott Presents: Money',
+            },
+            'params': {
+                'usenetrc': True,
+            },
+            'skip': 'All Nebula content requires authentication',
+        },
+    ]
+    _NETRC_MACHINE = 'watchnebula'
+
+    def _retrieve_nebula_auth(self, video_id):
+        """
+        Log in to Nebula, and returns a Nebula API token
+        """
+
+        username, password = self._get_login_info()
+        if not (username and password):
+            self.raise_login_required()
+
+        self.report_login()
+        data = json.dumps({'email': username, 'password': password}).encode('utf8')
+        response = self._download_json(
+            'https://api.watchnebula.com/api/v1/auth/login/',
+            data=data, fatal=False, video_id=video_id,
+            headers={
+                'content-type': 'application/json',
+                # Submitting the 'sessionid' cookie always causes a 403 on auth endpoint
+                'cookie': ''
+            },
+            note='Authenticating to Nebula with supplied credentials',
+            errnote='Authentication failed or rejected')
+        if not response or not response.get('key'):
+            self.raise_login_required()
+        return response['key']
+
+    def _retrieve_zype_api_key(self, page_url, display_id):
+        """
+        Retrieves the Zype API key
+        """
+
+        # Find the js that has the API key from the webpage and download it
+        webpage = self._download_webpage(page_url, video_id=display_id)
+        main_script_relpath = self._search_regex(
+            r'<script[^>]*src="(?P<script_relpath>[^"]*main.[0-9a-f]*.chunk.js)"[^>]*>', webpage,
+            group='script_relpath', name='script relative path', fatal=True)
+        main_script_abspath = urljoin(page_url, main_script_relpath)
+        main_script = self._download_webpage(main_script_abspath, video_id=display_id,
+                                             note='Retrieving Zype API key')
+
+        api_key = self._search_regex(
+            r'REACT_APP_ZYPE_API_KEY\s*:\s*"(?P<api_key>[\w-]*)"', main_script,
+            group='api_key', name='API key', fatal=True)
+
+        return api_key
+
+    def _call_zype_api(self, path, params, video_id, api_key, note):
+        """
+        A helper for making calls to the Zype API.
+        """
+        query = {'api_key': api_key, 'per_page': 1}
+        query.update(params)
+        return self._download_json('https://api.zype.com' + path, video_id, query=query, note=note)
+
+    def _call_nebula_api(self, path, video_id, access_token, note):
+        """
+        A helper for making calls to the Nebula API.
+        """
+        return self._download_json('https://api.watchnebula.com/api/v1' + path, video_id, headers={
+            'Authorization': 'Token {access_token}'.format(access_token=access_token)
+        }, note=note)
+
+    def _fetch_zype_access_token(self, video_id, nebula_token):
+        user_object = self._call_nebula_api('/auth/user/', video_id, nebula_token, note='Retrieving Zype access token')
+        access_token = try_get(user_object, lambda x: x['zype_auth_info']['access_token'], compat_str)
+        if not access_token:
+            if try_get(user_object, lambda x: x['is_subscribed'], bool):
+                # TODO: Reimplement the same Zype token polling the Nebula frontend implements
+                # see https://github.com/ytdl-org/youtube-dl/pull/24805#issuecomment-749231532
+                raise ExtractorError(
+                    'Unable to extract Zype access token from Nebula API authentication endpoint. '
+                    'Open an arbitrary video in a browser with this account to generate a token',
+                    expected=True)
+            raise ExtractorError('Unable to extract Zype access token from Nebula API authentication endpoint')
+        return access_token
+
+    def _extract_channel_title(self, video_meta):
+        # TODO: Implement the API calls giving us the channel list,
+        # so that we can do the title lookup and then figure out the channel URL
+        categories = video_meta.get('categories', []) if video_meta else []
+        # the channel name is the value of the first category
+        for category in categories:
+            if category.get('value'):
+                return category['value'][0]
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        nebula_token = self._retrieve_nebula_auth(display_id)
+        api_key = self._retrieve_zype_api_key(url, display_id)
+
+        response = self._call_zype_api('/videos', {'friendly_title': display_id},
+                                       display_id, api_key, note='Retrieving metadata from Zype')
+        if len(response.get('response') or []) != 1:
+            raise ExtractorError('Unable to find video on Zype API')
+        video_meta = response['response'][0]
+
+        video_id = video_meta['_id']
+        zype_access_token = self._fetch_zype_access_token(display_id, nebula_token=nebula_token)
+
+        channel_title = self._extract_channel_title(video_meta)
+
+        return {
+            'id': video_id,
+            'display_id': display_id,
+            '_type': 'url_transparent',
+            'ie_key': 'Zype',
+            'url': 'https://player.zype.com/embed/%s.html?access_token=%s' % (video_id, zype_access_token),
+            'title': video_meta.get('title'),
+            'description': video_meta.get('description'),
+            'timestamp': parse_iso8601(video_meta.get('published_at')),
+            'thumbnails': [
+                {
+                    'id': tn.get('name'),  # this appears to be null
+                    'url': tn['url'],
+                    'width': tn.get('width'),
+                    'height': tn.get('height'),
+                } for tn in video_meta.get('thumbnails', [])],
+            'duration': video_meta.get('duration'),
+            'channel': channel_title,
+            'uploader': channel_title,  # we chose uploader = channel name
+            # TODO: uploader_url, channel_id, channel_url
+        }

yt_dlp/extractor/nfhsnetwork.py

@@ -0,0 +1,144 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+from ..utils import (
+    try_get,
+    unified_strdate,
+    unified_timestamp
+)
+
+
+class NFHSNetworkIE(InfoExtractor):
+    IE_NAME = 'NFHSNetwork'
+    _VALID_URL = r'https?://(?:www\.)?nfhsnetwork\.com/events/[\w-]+/(?P<id>(?:gam|evt|dd|)?[\w\d]{0,10})'
+    _TESTS = [{
+        # Auto-generated two-team sport (pixellot)
+        'url': 'https://www.nfhsnetwork.com/events/rockford-high-school-rockford-mi/gamcf7e54cfbc',
+        'info_dict': {
+            'id': 'gamcf7e54cfbc',
+            'ext': 'mp4',
+            'title': 'Rockford vs Spring Lake - Girls Varsity Lacrosse 03/27/2021',
+            'uploader': 'MHSAA - Michigan: Rockford High School, Rockford, MI',
+            'uploader_id': 'cd2622cf76',
+            'uploader_url': 'https://www.nfhsnetwork.com/schools/rockford-high-school-rockford-mi',
+            'location': 'Rockford, Michigan',
+            'timestamp': 1616859000,
+            'upload_date': '20210327'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        # Non-sport activity with description
+        'url': 'https://www.nfhsnetwork.com/events/limon-high-school-limon-co/evt4a30e3726c',
+        'info_dict': {
+            'id': 'evt4a30e3726c',
+            'ext': 'mp4',
+            'title': 'Drama Performance Limon High School vs. Limon High School - 12/13/2020',
+            'description': 'Join the broadcast of the Limon High School Musical Performance at 2 PM.',
+            'uploader': 'CHSAA: Limon High School, Limon, CO',
+            'uploader_id': '7d2d121332',
+            'uploader_url': 'https://www.nfhsnetwork.com/schools/limon-high-school-limon-co',
+            'location': 'Limon, Colorado',
+            'timestamp': 1607893200,
+            'upload_date': '20201213'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        # Postseason game
+        'url': 'https://www.nfhsnetwork.com/events/nfhs-network-special-events/dd8de71d45',
+        'info_dict': {
+            'id': 'dd8de71d45',
+            'ext': 'mp4',
+            'title': '2015 UA Holiday Classic Tournament: National Division  - 12/26/2015',
+            'uploader': 'SoCal Sports Productions',
+            'uploader_id': '063dba0150',
+            'uploader_url': 'https://www.nfhsnetwork.com/affiliates/socal-sports-productions',
+            'location': 'San Diego, California',
+            'timestamp': 1451187000,
+            'upload_date': '20151226'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }, {
+        # Video with no broadcasts object
+        'url': 'https://www.nfhsnetwork.com/events/wiaa-wi/9aa2f92f82',
+        'info_dict': {
+            'id': '9aa2f92f82',
+            'ext': 'mp4',
+            'title': 'Competitive Equity  - 01/21/2015',
+            'description': 'Committee members discuss points of their research regarding a competitive equity plan',
+            'uploader': 'WIAA - Wisconsin: Wisconsin Interscholastic Athletic Association',
+            'uploader_id': 'a49f7d1002',
+            'uploader_url': 'https://www.nfhsnetwork.com/associations/wiaa-wi',
+            'location': 'Stevens Point, Wisconsin',
+            'timestamp': 1421856000,
+            'upload_date': '20150121'
+        },
+        'params': {
+            # m3u8 download
+            'skip_download': True,
+        }
+    }
+    ]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        data = self._download_json(
+            'https://cfunity.nfhsnetwork.com/v2/game_or_event/' + video_id,
+            video_id)
+        publisher = data.get('publishers')[0]  # always exists
+        broadcast = (publisher.get('broadcasts') or publisher.get('vods'))[0]  # some (older) videos don't have a broadcasts object
+        uploader = publisher.get('formatted_name') or publisher.get('name')
+        uploaderID = publisher.get('publisher_key')
+        pubType = publisher.get('type')
+        uploaderPrefix = (
+            "schools" if pubType == "school"
+            else "associations" if "association" in pubType
+            else "affiliates" if (pubType == "publisher" or pubType == "affiliate")
+            else "schools")
+        uploaderPage = 'https://www.nfhsnetwork.com/%s/%s' % (uploaderPrefix, publisher.get('slug'))
+        location = '%s, %s' % (data.get('city'), data.get('state_name'))
+        description = broadcast.get('description')
+        isLive = broadcast.get('on_air') or broadcast.get('status') == 'on_air' or False
+
+        timestamp = unified_timestamp(data.get('local_start_time'))
+        upload_date = unified_strdate(data.get('local_start_time'))
+
+        title = (
+            self._og_search_title(webpage)
+            or self._html_search_regex(r'<h1 class="sr-hidden">(.*?)</h1>', webpage, 'title'))
+        title = title.split('|')[0].strip()
+
+        video_type = 'broadcasts' if isLive else 'vods'
+        key = broadcast.get('key') if isLive else try_get(publisher, lambda x: x['vods'][0]['key'])
+        m3u8_url = self._download_json(
+            'https://cfunity.nfhsnetwork.com/v2/%s/%s/url' % (video_type, key),
+            video_id).get('video_url')
+
+        formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', live=isLive)
+        self._sort_formats(formats, ['res', 'tbr'])
+
+        return {
+            'id': video_id,
+            'title': title,
+            'formats': formats,
+            'description': description,
+            'timestamp': timestamp,
+            'uploader': uploader,
+            'uploader_id': uploaderID,
+            'uploader_url': uploaderPage,
+            'location': location,
+            'upload_date': upload_date,
+            'is_live': isLive
+        }

yt_dlp/extractor/nick.py

@@ -8,59 +8,66 @@ from ..utils import update_url_query
 
 
 class NickIE(MTVServicesInfoExtractor):
-    # None of videos on the website are still alive?
     IE_NAME = 'nick.com'
-    _VALID_URL = r'https?://(?P<domain>(?:(?:www|beta)\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?:videos/clip|[^/]+/videos)/(?P<id>[^/?#.]+)'
+    _VALID_URL = r'https?://(?P<domain>(?:www\.)?nick(?:jr)?\.com)/(?:[^/]+/)?(?P<type>videos/clip|[^/]+/videos|episodes/[^/]+)/(?P<id>[^/?#.]+)'
     _FEED_URL = 'http://udat.mtvnservices.com/service1/dispatch.htm'
     _GEO_COUNTRIES = ['US']
     _TESTS = [{
-        'url': 'http://www.nick.com/videos/clip/alvinnn-and-the-chipmunks-112-full-episode.html',
+        'url': 'https://www.nick.com/episodes/sq47rw/spongebob-squarepants-a-place-for-pets-lockdown-for-love-season-13-ep-1',
+        'info_dict': {
+            'description': 'md5:0650a9eb88955609d5c1d1c79292e234',
+            'title': 'A Place for Pets/Lockdown for Love',
+        },
         'playlist': [
             {
-                'md5': '6e5adc1e28253bbb1b28ab05403dd4d4',
+                'md5': 'cb8a2afeafb7ae154aca5a64815ec9d6',
                 'info_dict': {
-                    'id': 'be6a17b0-412d-11e5-8ff7-0026b9414f30',
+                    'id': '85ee8177-d6ce-48f8-9eee-a65364f8a6df',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S1',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S1',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
 
                 }
             },
             {
-                'md5': 'd7be441fc53a1d4882fa9508a1e5b3ce',
+                'md5': '839a04f49900a1fcbf517020d94e0737',
                 'info_dict': {
-                    'id': 'be6b8f96-412d-11e5-8ff7-0026b9414f30',
+                    'id': '2e2a9960-8fd4-411d-868b-28eb1beb7fae',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S2',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S2',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
 
                 }
             },
             {
-                'md5': 'efffe1728a234b2b0d2f2b343dd1946f',
+                'md5': 'f1145699f199770e2919ee8646955d46',
                 'info_dict': {
-                    'id': 'be6cf7e6-412d-11e5-8ff7-0026b9414f30',
+                    'id': 'dc91c304-6876-40f7-84a6-7aece7baa9d0',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S3',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S3',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
+
                 }
             },
             {
-                'md5': '1ec6690733ab9f41709e274a1d5c7556',
+                'md5': 'd463116875aee2585ee58de3b12caebd',
                 'info_dict': {
-                    'id': 'be6e3354-412d-11e5-8ff7-0026b9414f30',
+                    'id': '5d929486-cf4c-42a1-889a-6e0d183a101a',
                     'ext': 'mp4',
-                    'title': 'ALVINNN!!! and The Chipmunks: "Mojo Missing/Who\'s The Animal" S4',
-                    'description': 'Alvin is convinced his mojo was in a cap he gave to a fan, and must find a way to get his hat back before the Chipmunks’ big concert.\nDuring a costume visit to the zoo, Alvin finds himself mistaken for the real Tasmanian devil.',
+                    'title': 'SpongeBob SquarePants: "A Place for Pets/Lockdown for Love" S4',
+                    'description': 'A Place for Pets/Lockdown for Love: When customers bring pets into the Krusty Krab, Mr. Krabs realizes pets are more profitable than owners. Plankton ruins another date with Karen, so she puts the Chum Bucket on lockdown until he proves his affection.',
+
                 }
             },
         ],
     }, {
-        'url': 'http://www.nickjr.com/paw-patrol/videos/pups-save-a-goldrush-s3-ep302-full-episode/',
-        'only_matching': True,
-    }, {
-        'url': 'http://beta.nick.com/nicky-ricky-dicky-and-dawn/videos/nicky-ricky-dicky-dawn-301-full-episode/',
-        'only_matching': True,
+        'url': 'http://www.nickjr.com/blues-clues-and-you/videos/blues-clues-and-you-original-209-imagination-station/',
+        'info_dict': {
+            'id': '31631529-2fc5-430b-b2ef-6a74b4609abd',
+            'ext': 'mp4',
+            'description': 'md5:9d65a66df38e02254852794b2809d1cf',
+            'title': 'Blue\'s Imagination Station',
+        },
     }]
 
     def _get_feed_query(self, uri):
@@ -69,8 +76,14 @@ class NickIE(MTVServicesInfoExtractor):
             'mgid': uri,
         }
 
+    def _extract_mgid(self, webpage):
+        mgid = self._search_regex(r'"media":{"video":{"config":{"uri":"(mgid:.*?)"', webpage, 'mgid', default=None)
+        return mgid
+
     def _real_extract(self, url):
-        domain, display_id = re.match(self._VALID_URL, url).groups()
+        domain, video_type, display_id = re.match(self._VALID_URL, url).groups()
+        if video_type.startswith("episodes"):
+            return super()._real_extract(url)
         video_data = self._download_json(
             'http://%s/data/video.endLevel.json' % domain,
             display_id, query={

yt_dlp/extractor/niconico.py

@@ -8,6 +8,7 @@ import datetime
 from .common import InfoExtractor
 from ..postprocessor.ffmpeg import FFmpegPostProcessor
 from ..compat import (
+    compat_str,
     compat_parse_qs,
     compat_urllib_parse_urlparse,
 )
@@ -20,6 +21,7 @@ from ..utils import (
     parse_duration,
     parse_iso8601,
     PostProcessingError,
+    str_or_none,
     remove_start,
     try_get,
     unified_timestamp,
@@ -34,7 +36,7 @@ class NiconicoIE(InfoExtractor):
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/watch/sm22312215',
-        'md5': 'd1a75c0823e2f629128c43e1212760f9',
+        'md5': 'a5bad06f1347452102953f323c69da34s',
         'info_dict': {
             'id': 'sm22312215',
             'ext': 'mp4',
@@ -203,7 +205,7 @@ class NiconicoIE(InfoExtractor):
             'data-api-data="([^"]+)"', webpage,
             'API data', default='{}'), video_id)
 
-        session_api_data = try_get(api_data, lambda x: x['video']['dmcInfo']['session_api'])
+        session_api_data = try_get(api_data, lambda x: x['media']['delivery']['movie']['session'])
         session_api_endpoint = try_get(session_api_data, lambda x: x['urls'][0])
 
         # ping
@@ -220,7 +222,7 @@ class NiconicoIE(InfoExtractor):
         yesno = lambda x: 'yes' if x else 'no'
 
         # m3u8 (encryption)
-        if 'encryption' in try_get(api_data, lambda x: x['video']['dmcInfo']) or {}:
+        if 'encryption' in (try_get(api_data, lambda x: x['media']['delivery']['movie']) or {}):
             protocol = 'm3u8'
             session_api_http_parameters = {
                 'parameters': {
@@ -244,8 +246,8 @@ class NiconicoIE(InfoExtractor):
             session_api_http_parameters = {
                 'parameters': {
                     'http_output_download_parameters': {
-                        'use_ssl': yesno(session_api_endpoint['is_ssl']),
-                        'use_well_known_port': yesno(session_api_endpoint['is_well_known_port']),
+                        'use_ssl': yesno(session_api_endpoint['isSsl']),
+                        'use_well_known_port': yesno(session_api_endpoint['isWellKnownPort']),
                     }
                 }
             }
@@ -258,15 +260,15 @@ class NiconicoIE(InfoExtractor):
             data=json.dumps({
                 'session': {
                     'client_info': {
-                        'player_id': session_api_data.get('player_id'),
+                        'player_id': session_api_data.get('playerId'),
                     },
                     'content_auth': {
-                        'auth_type': try_get(session_api_data, lambda x: x['auth_types'][session_api_data['protocols'][0]]),
-                        'content_key_timeout': session_api_data.get('content_key_timeout'),
+                        'auth_type': try_get(session_api_data, lambda x: x['authTypes'][session_api_data['protocols'][0]]),
+                        'content_key_timeout': session_api_data.get('contentKeyTimeout'),
                         'service_id': 'nicovideo',
-                        'service_user_id': session_api_data.get('service_user_id')
+                        'service_user_id': session_api_data.get('serviceUserId')
                     },
-                    'content_id': session_api_data.get('content_id'),
+                    'content_id': session_api_data.get('contentId'),
                     'content_src_id_sets': [{
                         'content_src_ids': [{
                             'src_id_to_mux': {
@@ -279,7 +281,7 @@ class NiconicoIE(InfoExtractor):
                     'content_uri': '',
                     'keep_method': {
                         'heartbeat': {
-                            'lifetime': session_api_data.get('heartbeat_lifetime')
+                            'lifetime': session_api_data.get('heartbeatLifetime')
                         }
                     },
                     'priority': session_api_data.get('priority'),
@@ -289,7 +291,7 @@ class NiconicoIE(InfoExtractor):
                             'http_parameters': session_api_http_parameters
                         }
                     },
-                    'recipe_id': session_api_data.get('recipe_id'),
+                    'recipe_id': session_api_data.get('recipeId'),
                     'session_operation_auth': {
                         'session_operation_auth_by_signature': {
                             'signature': session_api_data.get('signature'),
@@ -308,7 +310,7 @@ class NiconicoIE(InfoExtractor):
             'url': session_api_endpoint['url'] + '/' + session_response['data']['session']['id'] + '?_format=json&_method=PUT',
             'data': json.dumps(session_response['data']),
             # interval, convert milliseconds to seconds, then halve to make a buffer.
-            'interval': float_or_none(session_api_data.get('heartbeat_lifetime'), scale=2000),
+            'interval': float_or_none(session_api_data.get('heartbeatLifetime'), scale=2000),
         }
 
         return info_dict, heartbeat_info_dict
@@ -327,15 +329,17 @@ class NiconicoIE(InfoExtractor):
         format_id = '-'.join(map(lambda s: remove_start(s['id'], 'archive_'), [video_quality, audio_quality]))
         vdict = parse_format_id(video_quality['id'])
         adict = parse_format_id(audio_quality['id'])
-        resolution = video_quality.get('resolution', {'height': vdict.get('res')})
+        resolution = try_get(video_quality, lambda x: x['metadata']['resolution'], dict) or {'height': vdict.get('res')}
+        vbr = try_get(video_quality, lambda x: x['metadata']['bitrate'], float)
 
         return {
             'url': '%s:%s/%s/%s' % (protocol, video_id, video_quality['id'], audio_quality['id']),
             'format_id': format_id,
+            'format_note': 'DMC %s' % try_get(video_quality, lambda x: x['metadata']['label'], compat_str),
             'ext': 'mp4',  # Session API are used in HTML5, which always serves mp4
             'vcodec': vdict.get('codec'),
             'acodec': adict.get('codec'),
-            'vbr': float_or_none(video_quality.get('bitrate'), 1000) or float_or_none(vdict.get('br')),
+            'vbr': float_or_none(vbr, 1000) or float_or_none(vdict.get('br')),
             'abr': float_or_none(audio_quality.get('bitrate'), 1000) or float_or_none(adict.get('br')),
             'height': int_or_none(resolution.get('height', vdict.get('res'))),
             'width': int_or_none(resolution.get('width')),
@@ -394,92 +398,93 @@ class NiconicoIE(InfoExtractor):
         formats = []
 
         # Get HTML5 videos info
-        try:
-            dmc_info = api_data['video']['dmcInfo']
-        except KeyError:
-            raise ExtractorError('The video can\'t downloaded.',
-                                 expected=True)
+        quality_info = try_get(api_data, lambda x: x['media']['delivery']['movie'])
+        if not quality_info:
+            raise ExtractorError('The video can\'t downloaded.', expected=True)
 
-        quality_info = dmc_info.get('quality')
         for audio_quality in quality_info.get('audios') or {}:
             for video_quality in quality_info.get('videos') or {}:
-                if not audio_quality.get('available') or not video_quality.get('available'):
+                if not audio_quality.get('isAvailable') or not video_quality.get('isAvailable'):
                     continue
                 formats.append(self._extract_format_for_quality(
                     api_data, video_id, audio_quality, video_quality))
 
         # Get flv/swf info
+        timestamp = None
         video_real_url = try_get(api_data, lambda x: x['video']['smileInfo']['url'])
-        is_economy = video_real_url.endswith('low')
+        if not video_real_url:
+            self.report_warning('Unable to obtain smile video information')
+        else:
+            is_economy = video_real_url.endswith('low')
 
-        if is_economy:
-            self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
+            if is_economy:
+                self.report_warning('Site is currently in economy mode! You will only have access to lower quality streams')
 
-        # Invoking ffprobe to determine resolution
-        pp = FFmpegPostProcessor(self._downloader)
-        cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
+            # Invoking ffprobe to determine resolution
+            pp = FFmpegPostProcessor(self._downloader)
+            cookies = self._get_cookies('https://nicovideo.jp').output(header='', sep='; path=/; domain=nicovideo.jp;\n')
 
-        self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
+            self.to_screen('%s: %s' % (video_id, 'Checking smile format with ffprobe'))
 
-        try:
-            metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
-        except PostProcessingError as err:
-            raise ExtractorError(err.msg, expected=True)
+            try:
+                metadata = pp.get_metadata_object(video_real_url, ['-cookies', cookies])
+            except PostProcessingError as err:
+                raise ExtractorError(err.msg, expected=True)
 
-        v_stream = a_stream = {}
+            v_stream = a_stream = {}
 
-        # Some complex swf files doesn't have video stream (e.g. nm4809023)
-        for stream in metadata['streams']:
-            if stream['codec_type'] == 'video':
-                v_stream = stream
-            elif stream['codec_type'] == 'audio':
-                a_stream = stream
+            # Some complex swf files doesn't have video stream (e.g. nm4809023)
+            for stream in metadata['streams']:
+                if stream['codec_type'] == 'video':
+                    v_stream = stream
+                elif stream['codec_type'] == 'audio':
+                    a_stream = stream
 
-        # Community restricted videos seem to have issues with the thumb API not returning anything at all
-        filesize = int(
-            (get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
-            or metadata['format']['size']
-        )
-        extension = (
-            get_video_info_xml('movie_type')
-            or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
-        )
+            # Community restricted videos seem to have issues with the thumb API not returning anything at all
+            filesize = int(
+                (get_video_info_xml('size_high') if not is_economy else get_video_info_xml('size_low'))
+                or metadata['format']['size']
+            )
+            extension = (
+                get_video_info_xml('movie_type')
+                or 'mp4' if 'mp4' in metadata['format']['format_name'] else metadata['format']['format_name']
+            )
 
-        # 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
-        timestamp = (
-            parse_iso8601(get_video_info_web('first_retrieve'))
-            or unified_timestamp(get_video_info_web('postedDateTime'))
-        )
-        metadata_timestamp = (
-            parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
-            or timestamp if extension != 'mp4' else 0
-        )
+            # 'creation_time' tag on video stream of re-encoded SMILEVIDEO mp4 files are '1970-01-01T00:00:00.000000Z'.
+            timestamp = (
+                parse_iso8601(get_video_info_web('first_retrieve'))
+                or unified_timestamp(get_video_info_web('postedDateTime'))
+            )
+            metadata_timestamp = (
+                parse_iso8601(try_get(v_stream, lambda x: x['tags']['creation_time']))
+                or timestamp if extension != 'mp4' else 0
+            )
 
-        # According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
-        smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
+            # According to compconf, smile videos from pre-2017 are always better quality than their DMC counterparts
+            smile_threshold_timestamp = parse_iso8601('2016-12-08T00:00:00+09:00')
 
-        is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
+            is_source = timestamp < smile_threshold_timestamp or metadata_timestamp > 0
 
-        # If movie file size is unstable, old server movie is not source movie.
-        if filesize > 1:
-            formats.append({
-                'url': video_real_url,
-                'format_id': 'smile' if not is_economy else 'smile_low',
-                'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
-                'ext': extension,
-                'container': extension,
-                'vcodec': v_stream.get('codec_name'),
-                'acodec': a_stream.get('codec_name'),
-                # Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
-                'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
-                'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
-                'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
-                'height': int_or_none(v_stream.get('height')),
-                'width': int_or_none(v_stream.get('width')),
-                'source_preference': 5 if not is_economy else -2,
-                'quality': 5 if is_source and not is_economy else None,
-                'filesize': filesize
-            })
+            # If movie file size is unstable, old server movie is not source movie.
+            if filesize > 1:
+                formats.append({
+                    'url': video_real_url,
+                    'format_id': 'smile' if not is_economy else 'smile_low',
+                    'format_note': 'SMILEVIDEO source' if not is_economy else 'SMILEVIDEO low quality',
+                    'ext': extension,
+                    'container': extension,
+                    'vcodec': v_stream.get('codec_name'),
+                    'acodec': a_stream.get('codec_name'),
+                    # Some complex swf files doesn't have total bit rate metadata (e.g. nm6049209)
+                    'tbr': int_or_none(metadata['format'].get('bit_rate'), scale=1000),
+                    'vbr': int_or_none(v_stream.get('bit_rate'), scale=1000),
+                    'abr': int_or_none(a_stream.get('bit_rate'), scale=1000),
+                    'height': int_or_none(v_stream.get('height')),
+                    'width': int_or_none(v_stream.get('width')),
+                    'source_preference': 5 if not is_economy else -2,
+                    'quality': 5 if is_source and not is_economy else None,
+                    'filesize': filesize
+                })
 
         if len(formats) == 0:
             raise ExtractorError('Unable to find video info.')
@@ -487,13 +492,12 @@ class NiconicoIE(InfoExtractor):
         self._sort_formats(formats)
 
         # Start extracting information
-        title = get_video_info_web('originalTitle')
-        if not title:
-            title = self._og_search_title(webpage, default=None)
-        if not title:
-            title = self._html_search_regex(
+        title = (
+            get_video_info_web(['originalTitle', 'title'])
+            or self._og_search_title(webpage, default=None)
+            or self._html_search_regex(
                 r'<span[^>]+class="videoHeaderTitle"[^>]*>([^<]+)</span>',
-                webpage, 'video title')
+                webpage, 'video title'))
 
         watch_api_data_string = self._html_search_regex(
             r'<div[^>]+id="watchAPIDataContainer"[^>]+>([^<]+)</div>',
@@ -517,6 +521,7 @@ class NiconicoIE(InfoExtractor):
             timestamp = parse_iso8601(
                 video_detail['postedAt'].replace('/', '-'),
                 delimiter=' ', timezone=datetime.timedelta(hours=9))
+        timestamp = timestamp or try_get(api_data, lambda x: parse_iso8601(x['video']['registeredAt']))
 
         view_count = int_or_none(get_video_info_web(['view_counter', 'viewCount']))
         if not view_count:
@@ -525,11 +530,16 @@ class NiconicoIE(InfoExtractor):
                 webpage, 'view count', default=None)
             if match:
                 view_count = int_or_none(match.replace(',', ''))
-        view_count = view_count or video_detail.get('viewCount')
+        view_count = (
+            view_count
+            or video_detail.get('viewCount')
+            or try_get(api_data, lambda x: x['video']['count']['view']))
+
+        comment_count = (
+            int_or_none(get_video_info_web('comment_num'))
+            or video_detail.get('commentCount')
+            or try_get(api_data, lambda x: x['video']['count']['comment']))
 
-        comment_count = (int_or_none(get_video_info_web('comment_num'))
-                         or video_detail.get('commentCount')
-                         or try_get(api_data, lambda x: x['thread']['commentCount']))
         if not comment_count:
             match = self._html_search_regex(
                 r'>Comments: <strong[^>]*>([^<]+)</strong>',
@@ -559,7 +569,7 @@ class NiconicoIE(InfoExtractor):
         # Note: cannot use api_data.get('owner', {}) because owner may be set to "null"
         # in the JSON, which will cause None to be returned instead of {}.
         owner = try_get(api_data, lambda x: x.get('owner'), dict) or {}
-        uploader_id = (
+        uploader_id = str_or_none(
             get_video_info_web(['ch_id', 'user_id'])
             or owner.get('id')
             or channel_id
@@ -589,7 +599,7 @@ class NiconicoIE(InfoExtractor):
 
 
 class NiconicoPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/)?mylist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/(?:user/\d+/|my/)?mylist/(?P<id>\d+)'
 
     _TESTS = [{
         'url': 'http://www.nicovideo.jp/mylist/27411728',
@@ -647,3 +657,40 @@ class NiconicoPlaylistIE(InfoExtractor):
             'uploader_id': uploader_id,
             'entries': OnDemandPagedList(pagefunc, 25),
         }
+
+
+class NiconicoUserIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?nicovideo\.jp/user/(?P<id>\d+)/?(?:$|[#?])'
+    _TEST = {
+        'url': 'https://www.nicovideo.jp/user/419948',
+        'info_dict': {
+            'id': '419948',
+        },
+        'playlist_mincount': 101,
+    }
+    _API_URL = "https://nvapi.nicovideo.jp/v1/users/%s/videos?sortKey=registeredAt&sortOrder=desc&pageSize=%s&page=%s"
+    _api_headers = {
+        'X-Frontend-ID': '6',
+        'X-Frontend-Version': '0',
+        'X-Niconico-Language': 'en-us'
+    }
+    _PAGE_SIZE = 100
+
+    def _entries(self, list_id, ):
+        total_count = 1
+        count = page_num = 0
+        while count < total_count:
+            json_parsed = self._download_json(
+                self._API_URL % (list_id, self._PAGE_SIZE, page_num + 1), list_id,
+                headers=self._api_headers,
+                note='Downloading JSON metadata%s' % (' page %d' % page_num if page_num else ''))
+            if not page_num:
+                total_count = int_or_none(json_parsed['data'].get('totalCount'))
+            for entry in json_parsed["data"]["items"]:
+                count += 1
+                yield self.url_result('https://www.nicovideo.jp/watch/%s' % entry['id'])
+            page_num += 1
+
+    def _real_extract(self, url):
+        list_id = self._match_id(url)
+        return self.playlist_result(self._entries(list_id), list_id, ie=NiconicoIE.ie_key())

yt_dlp/extractor/ninecninemedia.py

@@ -23,11 +23,9 @@ class NineCNineMediaIE(InfoExtractor):
         destination_code, content_id = re.match(self._VALID_URL, url).groups()
         api_base_url = self._API_BASE_TEMPLATE % (destination_code, content_id)
         content = self._download_json(api_base_url, content_id, query={
-            '$include': '[Media,Season,ContentPackages]',
+            '$include': '[Media.Name,Season,ContentPackages.Duration,ContentPackages.Id]',
         })
         title = content['Name']
-        if len(content['ContentPackages']) > 1:
-            raise ExtractorError('multiple content packages')
         content_package = content['ContentPackages'][0]
         package_id = content_package['Id']
         content_package_url = api_base_url + 'contentpackages/%s/' % package_id

yt_dlp/extractor/nitter.py

@@ -11,60 +11,100 @@ from ..utils import (
     determine_ext,
 )
 import re
+import random
 
 
 class NitterIE(InfoExtractor):
     # Taken from https://github.com/zedeus/nitter/wiki/Instances
-    INSTANCES = ('nitter.net',
-                 'nitter.snopyta.org',
-                 'nitter.42l.fr',
-                 'nitter.nixnet.services',
-                 'nitter.13ad.de',
-                 'nitter.pussthecat.org',
-                 'nitter.mastodont.cat',
-                 'nitter.dark.fail',
-                 'nitter.tedomum.net',
-                 'nitter.cattube.org',
-                 'nitter.fdn.fr',
-                 'nitter.1d4.us',
-                 'nitter.kavin.rocks',
-                 'tweet.lambda.dance',
-                 'nitter.cc',
-                 'nitter.weaponizedhumiliation.com',
-                 '3nzoldnxplag42gqjs23xvghtzf6t6yzssrtytnntc6ppc7xxuoneoad.onion',
-                 'nitter.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd.onion',
-                 'nitterlgj3n5fgwesu3vxc5h67ruku33nqaoeoocae2mvlzhsu6k7fqd.onion')
+
+    NON_HTTP_INSTANCES = (
+        '3nzoldnxplag42gqjs23xvghtzf6t6yzssrtytnntc6ppc7xxuoneoad.onion',
+        'nitter.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd.onion',
+        'nitter7bryz3jv7e3uekphigvmoyoem4al3fynerxkj22dmoxoq553qd.onion',
+        'npf37k3mtzwxreiw52ccs5ay4e6qt2fkcs2ndieurdyn2cuzzsfyfvid.onion',
+        'nitter.v6vgyqpa7yefkorazmg5d5fimstmvm2vtbirt6676mt7qmllrcnwycqd.onion',
+        'i23nv6w3juvzlw32xzoxcqzktegd4i4fu3nmnc2ewv4ggiu4ledwklad.onion',
+        '26oq3gioiwcmfojub37nz5gzbkdiqp7fue5kvye7d4txv4ny6fb4wwid.onion',
+
+        'nitter.i2p',
+        'u6ikd6zndl3c4dsdq4mmujpntgeevdk5qzkfb57r4tnfeccrn2qa.b32.i2p',
+
+        'nitterlgj3n5fgwesu3vxc5h67ruku33nqaoeoocae2mvlzhsu6k7fqd.onion',
+    )
+
+    HTTP_INSTANCES = (
+        'nitter.42l.fr',
+        'nitter.pussthecat.org',
+        'nitter.nixnet.services',
+        'nitter.mastodont.cat',
+        'nitter.tedomum.net',
+        'nitter.fdn.fr',
+        'nitter.1d4.us',
+        'nitter.kavin.rocks',
+        'tweet.lambda.dance',
+        'nitter.cc',
+        'nitter.vxempire.xyz',
+        'nitter.unixfox.eu',
+        'nitter.domain.glass',
+        'nitter.himiko.cloud',
+        'nitter.eu',
+        'nitter.namazso.eu',
+        'nitter.mailstation.de',
+        'nitter.actionsack.com',
+        'nitter.cattube.org',
+        'nitter.dark.fail',
+        'birdsite.xanny.family',
+        'nitter.40two.app',
+        'nitter.skrep.in',
+
+        # not in the list anymore
+        'nitter.snopyta.org',
+    )
+
+    DEAD_INSTANCES = (
+        # maintenance
+        'nitter.ethibox.fr',
+
+        # official, rate limited
+        'nitter.net',
+        # offline
+        'nitter.13ad.de',
+        'nitter.weaponizedhumiliation.com',
+    )
+
+    INSTANCES = NON_HTTP_INSTANCES + HTTP_INSTANCES + DEAD_INSTANCES
 
     _INSTANCES_RE = '(?:' + '|'.join([re.escape(instance) for instance in INSTANCES]) + ')'
     _VALID_URL = r'https?://%(instance)s/(?P<uploader_id>.+)/status/(?P<id>[0-9]+)(#.)?' % {'instance': _INSTANCES_RE}
-    current_instance = INSTANCES[0]  # the test and official instance
+    current_instance = random.choice(HTTP_INSTANCES)
+
     _TESTS = [
         {
             # GIF (wrapped in mp4)
-            'url': 'https://' + current_instance + '/firefox/status/1314279897502629888#m',
+            'url': 'https://%s/firefox/status/1314279897502629888#m' % current_instance,
             'info_dict': {
                 'id': '1314279897502629888',
                 'ext': 'mp4',
-                'title': 'Firefox 🔥 - You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension.   Report harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg  #UnfckTheInternet',
-                'description': 'You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension.   Report harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg  #UnfckTheInternet',
+                'title': 'Firefox 🔥 - You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension. \n\nReport harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg\n\n#UnfckTheInternet',
+                'description': 'You know the old saying, if you see something say something. Now you actually can with the YouTube regrets extension. \n\nReport harmful YouTube recommendations so others can avoid watching them. ➡️ https://mzl.la/3iFIiyg\n\n#UnfckTheInternet',
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'uploader': 'Firefox 🔥',
                 'uploader_id': 'firefox',
-                'uploader_url': 'https://' + current_instance + '/firefox',
+                'uploader_url': 'https://%s/firefox' % current_instance,
                 'upload_date': '20201008',
                 'timestamp': 1602183720,
             },
         }, {  # normal video
-            'url': 'https://' + current_instance + '/Le___Doc/status/1299715685392756737#m',
+            'url': 'https://%s/Le___Doc/status/1299715685392756737#m' % current_instance,
             'info_dict': {
                 'id': '1299715685392756737',
                 'ext': 'mp4',
-                'title': 'Le Doc - "Je ne prédis jamais rien" D Raoult, Août 2020...',
-                'description': '"Je ne prédis jamais rien" D Raoult, Août 2020...',
+                'title': 'Le Doc - "Je ne prédis jamais rien"\nD Raoult, Août 2020...',
+                'description': '"Je ne prédis jamais rien"\nD Raoult, Août 2020...',
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'uploader': 'Le Doc',
                 'uploader_id': 'Le___Doc',
-                'uploader_url': 'https://' + current_instance + '/Le___Doc',
+                'uploader_url': 'https://%s/Le___Doc' % current_instance,
                 'upload_date': '20200829',
                 'timestamp': 1598711341,
                 'view_count': int,
@@ -73,31 +113,51 @@ class NitterIE(InfoExtractor):
                 'comment_count': int,
             },
         }, {  # video embed in a "Streaming Political Ads" box
-            'url': 'https://' + current_instance + '/mozilla/status/1321147074491092994#m',
+            'url': 'https://%s/mozilla/status/1321147074491092994#m' % current_instance,
             'info_dict': {
                 'id': '1321147074491092994',
                 'ext': 'mp4',
-                'title': "Mozilla - Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?  This isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few.   Learn more ➡️ https://mzl.la/StreamingAds",
-                'description': "Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?  This isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few.   Learn more ➡️ https://mzl.la/StreamingAds",
+                'title': "Mozilla - Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?\n\nThis isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few. \n\nLearn more ➡️ https://mzl.la/StreamingAds",
+                'description': "Are you being targeted with weird, ominous or just plain annoying political ads while streaming your favorite shows?\n\nThis isn't a real political ad, but if you're watching streaming TV in the U.S., chances are you've seen quite a few. \n\nLearn more ➡️ https://mzl.la/StreamingAds",
                 'thumbnail': r're:^https?://.*\.jpg$',
                 'uploader': 'Mozilla',
                 'uploader_id': 'mozilla',
-                'uploader_url': 'https://' + current_instance + '/mozilla',
+                'uploader_url': 'https://%s/mozilla' % current_instance,
                 'upload_date': '20201027',
                 'timestamp': 1603820982
             },
-        },
+        }, {  # not the first tweet but main-tweet
+            'url': 'https://%s/TheNaturalNu/status/1379050895539724290#m' % current_instance,
+            'info_dict': {
+                'id': '1379050895539724290',
+                'ext': 'mp4',
+                'title': 'Dorothy Zbornak - This had me hollering!!',
+                'description': 'This had me hollering!!',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'uploader': 'Dorothy Zbornak',
+                'uploader_id': 'TheNaturalNu',
+                'uploader_url': 'https://%s/TheNaturalNu' % current_instance,
+                'timestamp': 1617626329,
+                'upload_date': '20210405'
+            }
+        }
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
         parsed_url = compat_urlparse.urlparse(url)
-        base_url = parsed_url.scheme + '://' + parsed_url.netloc
+        base_url = '%s://%s' % (parsed_url.scheme, parsed_url.netloc)
 
         self._set_cookie(parsed_url.netloc, 'hlsPlayback', 'on')
-        webpage = self._download_webpage(url, video_id)
+        full_webpage = self._download_webpage(url, video_id)
 
-        video_url = base_url + self._html_search_regex(r'(?:<video[^>]+data-url|<source[^>]+src)="([^"]+)"', webpage, 'video url')
+        main_tweet_start = full_webpage.find('class="main-tweet"')
+        if main_tweet_start > 0:
+            webpage = full_webpage[main_tweet_start:]
+        if not webpage:
+            webpage = full_webpage
+
+        video_url = '%s%s' % (base_url, self._html_search_regex(r'(?:<video[^>]+data-url|<source[^>]+src)="([^"]+)"', webpage, 'video url'))
         ext = determine_ext(video_url)
 
         if ext == 'unknown_video':
@@ -108,33 +168,34 @@ class NitterIE(InfoExtractor):
                 'ext': ext
             }]
 
-        title = (
-            self._og_search_description(webpage).replace('\n', ' ')
-            or self._html_search_regex(r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title'))
+        title = self._og_search_description(full_webpage)
+        if not title:
+            title = self._html_search_regex(r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title')
         description = title
 
         mobj = re.match(self._VALID_URL, url)
         uploader_id = (
             mobj.group('uploader_id')
-            or self._html_search_regex(r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False))
+            or self._html_search_regex(r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False)
+        )
 
         if uploader_id:
-            uploader_url = base_url + '/' + uploader_id
+            uploader_url = '%s/%s' % (base_url, uploader_id)
 
         uploader = self._html_search_regex(r'<a class="fullname"[^>]+title="([^"]+)"', webpage, 'uploader name', fatal=False)
 
         if uploader:
-            title = uploader + ' - ' + title
+            title = '%s - %s' % (uploader, title)
 
         view_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-play[^>]*></span>\s([^<]+)</div>', webpage, 'view count', fatal=False))
         like_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-heart[^>]*></span>\s([^<]+)</div>', webpage, 'like count', fatal=False))
         repost_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-retweet[^>]*></span>\s([^<]+)</div>', webpage, 'repost count', fatal=False))
         comment_count = parse_count(self._html_search_regex(r'<span[^>]+class="icon-comment[^>]*></span>\s([^<]+)</div>', webpage, 'repost count', fatal=False))
 
-        thumbnail = base_url + (self._html_search_meta('og:image', webpage, 'thumbnail url')
-                                or self._html_search_regex(r'<video[^>]+poster="([^"]+)"', webpage, 'thumbnail url', fatal=False))
-
-        thumbnail = remove_end(thumbnail, '%3Asmall')  # if parsed with regex, it should contain this
+        thumbnail = self._html_search_meta('og:image', full_webpage, 'thumbnail url')
+        if not thumbnail:
+            thumbnail = '%s%s' % (base_url, self._html_search_regex(r'<video[^>]+poster="([^"]+)"', webpage, 'thumbnail url', fatal=False))
+            thumbnail = remove_end(thumbnail, '%3Asmall')
 
         thumbnails = []
         thumbnail_ids = ('thumb', 'small', 'large', 'medium', 'orig')

yt_dlp/extractor/palcomp3.py

@@ -0,0 +1,148 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    str_or_none,
+    try_get,
+)
+
+
+class PalcoMP3BaseIE(InfoExtractor):
+    _GQL_QUERY_TMPL = '''{
+  artist(slug: "%s") {
+    %s
+  }
+}'''
+    _ARTIST_FIELDS_TMPL = '''music(slug: "%%s") {
+      %s
+    }'''
+    _MUSIC_FIELDS = '''duration
+      hls
+      mp3File
+      musicID
+      plays
+      title'''
+
+    def _call_api(self, artist_slug, artist_fields):
+        return self._download_json(
+            'https://www.palcomp3.com.br/graphql/', artist_slug, query={
+                'query': self._GQL_QUERY_TMPL % (artist_slug, artist_fields),
+            })['data']
+
+    def _parse_music(self, music):
+        music_id = compat_str(music['musicID'])
+        title = music['title']
+
+        formats = []
+        hls_url = music.get('hls')
+        if hls_url:
+            formats.append({
+                'url': hls_url,
+                'protocol': 'm3u8_native',
+                'ext': 'mp4',
+            })
+        mp3_file = music.get('mp3File')
+        if mp3_file:
+            formats.append({
+                'url': mp3_file,
+            })
+
+        return {
+            'id': music_id,
+            'title': title,
+            'formats': formats,
+            'duration': int_or_none(music.get('duration')),
+            'view_count': int_or_none(music.get('plays')),
+        }
+
+    def _real_initialize(self):
+        self._ARTIST_FIELDS_TMPL = self._ARTIST_FIELDS_TMPL % self._MUSIC_FIELDS
+
+    def _real_extract(self, url):
+        artist_slug, music_slug = re.match(self._VALID_URL, url).groups()
+        artist_fields = self._ARTIST_FIELDS_TMPL % music_slug
+        music = self._call_api(artist_slug, artist_fields)['artist']['music']
+        return self._parse_music(music)
+
+
+class PalcoMP3IE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:song'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/nossas-composicoes-cuida-bem-dela/',
+        'md5': '99fd6405b2d8fd589670f6db1ba3b358',
+        'info_dict': {
+            'id': '3162927',
+            'ext': 'mp3',
+            'title': 'Nossas Composições - CUIDA BEM DELA',
+            'duration': 210,
+            'view_count': int,
+        }
+    }]
+
+    @classmethod
+    def suitable(cls, url):
+        return False if PalcoMP3VideoIE.suitable(url) else super(PalcoMP3IE, cls).suitable(url)
+
+
+class PalcoMP3ArtistIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:artist'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<id>[^/?&#]+)'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com.br/condedoforro/',
+        'info_dict': {
+            'id': '358396',
+            'title': 'Conde do Forró',
+        },
+        'playlist_mincount': 188,
+    }]
+    _ARTIST_FIELDS_TMPL = '''artistID
+    musics {
+      nodes {
+        %s
+      }
+    }
+    name'''
+
+    @ classmethod
+    def suitable(cls, url):
+        return False if re.match(PalcoMP3IE._VALID_URL, url) else super(PalcoMP3ArtistIE, cls).suitable(url)
+
+    def _real_extract(self, url):
+        artist_slug = self._match_id(url)
+        artist = self._call_api(artist_slug, self._ARTIST_FIELDS_TMPL)['artist']
+
+        def entries():
+            for music in (try_get(artist, lambda x: x['musics']['nodes'], list) or []):
+                yield self._parse_music(music)
+
+        return self.playlist_result(
+            entries(), str_or_none(artist.get('artistID')), artist.get('name'))
+
+
+class PalcoMP3VideoIE(PalcoMP3BaseIE):
+    IE_NAME = 'PalcoMP3:video'
+    _VALID_URL = r'https?://(?:www\.)?palcomp3\.com(?:\.br)?/(?P<artist>[^/]+)/(?P<id>[^/?&#]+)/?#clipe'
+    _TESTS = [{
+        'url': 'https://www.palcomp3.com/maiaraemaraisaoficial/maiara-e-maraisa-voce-faz-falta-aqui-ao-vivo-em-vicosa-mg/#clipe',
+        'add_ie': ['Youtube'],
+        'info_dict': {
+            'id': '_pD1nR2qqPg',
+            'ext': 'mp4',
+            'title': 'Maiara e Maraisa - Você Faz Falta Aqui - DVD Ao Vivo Em Campo Grande',
+            'description': 'md5:7043342c09a224598e93546e98e49282',
+            'upload_date': '20161107',
+            'uploader_id': 'maiaramaraisaoficial',
+            'uploader': 'Maiara e Maraisa',
+        }
+    }]
+    _MUSIC_FIELDS = 'youtubeID'
+
+    def _parse_music(self, music):
+        youtube_id = music['youtubeID']
+        return self.url_result(youtube_id, 'Youtube', youtube_id)

yt_dlp/extractor/peertube.py

@@ -599,11 +599,13 @@ class PeerTubeIE(InfoExtractor):
         else:
             age_limit = None
 
+        webpage_url = 'https://%s/videos/watch/%s' % (host, video_id)
+
         return {
             'id': video_id,
             'title': title,
             'description': description,
-            'thumbnail': urljoin(url, video.get('thumbnailPath')),
+            'thumbnail': urljoin(webpage_url, video.get('thumbnailPath')),
             'timestamp': unified_timestamp(video.get('publishedAt')),
             'uploader': account_data('displayName', compat_str),
             'uploader_id': str_or_none(account_data('id', int)),
@@ -621,5 +623,6 @@ class PeerTubeIE(InfoExtractor):
             'tags': try_get(video, lambda x: x['tags'], list),
             'categories': categories,
             'formats': formats,
-            'subtitles': subtitles
+            'subtitles': subtitles,
+            'webpage_url': webpage_url,
         }

yt_dlp/extractor/phoenix.py

@@ -1,52 +1,128 @@
+# coding: utf-8
 from __future__ import unicode_literals
 
-from .common import InfoExtractor
-from ..utils import ExtractorError
+import re
+
+from .youtube import YoutubeIE
+from .zdf import ZDFBaseIE
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    merge_dicts,
+    unified_timestamp,
+    xpath_text,
+)
 
 
-class PhoenixIE(InfoExtractor):
+class PhoenixIE(ZDFBaseIE):
     IE_NAME = 'phoenix.de'
-    _VALID_URL = r'''https?://(?:www\.)?phoenix.de/\D+(?P<id>\d+)\.html'''
-    _TESTS = [
-        {
-            'url': 'https://www.phoenix.de/sendungen/dokumentationen/unsere-welt-in-zukunft---stadt-a-1283620.html',
-            'md5': '5e765e838aa3531c745a4f5b249ee3e3',
-            'info_dict': {
-                'id': '0OB4HFc43Ns',
-                'ext': 'mp4',
-                'title': 'Unsere Welt in Zukunft - Stadt',
-                'description': 'md5:9bfb6fd498814538f953b2dcad7ce044',
-                'upload_date': '20190912',
-                'uploader': 'phoenix',
-                'uploader_id': 'phoenix',
-            }
+    _VALID_URL = r'https?://(?:www\.)?phoenix\.de/(?:[^/]+/)*[^/?#&]*-a-(?P<id>\d+)\.html'
+    _TESTS = [{
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/wohin-fuehrt-der-protest-in-der-pandemie-100.html
+        'url': 'https://www.phoenix.de/sendungen/ereignisse/corona-nachgehakt/wohin-fuehrt-der-protest-in-der-pandemie-a-2050630.html',
+        'md5': '34ec321e7eb34231fd88616c65c92db0',
+        'info_dict': {
+            'id': '210222_phx_nachgehakt_corona_protest',
+            'ext': 'mp4',
+            'title': 'Wohin führt der Protest in der Pandemie?',
+            'description': 'md5:7d643fe7f565e53a24aac036b2122fbd',
+            'duration': 1691,
+            'timestamp': 1613906100,
+            'upload_date': '20210221',
+            'uploader': 'Phoenix',
+            'channel': 'corona nachgehakt',
         },
-        {
-            'url': 'https://www.phoenix.de/drohnenangriffe-in-saudi-arabien-a-1286995.html?ref=aktuelles',
-            'only_matching': True,
+    }, {
+        # Youtube embed
+        'url': 'https://www.phoenix.de/sendungen/gespraeche/phoenix-streitgut-brennglas-corona-a-1965505.html',
+        'info_dict': {
+            'id': 'hMQtqFYjomk',
+            'ext': 'mp4',
+            'title': 'phoenix streitgut: Brennglas Corona - Wie gerecht ist unsere Gesellschaft?',
+            'description': 'md5:ac7a02e2eb3cb17600bc372e4ab28fdd',
+            'duration': 3509,
+            'upload_date': '20201219',
+            'uploader': 'phoenix',
+            'uploader_id': 'phoenix',
         },
-        # an older page: https://www.phoenix.de/sendungen/gespraeche/phoenix-persoenlich/im-dialog-a-177727.html
-        # seems to not have an embedded video, even though it's uploaded on youtube: https://www.youtube.com/watch?v=4GxnoUHvOkM
-    ]
-
-    def extract_from_json_api(self, video_id, api_url):
-        doc = self._download_json(
-            api_url, video_id,
-            note="Downloading webpage metadata",
-            errnote="Failed to load webpage metadata")
-
-        for a in doc["absaetze"]:
-            if a["typ"] == "video-youtube":
-                return {
-                    '_type': 'url_transparent',
-                    'id': a["id"],
-                    'title': doc["titel"],
-                    'url': "https://www.youtube.com/watch?v=%s" % a["id"],
-                    'ie_key': 'Youtube',
-                }
-        raise ExtractorError("No downloadable video found", expected=True)
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://www.phoenix.de/entwicklungen-in-russland-a-2044720.html',
+        'only_matching': True,
+    }, {
+        # no media
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/mit-dem-jumbo-durch-die-nacht-a-89625.html',
+        'only_matching': True,
+    }, {
+        # Same as https://www.zdf.de/politik/phoenix-sendungen/die-gesten-der-maechtigen-100.html
+        'url': 'https://www.phoenix.de/sendungen/dokumentationen/gesten-der-maechtigen-i-a-89468.html?ref=suche',
+        'only_matching': True,
+    }]
 
     def _real_extract(self, url):
-        page_id = self._match_id(url)
-        api_url = 'https://www.phoenix.de/response/id/%s' % page_id
-        return self.extract_from_json_api(page_id, api_url)
+        article_id = self._match_id(url)
+
+        article = self._download_json(
+            'https://www.phoenix.de/response/id/%s' % article_id, article_id,
+            'Downloading article JSON')
+
+        video = article['absaetze'][0]
+        title = video.get('titel') or article.get('subtitel')
+
+        if video.get('typ') == 'video-youtube':
+            video_id = video['id']
+            return self.url_result(
+                video_id, ie=YoutubeIE.ie_key(), video_id=video_id,
+                video_title=title)
+
+        video_id = compat_str(video.get('basename') or video.get('content'))
+
+        details = self._download_xml(
+            'https://www.phoenix.de/php/mediaplayer/data/beitrags_details.php',
+            video_id, 'Downloading details XML', query={
+                'ak': 'web',
+                'ptmd': 'true',
+                'id': video_id,
+                'profile': 'player2',
+            })
+
+        title = title or xpath_text(
+            details, './/information/title', 'title', fatal=True)
+        content_id = xpath_text(
+            details, './/video/details/basename', 'content id', fatal=True)
+
+        info = self._extract_ptmd(
+            'https://tmd.phoenix.de/tmd/2/ngplayer_2_3/vod/ptmd/phoenix/%s' % content_id,
+            content_id, None, url)
+
+        timestamp = unified_timestamp(xpath_text(details, './/details/airtime'))
+
+        thumbnails = []
+        for node in details.findall('.//teaserimages/teaserimage'):
+            thumbnail_url = node.text
+            if not thumbnail_url:
+                continue
+            thumbnail = {
+                'url': thumbnail_url,
+            }
+            thumbnail_key = node.get('key')
+            if thumbnail_key:
+                m = re.match('^([0-9]+)x([0-9]+)$', thumbnail_key)
+                if m:
+                    thumbnail['width'] = int(m.group(1))
+                    thumbnail['height'] = int(m.group(2))
+            thumbnails.append(thumbnail)
+
+        return merge_dicts(info, {
+            'id': content_id,
+            'title': title,
+            'description': xpath_text(details, './/information/detail'),
+            'duration': int_or_none(xpath_text(details, './/details/lengthSec')),
+            'thumbnails': thumbnails,
+            'timestamp': timestamp,
+            'uploader': xpath_text(details, './/details/channel'),
+            'uploader_id': xpath_text(details, './/details/originChannelId'),
+            'channel': xpath_text(details, './/details/originChannelTitle'),
+        })

yt_dlp/extractor/picarto.py

@@ -1,22 +1,15 @@
 # coding: utf-8
 from __future__ import unicode_literals
 
-import re
-import time
-
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     ExtractorError,
     js_to_json,
-    try_get,
-    update_url_query,
-    urlencode_postdata,
 )
 
 
 class PicartoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)(?:/(?P<token>[a-zA-Z0-9]+))?'
+    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
     _TEST = {
         'url': 'https://picarto.tv/Setz',
         'info_dict': {
@@ -34,65 +27,46 @@ class PicartoIE(InfoExtractor):
         return False if PicartoVodIE.suitable(url) else super(PicartoIE, cls).suitable(url)
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        channel_id = mobj.group('id')
+        channel_id = self._match_id(url)
 
-        metadata = self._download_json(
-            'https://api.picarto.tv/v1/channel/name/' + channel_id,
-            channel_id)
+        data = self._download_json(
+            'https://ptvintern.picarto.tv/ptvapi', channel_id, query={
+                'query': '''{
+  channel(name: "%s") {
+    adult
+    id
+    online
+    stream_name
+    title
+  }
+  getLoadBalancerUrl(channel_name: "%s") {
+    url
+  }
+}''' % (channel_id, channel_id),
+            })['data']
+        metadata = data['channel']
 
-        if metadata.get('online') is False:
+        if metadata.get('online') == 0:
             raise ExtractorError('Stream is offline', expected=True)
+        title = metadata['title']
 
         cdn_data = self._download_json(
-            'https://picarto.tv/process/channel', channel_id,
-            data=urlencode_postdata({'loadbalancinginfo': channel_id}),
-            note='Downloading load balancing info')
+            data['getLoadBalancerUrl']['url'] + '/stream/json_' + metadata['stream_name'] + '.js',
+            channel_id, 'Downloading load balancing info')
 
-        token = mobj.group('token') or 'public'
-        params = {
-            'con': int(time.time() * 1000),
-            'token': token,
-        }
-
-        prefered_edge = cdn_data.get('preferedEdge')
         formats = []
-
-        for edge in cdn_data['edges']:
-            edge_ep = edge.get('ep')
-            if not edge_ep or not isinstance(edge_ep, compat_str):
+        for source in (cdn_data.get('source') or []):
+            source_url = source.get('url')
+            if not source_url:
                 continue
-            edge_id = edge.get('id')
-            for tech in cdn_data['techs']:
-                tech_label = tech.get('label')
-                tech_type = tech.get('type')
-                preference = 0
-                if edge_id == prefered_edge:
-                    preference += 1
-                format_id = []
-                if edge_id:
-                    format_id.append(edge_id)
-                if tech_type == 'application/x-mpegurl' or tech_label == 'HLS':
-                    format_id.append('hls')
-                    formats.extend(self._extract_m3u8_formats(
-                        update_url_query(
-                            'https://%s/hls/%s/index.m3u8'
-                            % (edge_ep, channel_id), params),
-                        channel_id, 'mp4', quality=preference,
-                        m3u8_id='-'.join(format_id), fatal=False))
-                    continue
-                elif tech_type == 'video/mp4' or tech_label == 'MP4':
-                    format_id.append('mp4')
-                    formats.append({
-                        'url': update_url_query(
-                            'https://%s/mp4/%s.mp4' % (edge_ep, channel_id),
-                            params),
-                        'format_id': '-'.join(format_id),
-                        'quality': preference,
-                    })
-                else:
-                    # rtmp format does not seem to work
-                    continue
+            source_type = source.get('type')
+            if source_type == 'html5/application/vnd.apple.mpegurl':
+                formats.extend(self._extract_m3u8_formats(
+                    source_url, channel_id, 'mp4', m3u8_id='hls', fatal=False))
+            elif source_type == 'html5/video/mp4':
+                formats.append({
+                    'url': source_url,
+                })
         self._sort_formats(formats)
 
         mature = metadata.get('adult')
@@ -103,10 +77,10 @@ class PicartoIE(InfoExtractor):
 
         return {
             'id': channel_id,
-            'title': self._live_title(metadata.get('title') or channel_id),
+            'title': self._live_title(title.strip()),
             'is_live': True,
-            'thumbnail': try_get(metadata, lambda x: x['thumbnails']['web']),
             'channel': channel_id,
+            'channel_id': metadata.get('id'),
             'channel_url': 'https://picarto.tv/%s' % channel_id,
             'age_limit': age_limit,
             'formats': formats,

yt_dlp/extractor/pinterest.py

@@ -31,6 +31,7 @@ class PinterestBaseIE(InfoExtractor):
 
         title = (data.get('title') or data.get('grid_title') or video_id).strip()
 
+        urls = []
         formats = []
         duration = None
         if extract_formats:
@@ -38,8 +39,9 @@ class PinterestBaseIE(InfoExtractor):
                 if not isinstance(format_dict, dict):
                     continue
                 format_url = url_or_none(format_dict.get('url'))
-                if not format_url:
+                if not format_url or format_url in urls:
                     continue
+                urls.append(format_url)
                 duration = float_or_none(format_dict.get('duration'), scale=1000)
                 ext = determine_ext(format_url)
                 if 'hls' in format_id.lower() or ext == 'm3u8':

yt_dlp/extractor/plutotv.py

@@ -0,0 +1,164 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+import uuid
+
+from .common import InfoExtractor
+from ..compat import (
+    compat_str,
+    compat_urlparse,
+)
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    int_or_none,
+    try_get,
+    url_or_none,
+)
+
+
+class PlutoTVIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?pluto\.tv/on-demand/(?P<video_type>movies|series)/(?P<slug>.*)/?$'
+    _INFO_URL = 'https://service-vod.clusters.pluto.tv/v3/vod/slugs/'
+    _INFO_QUERY_PARAMS = {
+        'appName': 'web',
+        'appVersion': 'na',
+        'clientID': compat_str(uuid.uuid1()),
+        'clientModelNumber': 'na',
+        'serverSideAds': 'false',
+        'deviceMake': 'unknown',
+        'deviceModel': 'web',
+        'deviceType': 'web',
+        'deviceVersion': 'unknown',
+        'sid': compat_str(uuid.uuid1()),
+    }
+    _TESTS = [
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/2/episode/its-in-the-cards-2009-2-3',
+            'md5': 'ebcdd8ed89aaace9df37924f722fd9bd',
+            'info_dict': {
+                'id': '5de6c598e9379ae4912df0a8',
+                'ext': 'mp4',
+                'title': 'It\'s In The Cards',
+                'episode': 'It\'s In The Cards',
+                'description': 'The teams face off against each other in a 3-on-2 soccer showdown.  Strategy comes into play, though, as each team gets to select their opposing teams’ two defenders.',
+                'series': 'I Love Money',
+                'season_number': 2,
+                'episode_number': 3,
+                'duration': 3600,
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/season/1/',
+            'playlist_count': 11,
+            'info_dict': {
+                'id': '5de6c582e9379ae4912dedbd',
+                'title': 'I Love Money - Season 1',
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/series/i-love-money/',
+            'playlist_count': 26,
+            'info_dict': {
+                'id': '5de6c582e9379ae4912dedbd',
+                'title': 'I Love Money',
+            }
+        },
+        {
+            'url': 'https://pluto.tv/on-demand/movies/arrival-2015-1-1',
+            'md5': '3cead001d317a018bf856a896dee1762',
+            'info_dict': {
+                'id': '5e83ac701fa6a9001bb9df24',
+                'ext': 'mp4',
+                'title': 'Arrival',
+                'description': 'When mysterious spacecraft touch down across the globe, an elite team - led by expert translator Louise Banks (Academy Award® nominee Amy Adams) – races against time to decipher their intent.',
+                'duration': 9000,
+            }
+        },
+    ]
+
+    def _to_ad_free_formats(self, video_id, formats):
+        ad_free_formats = []
+        m3u8_urls = set()
+        for format in formats:
+            res = self._download_webpage(
+                format.get('url'), video_id, note='Downloading m3u8 playlist',
+                fatal=False)
+            if not res:
+                continue
+            first_segment_url = re.search(
+                r'^(https?://.*/)0\-(end|[0-9]+)/[^/]+\.ts$', res,
+                re.MULTILINE)
+            if not first_segment_url:
+                continue
+            m3u8_urls.add(
+                compat_urlparse.urljoin(first_segment_url.group(1), '0-end/master.m3u8'))
+
+        for m3u8_url in m3u8_urls:
+            ad_free_formats.extend(
+                self._extract_m3u8_formats(
+                    m3u8_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+        self._sort_formats(ad_free_formats)
+        return ad_free_formats
+
+    def _get_video_info(self, video_json, slug, series_name=None):
+        video_id = video_json.get('_id', slug)
+        formats = []
+        for video_url in try_get(video_json, lambda x: x['stitched']['urls'], list) or []:
+            if video_url.get('type') != 'hls':
+                continue
+            url = url_or_none(video_url.get('url'))
+            formats.extend(
+                self._extract_m3u8_formats(
+                    url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+        info = {
+            'id': video_id,
+            'formats': self._to_ad_free_formats(video_id, formats),
+            'title': video_json.get('name'),
+            'description': video_json.get('description'),
+            'duration': float_or_none(video_json.get('duration'), scale=1000),
+        }
+        if series_name:
+            info.update({
+                'series': series_name,
+                'episode': video_json.get('name'),
+                'season_number': int_or_none(video_json.get('season')),
+                'episode_number': int_or_none(video_json.get('number')),
+            })
+        return info
+
+    def _real_extract(self, url):
+        path = compat_urlparse.urlparse(url).path
+        path_components = path.split('/')
+        video_type = path_components[2]
+        info_slug = path_components[3]
+        video_json = self._download_json(self._INFO_URL + info_slug, info_slug,
+                                         query=self._INFO_QUERY_PARAMS)
+
+        if video_type == 'series':
+            series_name = video_json.get('name', info_slug)
+            season_number = int_or_none(try_get(path_components, lambda x: x[5]))
+            episode_slug = try_get(path_components, lambda x: x[7])
+
+            videos = []
+            for season in video_json['seasons']:
+                if season_number is not None and season_number != int_or_none(season.get('number')):
+                    continue
+                for episode in season['episodes']:
+                    if episode_slug is not None and episode_slug != episode.get('slug'):
+                        continue
+                    videos.append(self._get_video_info(episode, episode_slug, series_name))
+            if not videos:
+                raise ExtractorError('Failed to find any videos to extract')
+            if episode_slug is not None and len(videos) == 1:
+                return videos[0]
+            playlist_title = series_name
+            if season_number is not None:
+                playlist_title += ' - Season %d' % season_number
+            return self.playlist_result(videos,
+                                        playlist_id=video_json.get('_id', info_slug),
+                                        playlist_title=playlist_title)
+        return self._get_video_info(video_json, info_slug)

yt_dlp/extractor/pornhub.py

@@ -167,6 +167,7 @@ class PornHubIE(PornHubBaseIE):
         'params': {
             'skip_download': True,
         },
+        'skip': 'Video has been flagged for verification in accordance with our trust and safety policy',
     }, {
         # subtitles
         'url': 'https://www.pornhub.com/view_video.php?viewkey=ph5af5fef7c2aa7',
@@ -265,7 +266,8 @@ class PornHubIE(PornHubBaseIE):
         webpage = dl_webpage('pc')
 
         error_msg = self._html_search_regex(
-            r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+            (r'(?s)<div[^>]+class=(["\'])(?:(?!\1).)*\b(?:removed|userMessageSection)\b(?:(?!\1).)*\1[^>]*>(?P<error>.+?)</div>',
+             r'(?s)<section[^>]+class=["\']noVideo["\'][^>]*>(?P<error>.+?)</section>'),
             webpage, 'error message', default=None, group='error')
         if error_msg:
             error_msg = re.sub(r'\s+', ' ', error_msg)
@@ -394,34 +396,50 @@ class PornHubIE(PornHubBaseIE):
 
         upload_date = None
         formats = []
+
+        def add_format(format_url, height=None):
+            ext = determine_ext(format_url)
+            if ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    format_url, video_id, mpd_id='dash', fatal=False))
+                return
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
+                    m3u8_id='hls', fatal=False))
+                return
+            tbr = None
+            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', format_url)
+            if mobj:
+                if not height:
+                    height = int(mobj.group('height'))
+                tbr = int(mobj.group('tbr'))
+            formats.append({
+                'url': format_url,
+                'format_id': '%dp' % height if height else None,
+                'height': height,
+                'tbr': tbr,
+            })
+
         for video_url, height in video_urls:
             if not upload_date:
                 upload_date = self._search_regex(
                     r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
                 if upload_date:
                     upload_date = upload_date.replace('/', '')
-            ext = determine_ext(video_url)
-            if ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(
-                    video_url, video_id, mpd_id='dash', fatal=False))
+            if '/video/get_media' in video_url:
+                medias = self._download_json(video_url, video_id, fatal=False)
+                if isinstance(medias, list):
+                    for media in medias:
+                        if not isinstance(media, dict):
+                            continue
+                        video_url = url_or_none(media.get('videoUrl'))
+                        if not video_url:
+                            continue
+                        height = int_or_none(media.get('quality'))
+                        add_format(video_url, height)
                 continue
-            elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(
-                    video_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id='hls', fatal=False))
-                continue
-            tbr = None
-            mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
-            if mobj:
-                if not height:
-                    height = int(mobj.group('height'))
-                tbr = int(mobj.group('tbr'))
-            formats.append({
-                'url': video_url,
-                'format_id': '%dp' % height if height else None,
-                'height': height,
-                'tbr': tbr,
-            })
+            add_format(video_url)
         self._sort_formats(formats)
 
         video_uploader = self._html_search_regex(

yt_dlp/extractor/rai.py

@@ -158,6 +158,10 @@ class RaiPlayIE(RaiBaseIE):
         # subtitles at 'subtitlesArray' key (see #27698)
         'url': 'https://www.raiplay.it/video/2020/12/Report---04-01-2021-2e90f1de-8eee-4de4-ac0e-78d21db5b600.html',
         'only_matching': True,
+    }, {
+        # DRM protected
+        'url': 'https://www.raiplay.it/video/2020/09/Lo-straordinario-mondo-di-Zoey-S1E1-Lo-straordinario-potere-di-Zoey-ed493918-1d32-44b7-8454-862e473d00ff.html',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -166,6 +170,14 @@ class RaiPlayIE(RaiBaseIE):
         media = self._download_json(
             base + '.json', video_id, 'Downloading video JSON')
 
+        if not self._downloader.params.get('allow_unplayable_formats'):
+            if try_get(
+                    media,
+                    (lambda x: x['rights_management']['rights']['drm'],
+                     lambda x: x['program_info']['rights_management']['rights']['drm']),
+                    dict):
+                raise ExtractorError('This video is DRM protected.', expected=True)
+
         title = media['name']
         video = media['video']
 

yt_dlp/extractor/rcs.py

@@ -15,6 +15,9 @@ from ..utils import (
 
 
 class RCSBaseIE(InfoExtractor):
+    # based on VideoPlayerLoader.prototype.getVideoSrc
+    # and VideoPlayerLoader.prototype.transformSrc from
+    # https://js2.corriereobjects.it/includes2013/LIBS/js/corriere_video.sjs
     _ALL_REPLACE = {
         'media2vam.corriere.it.edgesuite.net':
             'media2vam-corriere-it.akamaized.net',
@@ -191,10 +194,10 @@ class RCSBaseIE(InfoExtractor):
             urls.get('m3u8'), video_id, 'mp4', entry_protocol='m3u8_native',
             m3u8_id='hls', fatal=False)
 
-        if not formats:
+        if urls.get('mp4'):
             formats.append({
                 'format_id': 'http-mp4',
-                'url': urls.get('mp4')
+                'url': urls['mp4']
             })
         self._sort_formats(formats)
         return formats
@@ -216,10 +219,12 @@ class RCSBaseIE(InfoExtractor):
         video_data = None
         # look for json video data url
         json = self._search_regex(
-            r'''(?x)var url\s*=\s*["']((?:https?:)?
-                //video\.rcs\.it
-                /fragment-includes/video-includes/.+?\.json)["'];''',
-            page, video_id, default=None)
+            r'''(?x)url\s*=\s*(["'])
+            (?P<url>
+                (?:https?:)?//video\.rcs\.it
+                /fragment-includes/video-includes/.+?\.json
+            )\1;''',
+            page, video_id, group='url', default=None)
         if json:
             if json.startswith('//'):
                 json = 'https:%s' % json
@@ -227,13 +232,16 @@ class RCSBaseIE(InfoExtractor):
 
         # if json url not found, look for json video data directly in the page
         else:
+            # RCS normal pages and most of the embeds
             json = self._search_regex(
                 r'[\s;]video\s*=\s*({[\s\S]+?})(?:;|,playlist=)',
                 page, video_id, default=None)
-            if json:
-                video_data = self._parse_json(
-                    json, video_id, transform_source=js_to_json)
-            else:
+            if not json and 'video-embed' in url:
+                page = self._download_webpage(url.replace('video-embed', 'video-json'), video_id)
+                json = self._search_regex(
+                    r'##start-video##({[\s\S]+?})##end-video##',
+                    page, video_id, default=None)
+            if not json:
                 # if no video data found try search for iframes
                 emb = RCSEmbedsIE._extract_url(page)
                 if emb:
@@ -242,6 +250,9 @@ class RCSBaseIE(InfoExtractor):
                         'url': emb,
                         'ie_key': RCSEmbedsIE.ie_key()
                     }
+            if json:
+                video_data = self._parse_json(
+                    json, video_id, transform_source=js_to_json)
 
         if not video_data:
             raise ExtractorError('Video data not found in the page')
@@ -250,7 +261,8 @@ class RCSBaseIE(InfoExtractor):
             self._get_video_src(video_data), video_id)
 
         description = (video_data.get('description')
-                       or clean_html(video_data.get('htmlDescription')))
+                       or clean_html(video_data.get('htmlDescription'))
+                       or self._html_search_meta('description', page))
         uploader = video_data.get('provider') or mobj.group('cdn')
 
         return {
@@ -283,6 +295,7 @@ class RCSEmbedsIE(RCSBaseIE):
             'uploader': 'rcs.it',
         }
     }, {
+        # redownload the page changing 'video-embed' in 'video-json'
         'url': 'https://video.gazzanet.gazzetta.it/video-embed/gazzanet-mo05-0000260789',
         'md5': 'a043e3fecbe4d9ed7fc5d888652a5440',
         'info_dict': {
@@ -359,6 +372,7 @@ class RCSIE(RCSBaseIE):
             'uploader': 'Corriere Tv',
         }
     }, {
+        # video data inside iframe
         'url': 'https://viaggi.corriere.it/video/norvegia-il-nuovo-ponte-spettacolare-sopra-la-cascata-di-voringsfossen/',
         'md5': 'da378e4918d2afbf7d61c35abb948d4c',
         'info_dict': {
@@ -389,15 +403,15 @@ class RCSVariousIE(RCSBaseIE):
                     (?P<cdn>
                         leitv\.it|
                         youreporter\.it
-                    )/(?:video/)?(?P<id>[^/]+?)(?:$|\?|/)'''
+                    )/(?:[^/]+/)?(?P<id>[^/]+?)(?:$|\?|/)'''
     _TESTS = [{
-        'url': 'https://www.leitv.it/video/marmellata-di-ciliegie-fatta-in-casa/',
-        'md5': '618aaabac32152199c1af86784d4d554',
+        'url': 'https://www.leitv.it/benessere/mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa/',
+        'md5': '92b4e63667b8f95acb0a04da25ae28a1',
         'info_dict': {
-            'id': 'marmellata-di-ciliegie-fatta-in-casa',
+            'id': 'mal-di-testa-come-combatterlo-ed-evitarne-la-comparsa',
             'ext': 'mp4',
-            'title': 'Marmellata di ciliegie fatta in casa',
-            'description': 'md5:89133864d6aad456dbcf6e7a29f86263',
+            'title': 'Cervicalgia e mal di testa, il video con i suggerimenti dell\'esperto',
+            'description': 'md5:ae21418f34cee0b8d02a487f55bcabb5',
             'uploader': 'leitv.it',
         }
     }, {

yt_dlp/extractor/rds.py

@@ -15,17 +15,17 @@ class RDSIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?rds\.ca/vid(?:[eé]|%C3%A9)os/(?:[^/]+/)*(?P<id>[^/]+)-\d+\.\d+'
 
     _TESTS = [{
-        'url': 'http://www.rds.ca/videos/football/nfl/fowler-jr-prend-la-direction-de-jacksonville-3.1132799',
+        # has two 9c9media ContentPackages, the web player selects the first ContentPackage
+        'url': 'https://www.rds.ca/videos/Hockey/NationalHockeyLeague/teams/9/forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande-3.1377606',
         'info_dict': {
-            'id': '604333',
-            'display_id': 'fowler-jr-prend-la-direction-de-jacksonville',
+            'id': '2083309',
+            'display_id': 'forum-du-5-a-7-jesperi-kotkaniemi-de-retour-de-finlande',
             'ext': 'flv',
-            'title': 'Fowler Jr. prend la direction de Jacksonville',
-            'description': 'Dante Fowler Jr. est le troisième choix du repêchage 2015 de la NFL. ',
-            'timestamp': 1430397346,
-            'upload_date': '20150430',
-            'duration': 154.354,
-            'age_limit': 0,
+            'title': 'Forum du 5 à 7 : Kotkaniemi de retour de Finlande',
+            'description': 'md5:83fa38ecc4a79b19e433433254077f25',
+            'timestamp': 1606129030,
+            'upload_date': '20201123',
+            'duration': 773.039,
         }
     }, {
         'url': 'http://www.rds.ca/vid%C3%A9os/un-voyage-positif-3.877934',

yt_dlp/extractor/rts.py

@@ -6,11 +6,12 @@ import re
 from .srgssr import SRGSSRIE
 from ..compat import compat_str
 from ..utils import (
+    determine_ext,
     int_or_none,
     parse_duration,
     parse_iso8601,
     unescapeHTML,
-    determine_ext,
+    urljoin,
 )
 
 
@@ -21,7 +22,7 @@ class RTSIE(SRGSSRIE):
     _TESTS = [
         {
             'url': 'http://www.rts.ch/archives/tv/divers/3449373-les-enfants-terribles.html',
-            'md5': 'ff7f8450a90cf58dacb64e29707b4a8e',
+            'md5': '753b877968ad8afaeddccc374d4256a5',
             'info_dict': {
                 'id': '3449373',
                 'display_id': 'les-enfants-terribles',
@@ -35,6 +36,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/emissions/passe-moi-les-jumelles/5624067-entre-ciel-et-mer.html',
@@ -63,11 +65,12 @@ class RTSIE(SRGSSRIE):
                 # m3u8 download
                 'skip_download': True,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
             'skip': 'Blocked outside Switzerland',
         },
         {
             'url': 'http://www.rts.ch/video/info/journal-continu/5745356-londres-cachee-par-un-epais-smog.html',
-            'md5': '1bae984fe7b1f78e94abc74e802ed99f',
+            'md5': '9bb06503773c07ce83d3cbd793cebb91',
             'info_dict': {
                 'id': '5745356',
                 'display_id': 'londres-cachee-par-un-epais-smog',
@@ -81,6 +84,7 @@ class RTSIE(SRGSSRIE):
                 'thumbnail': r're:^https?://.*\.image',
                 'view_count': int,
             },
+            'expected_warnings': ['Unable to download f4m manifest', 'Failed to download m3u8 information'],
         },
         {
             'url': 'http://www.rts.ch/audio/couleur3/programmes/la-belle-video-de-stephane-laurenceau/5706148-urban-hippie-de-damien-krisl-03-04-2014.html',
@@ -160,7 +164,7 @@ class RTSIE(SRGSSRIE):
         media_type = 'video' if 'video' in all_info else 'audio'
 
         # check for errors
-        self.get_media_data('rts', media_type, media_id)
+        self._get_media_data('rts', media_type, media_id)
 
         info = all_info['video']['JSONinfo'] if 'video' in all_info else all_info['audio']
 
@@ -194,6 +198,7 @@ class RTSIE(SRGSSRIE):
                     'tbr': extract_bitrate(format_url),
                 })
 
+        download_base = 'http://rtsww%s-d.rts.ch/' % ('-a' if media_type == 'audio' else '')
         for media in info.get('media', []):
             media_url = media.get('url')
             if not media_url or re.match(r'https?://', media_url):
@@ -205,7 +210,7 @@ class RTSIE(SRGSSRIE):
                 format_id += '-%dk' % rate
             formats.append({
                 'format_id': format_id,
-                'url': 'http://download-video.rts.ch/' + media_url,
+                'url': urljoin(download_base, media_url),
                 'tbr': rate or extract_bitrate(media_url),
             })
 

yt_dlp/extractor/rtve.py

@@ -2,8 +2,9 @@
 from __future__ import unicode_literals
 
 import base64
+import io
 import re
-import time
+import sys
 
 from .common import InfoExtractor
 from ..compat import (
@@ -14,56 +15,13 @@ from ..utils import (
     determine_ext,
     ExtractorError,
     float_or_none,
+    qualities,
     remove_end,
     remove_start,
-    sanitized_Request,
     std_headers,
 )
 
-
-def _decrypt_url(png):
-    encrypted_data = compat_b64decode(png)
-    text_index = encrypted_data.find(b'tEXt')
-    text_chunk = encrypted_data[text_index - 4:]
-    length = compat_struct_unpack('!I', text_chunk[:4])[0]
-    # Use bytearray to get integers when iterating in both python 2.x and 3.x
-    data = bytearray(text_chunk[8:8 + length])
-    data = [chr(b) for b in data if b != 0]
-    hash_index = data.index('#')
-    alphabet_data = data[:hash_index]
-    url_data = data[hash_index + 1:]
-    if url_data[0] == 'H' and url_data[3] == '%':
-        # remove useless HQ%% at the start
-        url_data = url_data[4:]
-
-    alphabet = []
-    e = 0
-    d = 0
-    for l in alphabet_data:
-        if d == 0:
-            alphabet.append(l)
-            d = e = (e + 1) % 4
-        else:
-            d -= 1
-    url = ''
-    f = 0
-    e = 3
-    b = 1
-    for letter in url_data:
-        if f == 0:
-            l = int(letter) * 10
-            f = 1
-        else:
-            if e == 0:
-                l += int(letter)
-                url += alphabet[l]
-                e = (b + 3) % 4
-                f = 0
-                b += 1
-            else:
-                e -= 1
-
-    return url
+_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
 
 
 class RTVEALaCartaIE(InfoExtractor):
@@ -79,28 +37,31 @@ class RTVEALaCartaIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia',
             'duration': 5024.566,
+            'series': 'Balonmano',
         },
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
     }, {
         'note': 'Live stream',
         'url': 'http://www.rtve.es/alacarta/videos/television/24h-live/1694255/',
         'info_dict': {
             'id': '1694255',
-            'ext': 'flv',
-            'title': 'TODO',
+            'ext': 'mp4',
+            'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
+            'is_live': True,
+        },
+        'params': {
+            'skip_download': 'live stream',
         },
-        'skip': 'The f4m manifest can\'t be used yet',
     }, {
         'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
-        'md5': 'e55e162379ad587e9640eda4f7353c0f',
+        'md5': 'd850f3c8731ea53952ebab489cf81cbf',
         'info_dict': {
             'id': '4236788',
             'ext': 'mp4',
-            'title': 'Servir y proteger - Capítulo 104 ',
+            'title': 'Servir y proteger - Capítulo 104',
             'duration': 3222.0,
         },
-        'params': {
-            'skip_download': True,  # requires ffmpeg
-        },
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
     }, {
         'url': 'http://www.rtve.es/m/alacarta/videos/cuentame-como-paso/cuentame-como-paso-t16-ultimo-minuto-nuestra-vida-capitulo-276/2969138/?media=tve',
         'only_matching': True,
@@ -111,58 +72,102 @@ class RTVEALaCartaIE(InfoExtractor):
 
     def _real_initialize(self):
         user_agent_b64 = base64.b64encode(std_headers['User-Agent'].encode('utf-8')).decode('utf-8')
-        manager_info = self._download_json(
+        self._manager = self._download_json(
             'http://www.rtve.es/odin/loki/' + user_agent_b64,
-            None, 'Fetching manager info')
-        self._manager = manager_info['manager']
+            None, 'Fetching manager info')['manager']
+
+    @staticmethod
+    def _decrypt_url(png):
+        encrypted_data = io.BytesIO(compat_b64decode(png)[8:])
+        while True:
+            length = compat_struct_unpack('!I', encrypted_data.read(4))[0]
+            chunk_type = encrypted_data.read(4)
+            if chunk_type == b'IEND':
+                break
+            data = encrypted_data.read(length)
+            if chunk_type == b'tEXt':
+                alphabet_data, text = data.split(b'\0')
+                quality, url_data = text.split(b'%%')
+                alphabet = []
+                e = 0
+                d = 0
+                for l in _bytes_to_chr(alphabet_data):
+                    if d == 0:
+                        alphabet.append(l)
+                        d = e = (e + 1) % 4
+                    else:
+                        d -= 1
+                url = ''
+                f = 0
+                e = 3
+                b = 1
+                for letter in _bytes_to_chr(url_data):
+                    if f == 0:
+                        l = int(letter) * 10
+                        f = 1
+                    else:
+                        if e == 0:
+                            l += int(letter)
+                            url += alphabet[l]
+                            e = (b + 3) % 4
+                            f = 0
+                            b += 1
+                        else:
+                            e -= 1
+
+                yield quality.decode(), url
+            encrypted_data.read(4)  # CRC
+
+    def _extract_png_formats(self, video_id):
+        png = self._download_webpage(
+            'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
+            video_id, 'Downloading url information', query={'q': 'v2'})
+        q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
+        formats = []
+        for quality, video_url in self._decrypt_url(png):
+            ext = determine_ext(video_url)
+            if ext == 'm3u8':
+                formats.extend(self._extract_m3u8_formats(
+                    video_url, video_id, 'mp4', 'm3u8_native',
+                    m3u8_id='hls', fatal=False))
+            elif ext == 'mpd':
+                formats.extend(self._extract_mpd_formats(
+                    video_url, video_id, 'dash', fatal=False))
+            else:
+                formats.append({
+                    'format_id': quality,
+                    'quality': q(quality),
+                    'url': video_url,
+                })
+        self._sort_formats(formats)
+        return formats
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)
         info = self._download_json(
             'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
             video_id)['page']['items'][0]
         if info['state'] == 'DESPU':
             raise ExtractorError('The video is no longer available', expected=True)
-        title = info['title']
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id)
-        png_request = sanitized_Request(png_url)
-        png_request.add_header('Referer', url)
-        png = self._download_webpage(png_request, video_id, 'Downloading url information')
-        video_url = _decrypt_url(png)
-        ext = determine_ext(video_url)
-
-        formats = []
-        if not video_url.endswith('.f4m') and ext != 'm3u8':
-            if '?' not in video_url:
-                video_url = video_url.replace('resources/', 'auth/resources/')
-            video_url = video_url.replace('.net.rtve', '.multimedia.cdn.rtve')
-
-        if ext == 'm3u8':
-            formats.extend(self._extract_m3u8_formats(
-                video_url, video_id, ext='mp4', entry_protocol='m3u8_native',
-                m3u8_id='hls', fatal=False))
-        elif ext == 'f4m':
-            formats.extend(self._extract_f4m_formats(
-                video_url, video_id, f4m_id='hds', fatal=False))
-        else:
-            formats.append({
-                'url': video_url,
-            })
-        self._sort_formats(formats)
+        title = info['title'].strip()
+        formats = self._extract_png_formats(video_id)
 
         subtitles = None
-        if info.get('sbtFile') is not None:
-            subtitles = self.extract_subtitles(video_id, info['sbtFile'])
+        sbt_file = info.get('sbtFile')
+        if sbt_file:
+            subtitles = self.extract_subtitles(video_id, sbt_file)
+
+        is_live = info.get('live') is True
 
         return {
             'id': video_id,
-            'title': title,
+            'title': self._live_title(title) if is_live else title,
             'formats': formats,
             'thumbnail': info.get('image'),
-            'page_url': url,
             'subtitles': subtitles,
-            'duration': float_or_none(info.get('duration'), scale=1000),
+            'duration': float_or_none(info.get('duration'), 1000),
+            'is_live': is_live,
+            'series': info.get('programTitle'),
         }
 
     def _get_subtitles(self, video_id, sub_file):
@@ -174,48 +179,26 @@ class RTVEALaCartaIE(InfoExtractor):
             for s in subs)
 
 
-class RTVEInfantilIE(InfoExtractor):
+class RTVEInfantilIE(RTVEALaCartaIE):
     IE_NAME = 'rtve.es:infantil'
     IE_DESC = 'RTVE infantil'
-    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/(?P<show>[^/]*)/video/(?P<short_title>[^/]*)/(?P<id>[0-9]+)/'
+    _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
 
     _TESTS = [{
         'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/',
-        'md5': '915319587b33720b8e0357caaa6617e6',
+        'md5': '5747454717aedf9f9fdf212d1bcfc48d',
         'info_dict': {
             'id': '3040283',
             'ext': 'mp4',
             'title': 'Maneras de vivir',
-            'thumbnail': 'http://www.rtve.es/resources/jpg/6/5/1426182947956.JPG',
+            'thumbnail': r're:https?://.+/1426182947956\.JPG',
             'duration': 357.958,
         },
+        'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
     }]
 
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        info = self._download_json(
-            'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id,
-            video_id)['page']['items'][0]
 
-        webpage = self._download_webpage(url, video_id)
-        vidplayer_id = self._search_regex(
-            r' id="vidplayer([0-9]+)"', webpage, 'internal video ID')
-
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/default/videos/%s.png' % vidplayer_id
-        png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        video_url = _decrypt_url(png)
-
-        return {
-            'id': video_id,
-            'ext': 'mp4',
-            'title': info['title'],
-            'url': video_url,
-            'thumbnail': info.get('image'),
-            'duration': float_or_none(info.get('duration'), scale=1000),
-        }
-
-
-class RTVELiveIE(InfoExtractor):
+class RTVELiveIE(RTVEALaCartaIE):
     IE_NAME = 'rtve.es:live'
     IE_DESC = 'RTVE.es live streams'
     _VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)'
@@ -225,7 +208,7 @@ class RTVELiveIE(InfoExtractor):
         'info_dict': {
             'id': 'la-1',
             'ext': 'mp4',
-            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2}Z[0-9]{6}$',
+            'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
         },
         'params': {
             'skip_download': 'live stream',
@@ -234,29 +217,22 @@ class RTVELiveIE(InfoExtractor):
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
-        start_time = time.gmtime()
         video_id = mobj.group('id')
 
         webpage = self._download_webpage(url, video_id)
         title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
         title = remove_start(title, 'Estoy viendo ')
-        title += ' ' + time.strftime('%Y-%m-%dZ%H%M%S', start_time)
 
         vidplayer_id = self._search_regex(
             (r'playerId=player([0-9]+)',
              r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
              r'data-id=["\'](\d+)'),
             webpage, 'internal video ID')
-        png_url = 'http://www.rtve.es/ztnr/movil/thumbnail/amonet/videos/%s.png' % vidplayer_id
-        png = self._download_webpage(png_url, video_id, 'Downloading url information')
-        m3u8_url = _decrypt_url(png)
-        formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4')
-        self._sort_formats(formats)
 
         return {
             'id': video_id,
-            'title': title,
-            'formats': formats,
+            'title': self._live_title(title),
+            'formats': self._extract_png_formats(vidplayer_id),
             'is_live': True,
         }
 

yt_dlp/extractor/sbs.py

@@ -10,7 +10,7 @@ from ..utils import (
 
 class SBSIE(InfoExtractor):
     IE_DESC = 'sbs.com.au'
-    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
+    _VALID_URL = r'https?://(?:www\.)?sbs\.com\.au/(?:ondemand(?:/video/(?:single/)?|.*?\bplay=|/watch/)|news/(?:embeds/)?video/)(?P<id>[0-9]+)'
 
     _TESTS = [{
         # Original URL is handled by the generic IE which finds the iframe:
@@ -43,6 +43,9 @@ class SBSIE(InfoExtractor):
     }, {
         'url': 'https://www.sbs.com.au/news/embeds/video/1840778819866',
         'only_matching': True,
+    }, {
+        'url': 'https://www.sbs.com.au/ondemand/watch/1698704451971',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):