[version] update

Created by: pukkandan

:ci skip all :ci run dl

.github/ISSUE_TEMPLATE/1_broken_site.yml

@@ -2,6 +2,13 @@ name: Broken site
 description: Report broken or misfunctioning site
 labels: [triage, site-bug]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
   - type: checkboxes
     id: checklist
     attributes:
@@ -11,13 +18,13 @@ body:
       options:
         - label: I'm reporting a broken site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
         - label: I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/ytdl-org/youtube-dl#video-url-contains-an-ampersand-and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -26,37 +33,45 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your issue in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+          required: true
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
+          required: true
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        Provide the complete verbose output of yt-dlp **that clearly demonstrates the problem**.
+        It should start like this:
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2022.06.29 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2022.06.29)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/2_site_support_request.yml

@@ -2,6 +2,13 @@ name: Site support request
 description: Request support for a new site
 labels: [triage, site-request]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
   - type: checkboxes
     id: checklist
     attributes:
@@ -11,13 +18,13 @@ body:
       options:
         - label: I'm reporting a new site support request
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
         - label: I've checked that none of provided URLs [violate any copyrights](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) or contain any [DRM](https://en.wikipedia.org/wiki/Digital_rights_management) to the best of my knowledge
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -26,8 +33,8 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: example-urls
     attributes:
@@ -43,31 +50,40 @@ body:
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide any additional information
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+          required: true
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
+          required: true
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        Provide the complete verbose output **using one of the example URLs provided above**.
+        It should start like this:
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2022.06.29 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2022.06.29)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/3_site_feature_request.yml

@@ -2,6 +2,13 @@ name: Site feature request
 description: Request a new functionality for a supported site
 labels: [triage, site-enhancement]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
   - type: checkboxes
     id: checklist
     attributes:
@@ -11,11 +18,11 @@ body:
       options:
         - label: I'm requesting a site-specific feature
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -24,8 +31,8 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: example-urls
     attributes:
@@ -39,33 +46,40 @@ body:
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your site feature request in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+          required: true
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
+          required: true
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        Provide the complete verbose output of yt-dlp that demonstrates the need for the enhancement.
+        It should start like this:
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2022.06.29 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2022.06.29)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/4_bug_report.yml

@@ -2,6 +2,13 @@ name: Bug report
 description: Report a bug unrelated to any particular site or extractor
 labels: [triage, bug]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
   - type: checkboxes
     id: checklist
     attributes:
@@ -11,46 +18,53 @@ body:
       options:
         - label: I'm reporting a bug unrelated to a specific site
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
         - label: I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/ytdl-org/youtube-dl#video-url-contains-an-ampersand-and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your issue in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+          required: true
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
+          required: true
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        Provide the complete verbose output of yt-dlp **that clearly demonstrates the problem**.
+        It should start like this:
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2022.06.29 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2022.06.29)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell
     validations:

.github/ISSUE_TEMPLATE/5_feature_request.yml

@@ -2,6 +2,13 @@ name: Feature request
 description: Request a new functionality unrelated to any particular site or extractor
 labels: [triage, enhancement]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
   - type: checkboxes
     id: checklist
     attributes:
@@ -13,41 +20,46 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your site feature request in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        If your feature request involves an existing yt-dlp command, provide the complete verbose output of that command.
+        It should start like this:
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2021.12.01 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2021.12.01)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell

.github/ISSUE_TEMPLATE/6_question.yml

@@ -2,6 +2,19 @@ name: Ask question
 description: Ask yt-dlp related question
 labels: [question]
 body:
+  - type: checkboxes
+    attributes:
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\* field
+          required: true
+  - type: markdown
+    attributes:
+      value: |
+        ### Make sure you are **only** asking a question and not reporting a bug or requesting a feature.
+        If your question contains "isn't working" or "can you add", this is most likely the wrong template.
+        If you are in doubt whether this is the right template, **USE ANOTHER TEMPLATE**!
   - type: checkboxes
     id: checklist
     attributes:
@@ -13,43 +26,46 @@ body:
           required: true
         - label: I've looked through the [README](https://github.com/yt-dlp/yt-dlp#readme)
           required: true
-        - label: I've verified that I'm running yt-dlp version **2022.06.29** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
+        - label: I've verified that I'm running yt-dlp version **2022.08.14** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: question
     attributes:
-      label: Question
+      label: Please make sure the question is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Ask your question in an arbitrary form.
+      placeholder: Provide any additional information and as much context and examples as possible
-        Please make sure it's worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information and as much context and examples as possible.
-        If your question contains "isn't working" or "can you add", this is most likely the wrong template.
-        If you are in doubt if this is the right template, use another template!
-      placeholder: WRITE QUESTION HERE
     validations:
       required: true
+  - type: checkboxes
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
   - type: textarea
     id: log
     attributes:
-      label: Verbose log
+      label: Complete Verbose Output
       description: |
-        If your question involves a yt-dlp command, provide the complete verbose output of that command.
+        It should start like this:
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
       placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
+        [debug] Command-line config: ['-vU', 'test:youtube']
-        [debug] Portable config file: yt-dlp.conf
+        [debug] Portable config "yt-dlp.conf": ['-i']
-        [debug] Portable config: ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
+        [debug] yt-dlp version 2022.08.14 [9d339c4] (win32_exe)
-        [debug] yt-dlp version 2021.12.01 (exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
+        [debug] Checking exe version: ffprobe -bsfs
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
         [debug] Proxy map: {}
-        yt-dlp is up to date (2021.12.01)
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: 2022.08.14, Current version: 2022.08.14
+        yt-dlp is up to date (2022.08.14)
         <more lines>
       render: shell

.github/ISSUE_TEMPLATE_tmpl/1_broken_site.yml

@@ -2,6 +2,7 @@ name: Broken site
 description: Report broken or misfunctioning site
 labels: [triage, site-bug]
 body:
+  %(no_skip)s
   - type: checkboxes
     id: checklist
     attributes:
@@ -17,7 +18,7 @@ body:
           required: true
         - label: I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/ytdl-org/youtube-dl#video-url-contains-an-ampersand-and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -26,38 +27,14 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your issue in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
-    validations:
-      required: true
-  - type: textarea
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        Provide the complete verbose output of yt-dlp **that clearly demonstrates the problem**.
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version %(version)s (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (%(version)s)
-        <more lines>
-      render: shell
     validations:
       required: true
+  %(verbose)s

.github/ISSUE_TEMPLATE_tmpl/2_site_support_request.yml

@@ -2,6 +2,7 @@ name: Site support request
 description: Request support for a new site
 labels: [triage, site-request]
 body:
+  %(no_skip)s
   - type: checkboxes
     id: checklist
     attributes:
@@ -17,7 +18,7 @@ body:
           required: true
         - label: I've checked that none of provided URLs [violate any copyrights](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) or contain any [DRM](https://en.wikipedia.org/wiki/Digital_rights_management) to the best of my knowledge
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -26,8 +27,8 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: example-urls
     attributes:
@@ -43,32 +44,9 @@ body:
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide any additional information
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
-    validations:
-      required: true
-  - type: textarea
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        Provide the complete verbose output **using one of the example URLs provided above**.
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version %(version)s (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (%(version)s)
-        <more lines>
-      render: shell
     validations:
       required: true
+  %(verbose)s

.github/ISSUE_TEMPLATE_tmpl/3_site_feature_request.yml

@@ -2,6 +2,7 @@ name: Site feature request
 description: Request a new functionality for a supported site
 labels: [triage, site-enhancement]
 body:
+  %(no_skip)s
   - type: checkboxes
     id: checklist
     attributes:
@@ -15,7 +16,7 @@ body:
           required: true
         - label: I've checked that all provided URLs are playable in a browser with the same IP and same login details
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
@@ -24,8 +25,8 @@ body:
     id: region
     attributes:
       label: Region
-      description: "Enter the region the site is accessible from"
+      description: Enter the country/region that the site is accessible from
-      placeholder: "India"
+      placeholder: India
   - type: textarea
     id: example-urls
     attributes:
@@ -39,34 +40,9 @@ body:
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your site feature request in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
-    validations:
-      required: true
-  - type: textarea
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        Provide the complete verbose output of yt-dlp that demonstrates the need for the enhancement.
-        Add the `-vU` flag to your command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version %(version)s (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (%(version)s)
-        <more lines>
-      render: shell
     validations:
       required: true
+  %(verbose)s

.github/ISSUE_TEMPLATE_tmpl/4_bug_report.yml

@@ -2,6 +2,7 @@ name: Bug report
 description: Report a bug unrelated to any particular site or extractor
 labels: [triage, bug]
 body:
+  %(no_skip)s
   - type: checkboxes
     id: checklist
     attributes:
@@ -17,41 +18,16 @@ body:
           required: true
         - label: I've checked that all URLs and arguments with special characters are [properly quoted or escaped](https://github.com/ytdl-org/youtube-dl#video-url-contains-an-ampersand-and-im-getting-some-strange-output-1-2839-or-v-is-not-recognized-as-an-internal-or-external-command)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your issue in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
-    validations:
-      required: true
-  - type: textarea
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        Provide the complete verbose output of yt-dlp **that clearly demonstrates the problem**.
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version %(version)s (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (%(version)s)
-        <more lines>
-      render: shell
     validations:
       required: true
+  %(verbose)s

.github/ISSUE_TEMPLATE_tmpl/5_feature_request.yml

@@ -2,6 +2,7 @@ name: Feature request
 description: Request a new functionality unrelated to any particular site or extractor
 labels: [triage, enhancement]
 body:
+  %(no_skip)s
   - type: checkboxes
     id: checklist
     attributes:
@@ -15,39 +16,16 @@ body:
           required: true
         - label: I've verified that I'm running yt-dlp version **%(version)s** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar issues **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: description
     attributes:
-      label: Description
+      label: Provide a description that is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Provide an explanation of your site feature request in an arbitrary form.
+      placeholder: Provide any additional information, any suggested solutions, and as much context and examples as possible
-        Please make sure the description is worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information, any suggested solutions, and as much context and examples as possible
-      placeholder: WRITE DESCRIPTION HERE
     validations:
       required: true
-  - type: textarea
+  %(verbose_optional)s
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        If your feature request involves an existing yt-dlp command, provide the complete verbose output of that command.
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version 2021.12.01 (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (2021.12.01)
-        <more lines>
-      render: shell

.github/ISSUE_TEMPLATE_tmpl/6_question.yml

@@ -2,6 +2,13 @@ name: Ask question
 description: Ask yt-dlp related question
 labels: [question]
 body:
+  %(no_skip)s
+  - type: markdown
+    attributes:
+      value: |
+        ### Make sure you are **only** asking a question and not reporting a bug or requesting a feature.
+        If your question contains "isn't working" or "can you add", this is most likely the wrong template.
+        If you are in doubt whether this is the right template, **USE ANOTHER TEMPLATE**!
   - type: checkboxes
     id: checklist
     attributes:
@@ -15,41 +22,16 @@ body:
           required: true
         - label: I've verified that I'm running yt-dlp version **%(version)s** ([update instructions](https://github.com/yt-dlp/yt-dlp#update)) or later (specify commit)
           required: true
-        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions including closed ones. DO NOT post duplicates
+        - label: I've searched the [bugtracker](https://github.com/yt-dlp/yt-dlp/issues?q=) for similar questions **including closed ones**. DO NOT post duplicates
           required: true
         - label: I've read the [guidelines for opening an issue](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#opening-an-issue)
           required: true
   - type: textarea
     id: question
     attributes:
-      label: Question
+      label: Please make sure the question is worded well enough to be understood
-      description: |
+      description: See [is-the-description-of-the-issue-itself-sufficient](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-description-of-the-issue-itself-sufficient)
-        Ask your question in an arbitrary form.
+      placeholder: Provide any additional information and as much context and examples as possible
-        Please make sure it's worded well enough to be understood, see [is-the-description-of-the-issue-itself-sufficient](https://github.com/ytdl-org/youtube-dl#is-the-description-of-the-issue-itself-sufficient).
-        Provide any additional information and as much context and examples as possible.
-        If your question contains "isn't working" or "can you add", this is most likely the wrong template.
-        If you are in doubt if this is the right template, use another template!
-      placeholder: WRITE QUESTION HERE
     validations:
       required: true
-  - type: textarea
+  %(verbose_optional)s
-    id: log
-    attributes:
-      label: Verbose log
-      description: |
-        If your question involves a yt-dlp command, provide the complete verbose output of that command.
-        Add the `-vU` flag to **your** command line you run yt-dlp with (`yt-dlp -vU <your command line>`), copy the WHOLE output and insert it below.
-        It should look similar to this:
-      placeholder: |
-        [debug] Command-line config: ['-vU', 'http://www.youtube.com/watch?v=BaW_jenozKc']
-        [debug] Portable config file: yt-dlp.conf
-        [debug] Portable config: ['-i']
-        [debug] Encodings: locale cp1252, fs utf-8, stdout utf-8, stderr utf-8, pref cp1252
-        [debug] yt-dlp version 2021.12.01 (exe)
-        [debug] Python version 3.8.8 (CPython 64bit) - Windows-10-10.0.19041-SP0
-        [debug] exe versions: ffmpeg 3.0.1, ffprobe 3.0.1
-        [debug] Optional libraries: Cryptodome, keyring, mutagen, sqlite, websockets
-        [debug] Proxy map: {}
-        yt-dlp is up to date (2021.12.01)
-        <more lines>
-      render: shell

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,5 +1,25 @@
+**IMPORTANT**: PRs without the template will be CLOSED
+
+### Description of your *pull request* and other information
+
+</details>
+
 <!--
-# Please follow the guide below
+
+Explanation of your *pull request* in arbitrary form goes here. Please **make sure the description explains the purpose and effect** of your *pull request* and is worded well enough to be understood. Provide as much **context and examples** as possible
+
+-->
+
+ADD DESCRIPTION HERE
+
+Fixes #
+
+
+<details open><summary>Template</summary> <!-- OPEN is intentional -->
+
+<!--
+
+# PLEASE FOLLOW THE GUIDE BELOW
 
 - You will be asked some questions, please read them **carefully** and answer honestly
 - Put an `x` into all the boxes `[ ]` relevant to your *pull request* (like [x])
@@ -21,9 +41,3 @@
 - [ ] New extractor ([Piracy websites will not be accepted](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#is-the-website-primarily-used-for-piracy))
 - [ ] Core bug fix/improvement
 - [ ] New feature (It is strongly [recommended to open an issue first](https://github.com/yt-dlp/yt-dlp/blob/master/CONTRIBUTING.md#adding-new-feature-or-making-overarching-changes))
-
----
-
-### Description of your *pull request* and other information
-
-Explanation of your *pull request* in arbitrary form goes here. Please **make sure the description explains the purpose and effect** of your *pull request* and is worded well enough to be understood. Provide as much **context and examples** as possible.

.github/workflows/build.yml

@@ -2,18 +2,17 @@ name: Build
 on: workflow_dispatch
 
 jobs:
-  create_release:
+  prepare:
     runs-on: ubuntu-latest
     outputs:
       version_suffix: ${{ steps.version_suffix.outputs.version_suffix }}
       ytdlp_version: ${{ steps.bump_version.outputs.ytdlp_version }}
-      upload_url: ${{ steps.create_release.outputs.upload_url }}
+      head_sha: ${{ steps.push_release.outputs.head_sha }}
-      release_id: ${{ steps.create_release.outputs.id }}
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
       with:
         fetch-depth: 0
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@v4
       with:
           python-version: '3.10'
 
@@ -43,53 +42,15 @@ jobs:
         PUSH_VERSION_COMMIT: ${{ secrets.PUSH_VERSION_COMMIT }}
       if: "env.PUSH_VERSION_COMMIT != ''"
       run: git push origin ${{ github.event.ref }}
-    - name: Get Changelog
-      run: |
-        changelog=$(grep -oPz '(?s)(?<=### ${{ steps.bump_version.outputs.ytdlp_version }}\n{2}).+?(?=\n{2,3}###)' Changelog.md) || true
-        echo "changelog<<EOF" >> $GITHUB_ENV
-        echo "$changelog" >> $GITHUB_ENV
-        echo "EOF" >> $GITHUB_ENV
-
-    - name: Create Release
-      id: create_release
-      uses: actions/create-release@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        tag_name: ${{ steps.bump_version.outputs.ytdlp_version }}
-        release_name: yt-dlp ${{ steps.bump_version.outputs.ytdlp_version }}
-        commitish: ${{ steps.push_release.outputs.head_sha }}
-        draft: true
-        prerelease: false
-        body: |
-          #### [A description of the various files]((https://github.com/yt-dlp/yt-dlp#release-files)) are in the README
-
-          ---
-          <details open><summary><h3>Changelog</summary>
-          <p>
-
-          ${{ env.changelog }}
-
-          </p>
-          </details>
 
 
   build_unix:
-    needs: create_release
+    needs: prepare
     runs-on: ubuntu-18.04  # Standalone executable should be built on minimum supported OS
-    outputs:
-      sha256_bin: ${{ steps.get_sha.outputs.sha256_bin }}
-      sha512_bin: ${{ steps.get_sha.outputs.sha512_bin }}
-      sha256_tar: ${{ steps.get_sha.outputs.sha256_tar }}
-      sha512_tar: ${{ steps.get_sha.outputs.sha512_tar }}
-      sha256_linux: ${{ steps.get_sha.outputs.sha256_linux }}
-      sha512_linux: ${{ steps.get_sha.outputs.sha512_linux }}
-      sha256_linux_zip: ${{ steps.get_sha.outputs.sha256_linux_zip }}
-      sha512_linux_zip: ${{ steps.get_sha.outputs.sha512_linux_zip }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@v4
       with:
           python-version: '3.10'
     - name: Install Requirements
@@ -100,7 +61,7 @@ jobs:
 
     - name: Prepare
       run: |
-          python devscripts/update-version.py ${{ needs.create_release.outputs.version_suffix }}
+          python devscripts/update-version.py ${{ needs.prepare.outputs.version_suffix }}
           python devscripts/make_lazy_extractors.py
     - name: Build Unix executables
       run: |
@@ -111,51 +72,15 @@ jobs:
     - name: Get SHA2-SUMS
       id: get_sha
       run: |
-          echo "::set-output name=sha256_bin::$(sha256sum yt-dlp | awk '{print $1}')"
-          echo "::set-output name=sha512_bin::$(sha512sum yt-dlp | awk '{print $1}')"
-          echo "::set-output name=sha256_tar::$(sha256sum yt-dlp.tar.gz | awk '{print $1}')"
-          echo "::set-output name=sha512_tar::$(sha512sum yt-dlp.tar.gz | awk '{print $1}')"
-          echo "::set-output name=sha256_linux::$(sha256sum dist/yt-dlp_linux | awk '{print $1}')"
-          echo "::set-output name=sha512_linux::$(sha512sum dist/yt-dlp_linux | awk '{print $1}')"
-          echo "::set-output name=sha256_linux_zip::$(sha256sum dist/yt-dlp_linux.zip | awk '{print $1}')"
-          echo "::set-output name=sha512_linux_zip::$(sha512sum dist/yt-dlp_linux.zip | awk '{print $1}')"
 
-    - name: Upload zip binary
+    - name: Upload artifacts
-      uses: actions/upload-release-asset@v1
+      uses: actions/upload-artifact@v3
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
+        path: |
-        asset_path: ./yt-dlp
+          yt-dlp
-        asset_name: yt-dlp
+          yt-dlp.tar.gz
-        asset_content_type: application/octet-stream
+          dist/yt-dlp_linux
-    - name: Upload Source tar
+          dist/yt-dlp_linux.zip
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./yt-dlp.tar.gz
-        asset_name: yt-dlp.tar.gz
-        asset_content_type: application/gzip
-    - name: Upload standalone binary
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./dist/yt-dlp_linux
-        asset_name: yt-dlp_linux
-        asset_content_type: application/octet-stream
-    - name: Upload onedir binary
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./dist/yt-dlp_linux.zip
-        asset_name: yt-dlp_linux.zip
-        asset_content_type: application/zip
 
     - name: Build and publish on PyPi
       env:
@@ -164,6 +89,7 @@ jobs:
       if: "env.TWINE_PASSWORD != ''"
       run: |
         rm -rf dist/*
+        python devscripts/set-variant.py pip -M "You installed yt-dlp with pip or using the wheel from PyPi; Use that to update"
         python setup.py sdist bdist_wheel
         twine upload dist/*
 
@@ -180,24 +106,19 @@ jobs:
       if: "env.BREW_TOKEN != ''"
       run: |
         git clone git@github.com:yt-dlp/homebrew-taps taps/
-        python devscripts/update-formulae.py taps/Formula/yt-dlp.rb "${{ needs.create_release.outputs.ytdlp_version }}"
+        python devscripts/update-formulae.py taps/Formula/yt-dlp.rb "${{ needs.prepare.outputs.ytdlp_version }}"
         git -C taps/ config user.name github-actions
         git -C taps/ config user.email github-actions@example.com
-        git -C taps/ commit -am 'yt-dlp: ${{ needs.create_release.outputs.ytdlp_version }}'
+        git -C taps/ commit -am 'yt-dlp: ${{ needs.prepare.outputs.ytdlp_version }}'
         git -C taps/ push
 
 
   build_macos:
     runs-on: macos-11
-    needs: create_release
+    needs: prepare
-    outputs:
-      sha256_macos: ${{ steps.get_sha.outputs.sha256_macos }}
-      sha512_macos: ${{ steps.get_sha.outputs.sha512_macos }}
-      sha256_macos_zip: ${{ steps.get_sha.outputs.sha256_macos_zip }}
-      sha512_macos_zip: ${{ steps.get_sha.outputs.sha512_macos_zip }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     # NB: In order to create a universal2 application, the version of python3 in /usr/bin has to be used
     - name: Install Requirements
       run: |
@@ -206,46 +127,28 @@ jobs:
 
     - name: Prepare
       run: |
-          /usr/bin/python3 devscripts/update-version.py ${{ needs.create_release.outputs.version_suffix }}
+          /usr/bin/python3 devscripts/update-version.py ${{ needs.prepare.outputs.version_suffix }}
           /usr/bin/python3 devscripts/make_lazy_extractors.py
     - name: Build
       run: |
           /usr/bin/python3 pyinst.py --target-architecture universal2 --onedir
           (cd ./dist/yt-dlp_macos && zip -r ../yt-dlp_macos.zip .)
           /usr/bin/python3 pyinst.py --target-architecture universal2
-    - name: Get SHA2-SUMS
-      id: get_sha
-      run: |
-          echo "::set-output name=sha256_macos::$(sha256sum dist/yt-dlp_macos | awk '{print $1}')"
-          echo "::set-output name=sha512_macos::$(sha512sum dist/yt-dlp_macos | awk '{print $1}')"
-          echo "::set-output name=sha256_macos_zip::$(sha256sum dist/yt-dlp_macos.zip | awk '{print $1}')"
-          echo "::set-output name=sha512_macos_zip::$(sha512sum dist/yt-dlp_macos.zip | awk '{print $1}')"
 
-    - name: Upload standalone binary
+    - name: Upload artifacts
-      uses: actions/upload-release-asset@v1
+      uses: actions/upload-artifact@v3
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
+        path: |
-        asset_path: ./dist/yt-dlp_macos
+          dist/yt-dlp_macos
-        asset_name: yt-dlp_macos
+          dist/yt-dlp_macos.zip
-        asset_content_type: application/octet-stream
-    - name: Upload onedir binary
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./dist/yt-dlp_macos.zip
-        asset_name: yt-dlp_macos.zip
-        asset_content_type: application/zip
 
 
   build_macos_legacy:
     runs-on: macos-latest
-    needs: create_release
+    needs: prepare
+
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Install Python
       # We need the official Python, because the GA ones only support newer macOS versions
       env:
@@ -265,52 +168,37 @@ jobs:
 
     - name: Prepare
       run: |
-          python3 devscripts/update-version.py ${{ needs.create_release.outputs.version_suffix }}
+          python3 devscripts/update-version.py ${{ needs.prepare.outputs.version_suffix }}
           python3 devscripts/make_lazy_extractors.py
     - name: Build
       run: |
           python3 pyinst.py
-    - name: Get SHA2-SUMS
+          mv dist/yt-dlp_macos dist/yt-dlp_macos_legacy
-      id: get_sha
-      run: |
-          echo "::set-output name=sha256_macos_legacy::$(sha256sum dist/yt-dlp_macos | awk '{print $1}')"
-          echo "::set-output name=sha512_macos_legacy::$(sha512sum dist/yt-dlp_macos | awk '{print $1}')"
 
-    - name: Upload standalone binary
+    - name: Upload artifacts
-      uses: actions/upload-release-asset@v1
+      uses: actions/upload-artifact@v3
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
+        path: |
-        asset_path: ./dist/yt-dlp_macos
+          dist/yt-dlp_macos_legacy
-        asset_name: yt-dlp_macos_legacy
-        asset_content_type: application/octet-stream
 
 
   build_windows:
     runs-on: windows-latest
-    needs: create_release
+    needs: prepare
-    outputs:
-      sha256_win: ${{ steps.get_sha.outputs.sha256_win }}
-      sha512_win: ${{ steps.get_sha.outputs.sha512_win }}
-      sha256_py2exe: ${{ steps.get_sha.outputs.sha256_py2exe }}
-      sha512_py2exe: ${{ steps.get_sha.outputs.sha512_py2exe }}
-      sha256_win_zip: ${{ steps.get_sha.outputs.sha256_win_zip }}
-      sha512_win_zip: ${{ steps.get_sha.outputs.sha512_win_zip }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@v4
       with:  # 3.8 is used for Win7 support
           python-version: '3.8'
     - name: Install Requirements
       run: |  # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python -m pip install --upgrade pip setuptools wheel py2exe
-          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-4.10-py3-none-any.whl" -r requirements.txt
+          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-5.2-py3-none-any.whl" -r requirements.txt
 
     - name: Prepare
       run: |
-          python devscripts/update-version.py ${{ needs.create_release.outputs.version_suffix }}
+          python devscripts/update-version.py ${{ needs.prepare.outputs.version_suffix }}
           python devscripts/make_lazy_extractors.py
     - name: Build
       run: |
@@ -319,153 +207,118 @@ jobs:
           python pyinst.py
           python pyinst.py --onedir
           Compress-Archive -Path ./dist/yt-dlp/* -DestinationPath ./dist/yt-dlp_win.zip
-    - name: Get SHA2-SUMS
-      id: get_sha
-      run: |
-          echo "::set-output name=sha256_py2exe::$((Get-FileHash dist\yt-dlp_min.exe -Algorithm SHA256).Hash.ToLower())"
-          echo "::set-output name=sha512_py2exe::$((Get-FileHash dist\yt-dlp_min.exe -Algorithm SHA512).Hash.ToLower())"
-          echo "::set-output name=sha256_win::$((Get-FileHash dist\yt-dlp.exe -Algorithm SHA256).Hash.ToLower())"
-          echo "::set-output name=sha512_win::$((Get-FileHash dist\yt-dlp.exe -Algorithm SHA512).Hash.ToLower())"
-          echo "::set-output name=sha256_win_zip::$((Get-FileHash dist\yt-dlp_win.zip -Algorithm SHA256).Hash.ToLower())"
-          echo "::set-output name=sha512_win_zip::$((Get-FileHash dist\yt-dlp_win.zip -Algorithm SHA512).Hash.ToLower())"
 
-    - name: Upload py2exe binary
+    - name: Upload artifacts
-      uses: actions/upload-release-asset@v1
+      uses: actions/upload-artifact@v3
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
+        path: |
-        asset_path: ./dist/yt-dlp_min.exe
+          dist/yt-dlp.exe
-        asset_name: yt-dlp_min.exe
+          dist/yt-dlp_min.exe
-        asset_content_type: application/vnd.microsoft.portable-executable
+          dist/yt-dlp_win.zip
-    - name: Upload standalone binary
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./dist/yt-dlp.exe
-        asset_name: yt-dlp.exe
-        asset_content_type: application/vnd.microsoft.portable-executable
-    - name: Upload onedir binary
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./dist/yt-dlp_win.zip
-        asset_name: yt-dlp_win.zip
-        asset_content_type: application/zip
 
 
   build_windows32:
     runs-on: windows-latest
-    needs: create_release
+    needs: prepare
-    outputs:
-      sha256_win32: ${{ steps.get_sha.outputs.sha256_win32 }}
-      sha512_win32: ${{ steps.get_sha.outputs.sha512_win32 }}
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
-    - uses: actions/setup-python@v2
+    - uses: actions/setup-python@v4
       with:  # 3.7 is used for Vista support. See https://github.com/yt-dlp/yt-dlp/issues/390
           python-version: '3.7'
           architecture: 'x86'
     - name: Install Requirements
       run: |
           python -m pip install --upgrade pip setuptools wheel
-          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-4.10-py3-none-any.whl" -r requirements.txt
+          pip install "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-5.2-py3-none-any.whl" -r requirements.txt
 
     - name: Prepare
       run: |
-          python devscripts/update-version.py ${{ needs.create_release.outputs.version_suffix }}
+          python devscripts/update-version.py ${{ needs.prepare.outputs.version_suffix }}
           python devscripts/make_lazy_extractors.py
     - name: Build
       run: |
           python pyinst.py
-    - name: Get SHA2-SUMS
-      id: get_sha
-      run: |
-          echo "::set-output name=sha256_win32::$((Get-FileHash dist\yt-dlp_x86.exe -Algorithm SHA256).Hash.ToLower())"
-          echo "::set-output name=sha512_win32::$((Get-FileHash dist\yt-dlp_x86.exe -Algorithm SHA512).Hash.ToLower())"
 
-    - name: Upload standalone binary
+    - name: Upload artifacts
-      uses: actions/upload-release-asset@v1
+      uses: actions/upload-artifact@v3
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
+        path: |
-        asset_path: ./dist/yt-dlp_x86.exe
+          dist/yt-dlp_x86.exe
-        asset_name: yt-dlp_x86.exe
-        asset_content_type: application/vnd.microsoft.portable-executable
 
 
-  finish:
+  publish_release:
     runs-on: ubuntu-latest
-    needs: [create_release, build_unix, build_windows, build_windows32, build_macos, build_macos_legacy]
+    needs: [prepare, build_unix, build_windows, build_windows32, build_macos, build_macos_legacy]
 
     steps:
-    - name: Make SHA2-SUMS files
+    - uses: actions/checkout@v3
+    - uses: actions/download-artifact@v3
+
+    - name: Get Changelog
       run: |
-        echo "${{ needs.build_unix.outputs.sha256_bin }}  yt-dlp" >> SHA2-256SUMS
+        changelog=$(grep -oPz '(?s)(?<=### ${{ needs.prepare.outputs.ytdlp_version }}\n{2}).+?(?=\n{2,3}###)' Changelog.md) || true
-        echo "${{ needs.build_unix.outputs.sha256_tar }}  yt-dlp.tar.gz" >> SHA2-256SUMS
+        echo "changelog<<EOF" >> $GITHUB_ENV
-        echo "${{ needs.build_unix.outputs.sha256_linux }}  yt-dlp_linux" >> SHA2-256SUMS
+        echo "$changelog" >> $GITHUB_ENV
-        echo "${{ needs.build_unix.outputs.sha256_linux_zip }}  yt-dlp_linux.zip" >> SHA2-256SUMS
+        echo "EOF" >> $GITHUB_ENV
-        echo "${{ needs.build_windows.outputs.sha256_win }}  yt-dlp.exe" >> SHA2-256SUMS
-        echo "${{ needs.build_windows.outputs.sha256_py2exe }}  yt-dlp_min.exe" >> SHA2-256SUMS
-        echo "${{ needs.build_windows32.outputs.sha256_win32 }}  yt-dlp_x86.exe" >> SHA2-256SUMS
-        echo "${{ needs.build_windows.outputs.sha256_win_zip }}  yt-dlp_win.zip" >> SHA2-256SUMS
-        echo "${{ needs.build_macos.outputs.sha256_macos }}  yt-dlp_macos" >> SHA2-256SUMS
-        echo "${{ needs.build_macos.outputs.sha256_macos_zip }}  yt-dlp_macos.zip" >> SHA2-256SUMS
-        echo "${{ needs.build_macos_legacy.outputs.sha256_macos_legacy }}  yt-dlp_macos_legacy" >> SHA2-256SUMS
-        echo "${{ needs.build_unix.outputs.sha512_bin }}  yt-dlp" >> SHA2-512SUMS
-        echo "${{ needs.build_unix.outputs.sha512_tar }}  yt-dlp.tar.gz" >> SHA2-512SUMS
-        echo "${{ needs.build_unix.outputs.sha512_linux }}  yt-dlp_linux" >> SHA2-512SUMS
-        echo "${{ needs.build_unix.outputs.sha512_linux_zip }}  yt-dlp_linux.zip" >> SHA2-512SUMS
-        echo "${{ needs.build_windows.outputs.sha512_win }}  yt-dlp.exe" >> SHA2-512SUMS
-        echo "${{ needs.build_windows.outputs.sha512_py2exe }}  yt-dlp_min.exe" >> SHA2-512SUMS
-        echo "${{ needs.build_windows32.outputs.sha512_win32 }}  yt-dlp_x86.exe" >> SHA2-512SUMS
-        echo "${{ needs.build_windows.outputs.sha512_win_zip }}  yt-dlp_win.zip" >> SHA2-512SUMS
-        echo "${{ needs.build_macos.outputs.sha512_macos }}  yt-dlp_macos" >> SHA2-512SUMS
-        echo "${{ needs.build_macos.outputs.sha512_macos_zip }}  yt-dlp_macos.zip" >> SHA2-512SUMS
-        echo "${{ needs.build_macos_legacy.outputs.sha512_macos_legacy }}  yt-dlp_macos_legacy" >> SHA2-512SUMS
-
-    - name: Upload SHA2-256SUMS file
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./SHA2-256SUMS
-        asset_name: SHA2-256SUMS
-        asset_content_type: text/plain
-    - name: Upload SHA2-512SUMS file
-      uses: actions/upload-release-asset@v1
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./SHA2-512SUMS
-        asset_name: SHA2-512SUMS
-        asset_content_type: text/plain
-
     - name: Make Update spec
       run: |
         echo "# This file is used for regulating self-update" >> _update_spec
-    - name: Upload update spec
+        echo "lock 2022.07.18 .+ Python 3.6" >> _update_spec
-      uses: actions/upload-release-asset@v1
+    - name: Make SHA2-SUMS files
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      with:
-        upload_url: ${{ needs.create_release.outputs.upload_url }}
-        asset_path: ./_update_spec
-        asset_name: _update_spec
-        asset_content_type: text/plain
-
-    - name: Finalize release
-      env:
-        GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
       run: |
-        gh api -X PATCH -H "Accept: application/vnd.github.v3+json" \
+          sha256sum artifact/yt-dlp | awk '{print $1 "  yt-dlp"}' >> SHA2-256SUMS
-          /repos/${{ github.repository }}/releases/${{ needs.create_release.outputs.release_id }} \
+          sha256sum artifact/yt-dlp.tar.gz | awk '{print $1 "  yt-dlp.tar.gz"}' >> SHA2-256SUMS
-          -F draft=false
+          sha256sum artifact/yt-dlp.exe | awk '{print $1 "  yt-dlp.exe"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_win.zip | awk '{print $1 "  yt-dlp_win.zip"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_min.exe | awk '{print $1 "  yt-dlp_min.exe"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_x86.exe | awk '{print $1 "  yt-dlp_x86.exe"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_macos | awk '{print $1 "  yt-dlp_macos"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_macos.zip | awk '{print $1 "  yt-dlp_macos.zip"}' >> SHA2-256SUMS
+          sha256sum artifact/yt-dlp_macos_legacy | awk '{print $1 "  yt-dlp_macos_legacy"}' >> SHA2-256SUMS
+          sha256sum artifact/dist/yt-dlp_linux | awk '{print $1 "  yt-dlp_linux"}' >> SHA2-256SUMS
+          sha256sum artifact/dist/yt-dlp_linux.zip | awk '{print $1 "  yt-dlp_linux.zip"}' >> SHA2-256SUMS
+          sha512sum artifact/yt-dlp | awk '{print $1 "  yt-dlp"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp.tar.gz | awk '{print $1 "  yt-dlp.tar.gz"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp.exe | awk '{print $1 "  yt-dlp.exe"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_win.zip | awk '{print $1 "  yt-dlp_win.zip"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_min.exe | awk '{print $1 "  yt-dlp_min.exe"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_x86.exe | awk '{print $1 "  yt-dlp_x86.exe"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_macos | awk '{print $1 "  yt-dlp_macos"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_macos.zip | awk '{print $1 "  yt-dlp_macos.zip"}' >> SHA2-512SUMS
+          sha512sum artifact/yt-dlp_macos_legacy | awk '{print $1 "  yt-dlp_macos_legacy"}' >> SHA2-512SUMS
+          sha512sum artifact/dist/yt-dlp_linux | awk '{print $1 "  yt-dlp_linux"}' >> SHA2-512SUMS
+          sha512sum artifact/dist/yt-dlp_linux.zip | awk '{print $1 "  yt-dlp_linux.zip"}' >> SHA2-512SUMS
+
+    - name: Publish Release
+      uses: yt-dlp/action-gh-release@v1
+      with:
+        tag_name: ${{ needs.prepare.outputs.ytdlp_version }}
+        name: yt-dlp ${{ needs.prepare.outputs.ytdlp_version }}
+        target_commitish: ${{ needs.prepare.outputs.head_sha }}
+        body: |
+          #### [A description of the various files]((https://github.com/yt-dlp/yt-dlp#release-files)) are in the README
+
+          ---
+          <details open><summary><h3>Changelog</summary>
+          <p>
+
+          ${{ env.changelog }}
+
+          </p>
+          </details>
+        files: |
+          SHA2-256SUMS
+          SHA2-512SUMS
+          artifact/yt-dlp
+          artifact/yt-dlp.tar.gz
+          artifact/yt-dlp.exe
+          artifact/yt-dlp_win.zip
+          artifact/yt-dlp_min.exe
+          artifact/yt-dlp_x86.exe
+          artifact/yt-dlp_macos
+          artifact/yt-dlp_macos.zip
+          artifact/yt-dlp_macos_legacy
+          artifact/dist/yt-dlp_linux
+          artifact/dist/yt-dlp_linux.zip
+          _update_spec

.github/workflows/core.yml

@@ -10,7 +10,7 @@ jobs:
       matrix:
         os: [ubuntu-latest]
         # CPython 3.9 is in quick-test
-        python-version: ['3.6', '3.7', '3.10', 3.11-dev, pypy-3.6, pypy-3.7, pypy-3.8]
+        python-version: ['3.7', '3.10', 3.11-dev, pypy-3.7, pypy-3.8]
         run-tests-ext: [sh]
         include:
         # atleast one of each CPython/PyPy tests must be in windows
@@ -21,9 +21,9 @@ jobs:
           python-version: pypy-3.9
           run-tests-ext: bat
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install pytest

.github/workflows/download.yml

@@ -1,15 +1,31 @@
 name: Download Tests
 on: [push, pull_request]
 jobs:
-  tests:
+  quick:
-    name: Download Tests
+    name: Quick Download Tests
     if: "contains(github.event.head_commit.message, 'ci run dl')"
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v4
+      with:
+        python-version: 3.9
+    - name: Install test requirements
+      run: pip install pytest
+    - name: Run tests
+      continue-on-error: true
+      run: ./devscripts/run_tests.sh download
+
+  full:
+    name: Full Download Tests
+    if: "contains(github.event.head_commit.message, 'ci run dl all')"
     runs-on: ${{ matrix.os }}
     strategy:
       fail-fast: true
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.6', '3.7', '3.9', '3.10', 3.11-dev, pypy-3.6, pypy-3.7, pypy-3.8]
+        python-version: ['3.7', '3.10', 3.11-dev, pypy-3.7, pypy-3.8]
         run-tests-ext: [sh]
         include:
         # atleast one of each CPython/PyPy tests must be in windows
@@ -20,9 +36,9 @@ jobs:
           python-version: pypy-3.9
           run-tests-ext: bat
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install pytest

.github/workflows/quick-test.yml

@@ -6,9 +6,9 @@ jobs:
     if: "!contains(github.event.head_commit.message, 'ci skip all')"
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.9
     - name: Install test requirements
@@ -20,9 +20,9 @@ jobs:
     if: "!contains(github.event.head_commit.message, 'ci skip all')"
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Set up Python
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: 3.9
     - name: Install flake8

.gitignore

@@ -27,11 +27,13 @@ cookies
 *.ass
 *.avi
 *.desktop
+*.f4v
 *.flac
 *.flv
 *.jpeg
 *.jpg
 *.m4a
+*.mpga
 *.m4v
 *.mhtml
 *.mkv

CONTRIBUTING.md

@@ -195,7 +195,7 @@ After you have ensured this site is distributing its content legally, you can fo
                 # * A value
                 # * MD5 checksum; start the string with md5:
                 # * A regular expression; start the string with re:
-                # * Any Python type (for example int or float)
+                # * Any Python type, e.g. int or float
             }
         }]
 
@@ -222,7 +222,7 @@ After you have ensured this site is distributing its content legally, you can fo
 
         $ flake8 yt_dlp/extractor/yourextractor.py
 
-1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython and PyPy for Python 3.6 and above. Backward compatibility is not required for even older versions of Python.
+1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython and PyPy for Python 3.7 and above. Backward compatibility is not required for even older versions of Python.
 1. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files, [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
 
         $ git add yt_dlp/extractor/_extractors.py
@@ -261,7 +261,7 @@ The aforementioned metafields are the critical data that the extraction does not
 
 For pornographic sites, appropriate `age_limit` must also be returned.
 
-The extractor is allowed to return the info dict without url or formats in some special cases if it allows the user to extract usefull information with `--ignore-no-formats-error` - Eg: when the video is a live stream that has not started yet.
+The extractor is allowed to return the info dict without url or formats in some special cases if it allows the user to extract usefull information with `--ignore-no-formats-error` - e.g. when the video is a live stream that has not started yet.
 
 [Any field](yt_dlp/extractor/common.py#219-L426) apart from the aforementioned ones are considered **optional**. That means that extraction should be **tolerant** to situations when sources for these fields can potentially be unavailable (even if they are always available at the moment) and **future-proof** in order not to break the extraction of general purpose mandatory fields.
 

CONTRIBUTORS

@@ -272,3 +272,30 @@ crazymoose77756
 nomevi
 Brett824
 pingiun
+dosy4ev
+EhtishamSabir
+Ferdi265
+FirefoxMetzger
+ftk
+lamby
+llamasblade
+lockmatrix
+misaelaguayo
+odo2063
+pritam20ps05
+scy
+sheerluck
+AxiosDeminence
+DjesonPV
+eren-kemer
+freezboltz
+Galiley
+haobinliang
+Mehavoid
+winterbird-code
+yashkc2025
+aldoridhoni
+bashonly
+jacobtruman
+masta79
+palewire

Changelog.md

@@ -11,6 +11,190 @@
 -->
 
 
+### 2022.08.14
+
+* Merge youtube-dl: Upto [commit/d231b56](https://github.com/ytdl-org/youtube-dl/commit/d231b56)
+* [jsinterp] Handle **new youtube signature functions**
+* [jsinterp] Truncate error messages
+* [extractor] Fix format sorting of `channels`
+* [ffmpeg] Disable avconv unless `--prefer-avconv`
+* [ffmpeg] Smarter detection of ffprobe filename
+* [patreon] Ignore erroneous media attachments by [coletdjnz](https://github.com/coletdjnz)
+* [postprocessor/embedthumbnail] Detect `libatomicparsley.so`
+* [ThumbnailsConvertor] Fix conversion after `fixup_webp`
+* [utils] Fix `get_compatible_ext`
+* [build] Fix changelog
+* [update] Set executable bit-mask by [pukkandan](https://github.com/pukkandan), [Lesmiscore](https://github.com/Lesmiscore)
+* [devscripts] Fix import
+* [docs] Consistent use of `e.g.` by [Lesmiscore](https://github.com/Lesmiscore)
+* [cleanup] Misc fixes and cleanup
+* [extractor/moview] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/parler] Add extractor by [palewire](https://github.com/palewire)
+* [extractor/truth] Add extractor by [palewire](https://github.com/palewire)
+* [extractor/aenetworks] Add formats parameter by [jacobtruman](https://github.com/jacobtruman)
+* [extractor/crunchyroll] Improve `_VALID_URL`s
+* [extractor/doodstream] Add `wf` domain by [aldoridhoni](https://github.com/aldoridhoni)
+* [extractor/facebook] Add reel support by [bashonly](https://github.com/bashonly)
+* [extractor/MLB] New extractor by [ischmidt20](https://github.com/ischmidt20)
+* [extractor/rai] Misc fixes by [nixxo](https://github.com/nixxo)
+* [extractor/toggo] Improve `_VALID_URL` by [masta79](https://github.com/masta79)
+* [extractor/tubitv] Extract additional formats by [shirt-dev](https://github.com/shirt-dev)
+* [extractor/zattoo] Potential fix for resellers
+
+
+### 2022.08.08
+
+* **Remove Python 3.6 support**
+* Determine merge container better by [pukkandan](https://github.com/pukkandan), [selfisekai](https://github.com/selfisekai)
+* Framework for embed detection by [coletdjnz](https://github.com/coletdjnz), [pukkandan](https://github.com/pukkandan)
+* Merge youtube-dl: Upto [commit/adb5294](https://github.com/ytdl-org/youtube-dl/commit/adb5294)
+* `--compat-option no-live-chat` should disable danmaku
+* Fix misleading DRM message
+* Import ctypes only when necessary
+* Minor bugfixes
+* Reject entire playlists faster with `--match-filter`
+* Remove filtered entries from `-J`
+* Standardize retry mechanism
+* Validate `--merge-output-format`
+* [downloader] Add average speed to final progress line
+* [extractor] Add field `audio_channels`
+* [extractor] Support multiple archive ids for one video
+* [ffmpeg] Set `ffmpeg_location` in a contextvar
+* [FFmpegThumbnailsConvertor] Fix conversion from GIF
+* [MetadataParser] Don't set `None` when the field didn't match
+* [outtmpl] Smarter replacing of unsupported characters
+* [outtmpl] Treat empty values as None in filenames
+* [utils] sanitize_open: Allow any IO stream as stdout
+* [build, devscripts] Add devscript to set a build variant
+* [build] Improve build process by [shirt-dev](https://github.com/shirt-dev)
+* [build] Update pyinstaller
+* [devscripts] Create `utils` and refactor
+* [docs] Clarify `best*`
+* [docs] Fix bug report issue template
+* [docs] Fix capitalization in references by [christoph-heinrich](https://github.com/christoph-heinrich)
+* [cleanup, mhtml] Use imghdr
+* [cleanup, utils] Consolidate known media extensions
+* [cleanup] Misc fixes and cleanup
+* [extractor/angel] Add extractor by [AxiosDeminence](https://github.com/AxiosDeminence)
+* [extractor/dplay] Add MotorTrend extractor by [Sipherdrakon](https://github.com/Sipherdrakon)
+* [extractor/harpodeon] Add extractor by [eren-kemer](https://github.com/eren-kemer)
+* [extractor/holodex] Add extractor by [pukkandan](https://github.com/pukkandan), [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/kompas] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/rai] Add raisudtirol extractor by [nixxo](https://github.com/nixxo)
+* [extractor/tempo] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/youtube] **Fixes for third party client detection** by [coletdjnz](https://github.com/coletdjnz)
+* [extractor/youtube] Add `live_status=post_live` by [lazypete365](https://github.com/lazypete365)
+* [extractor/youtube] Extract more format info
+* [extractor/youtube] Parse translated subtitles only when requested
+* [extractor/youtube, extractor/twitch] Allow waiting for channels to become live
+* [extractor/youtube, webvtt] Extract auto-subs from livestream VODs by [fstirlitz](https://github.com/fstirlitz), [pukkandan](https://github.com/pukkandan)
+* [extractor/AbemaTVTitle] Implement paging by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/archiveorg] Improve handling of formats by [coletdjnz](https://github.com/coletdjnz), [pukkandan](https://github.com/pukkandan)
+* [extractor/arte] Fix title extraction
+* [extractor/arte] **Move to v2 API** by [fstirlitz](https://github.com/fstirlitz), [pukkandan](https://github.com/pukkandan)
+* [extractor/bbc] Fix news articles by [ajj8](https://github.com/ajj8)
+* [extractor/camtasia] Separate into own extractor by [coletdjnz](https://github.com/coletdjnz)
+* [extractor/cloudflarestream] Fix video_id padding by [haobinliang](https://github.com/haobinliang)
+* [extractor/crunchyroll] Fix conversion of thumbnail from GIF
+* [extractor/crunchyroll] Handle missing metadata correctly by [Burve](https://github.com/Burve), [pukkandan](https://github.com/pukkandan)
+* [extractor/crunchyroll:beta] Extract timestamp and fix tests by [tejing1](https://github.com/tejing1)
+* [extractor/crunchyroll:beta] Use streams API by [tejing1](https://github.com/tejing1)
+* [extractor/doodstream] Support more domains by [Galiley](https://github.com/Galiley)
+* [extractor/ESPN] Extract duration by [ischmidt20](https://github.com/ischmidt20)
+* [extractor/FIFA] Change API endpoint by [Bricio](https://github.com/Bricio), [yashkc2025](https://github.com/yashkc2025)
+* [extractor/globo:article] Remove false positives by [Bricio](https://github.com/Bricio)
+* [extractor/Go] Extract timestamp by [ischmidt20](https://github.com/ischmidt20)
+* [extractor/hidive] Fix cookie login when netrc is also given by [winterbird-code](https://github.com/winterbird-code)
+* [extractor/html5] Separate into own extractor by [coletdjnz](https://github.com/coletdjnz), [pukkandan](https://github.com/pukkandan)
+* [extractor/ina] Improve extractor by [elyse0](https://github.com/elyse0)
+* [extractor/NaverNow] Change endpoint by [ping](https://github.com/ping)
+* [extractor/ninegag] Extract uploader by [DjesonPV](https://github.com/DjesonPV)
+* [extractor/NovaPlay] Fix extractor by [Bojidarist](https://github.com/Bojidarist)
+* [extractor/orf:radio] Rewrite extractors
+* [extractor/patreon] Fix and improve extractors by [coletdjnz](https://github.com/coletdjnz), [pukkandan](https://github.com/pukkandan)
+* [extractor/rai] Fix RaiNews extraction by [nixxo](https://github.com/nixxo)
+* [extractor/redbee] Unify and update extractors by [elyse0](https://github.com/elyse0)
+* [extractor/stripchat] Fix _VALID_URL by [freezboltz](https://github.com/freezboltz)
+* [extractor/tubi] Exclude playlists from playlist entries by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/tviplayer] Improve `_VALID_URL` by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/twitch] Extract chapters for single chapter VODs by [mpeter50](https://github.com/mpeter50)
+* [extractor/vgtv] Support tv.vg.no by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/vidio] Support embed link by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/vk] Fix extractor by [Mehavoid](https://github.com/Mehavoid)
+* [extractor/WASDTV:record] Fix `_VALID_URL`
+* [extractor/xfileshare] Add Referer by [Galiley](https://github.com/Galiley)
+* [extractor/YahooJapanNews] Fix extractor by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/yandexmusic] Extract higher quality format
+* [extractor/zee5] Update Device ID by [m4tu4g](https://github.com/m4tu4g)
+
+
+### 2022.07.18
+
+* Allow users to specify encoding in each config files by [Lesmiscore](https://github.com/Lesmiscore)
+* Discard infodict from memory if no longer needed
+* Do not allow extractors to return `None`
+* Do not load system certificates when `certifi` is used
+* Fix rounding of integers in format table
+* Improve chapter sanitization
+* Skip some fixup if remux/recode is needed by [Lesmiscore](https://github.com/Lesmiscore)
+* Support `--no-progress` for `--wait-for-video`
+* Fix bug in [612f2be](https://github.com/yt-dlp/yt-dlp/commit/612f2be5d3924540158dfbe5f25d841f04cff8c6)
+* [outtmpl] Add alternate form `h` for HTML escaping
+* [aes] Add multiple padding modes in CBC by [elyse0](https://github.com/elyse0)
+* [extractor/common] Passthrough `errnote=False` to parsers
+* [extractor/generic] Remove HEAD request
+* [http] Ensure the file handle is always closed
+* [ModifyChapters] Modify duration in infodict
+* [options] Fix aliases to `--config-location`
+* [utils] Fix `get_domain`
+* [build] Consistent order for lazy extractors by [lamby](https://github.com/lamby)
+* [build] Fix architecture suffix of executables by [odo2063](https://github.com/odo2063)
+* [build] Improve `setup.py`
+* [update] Do not check `_update_spec` when up to date
+* [update] Prepare to remove Python 3.6 support
+* [compat] Let PyInstaller detect _legacy module
+* [devscripts/update-formulae] Do not change dependency section
+* [test] Split download tests so they can be more easily run in CI
+* [docs] Improve docstring of `download_ranges` by [FirefoxMetzger](https://github.com/FirefoxMetzger)
+* [docs] Improve issue templates
+* [build] Fix bug in [6d916fe](https://github.com/yt-dlp/yt-dlp/commit/6d916fe709a38e8c4c69b73843acf170b5165931)
+* [cleanup, utils] Refactor parse_codecs
+* [cleanup] Misc fixes and cleanup
+* [extractor/acfun] Add extractors by [lockmatrix](https://github.com/lockmatrix)
+* [extractor/Audiodraft] Add extractors by [Ashish0804](https://github.com/Ashish0804), [fstirlitz](https://github.com/fstirlitz)
+* [extractor/cellebrite] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/detik] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/hytale] Add extractor by [llamasblade](https://github.com/llamasblade), [pukkandan](https://github.com/pukkandan)
+* [extractor/liputan6] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/mocha] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/rtl.lu] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/rtvsl] Add extractor by [iw0nderhow](https://github.com/iw0nderhow), [pukkandan](https://github.com/pukkandan)
+* [extractor/StarTrek] Add extractor by [scy](https://github.com/scy)
+* [extractor/syvdk] Add extractor by [misaelaguayo](https://github.com/misaelaguayo)
+* [extractor/theholetv] Add extractor by [dosy4ev](https://github.com/dosy4ev)
+* [extractor/TubeTuGraz] Add extractor by [Ferdi265](https://github.com/Ferdi265), [pukkandan](https://github.com/pukkandan)
+* [extractor/tviplayer] Add extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/wetv] Add extractors by [elyse0](https://github.com/elyse0)
+* [extractor/wikimedia] Add extractor by [EhtishamSabir](https://github.com/EhtishamSabir), [pukkandan](https://github.com/pukkandan)
+* [extractor/youtube] Fix duration check for post-live manifestless mode
+* [extractor/youtube] More metadata for storyboards by [ftk](https://github.com/ftk)
+* [extractor/bigo] Fix extractor by [Lesmiscore](https://github.com/Lesmiscore)
+* [extractor/BiliIntl] Fix subtitle extraction by [MinePlayersPE](https://github.com/MinePlayersPE)
+* [extractor/crunchyroll] Improve `_VALID_URL`
+* [extractor/fifa] Fix extractor by [ischmidt20](https://github.com/ischmidt20)
+* [extractor/instagram] Fix post/story extractors by [pritam20ps05](https://github.com/pritam20ps05), [pukkandan](https://github.com/pukkandan)
+* [extractor/iq] Set language correctly for Korean subtitles
+* [extractor/MangoTV] Fix subtitle languages
+* [extractor/Netverse] Improve playlist extractor by [HobbyistDev](https://github.com/HobbyistDev)
+* [extractor/philharmoniedeparis] Fix extractor by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/Trovo] Fix extractor by [u-spec-png](https://github.com/u-spec-png)
+* [extractor/twitch] Support storyboards for VODs by [ftk](https://github.com/ftk)
+* [extractor/WatchESPN] Improve `_VALID_URL` by [IONECarter](https://github.com/IONECarter), [dirkf](https://github.com/dirkf)
+* [extractor/WSJArticle] Fix video id extraction by [sqrtNOT](https://github.com/sqrtNOT)
+* [extractor/Ximalaya] Fix extractors by [lockmatrix](https://github.com/lockmatrix)
+* [cleanup, extractor/youtube] Fix tests by [sheerluck](https://github.com/sheerluck)
+
+
 ### 2022.06.29
 
 * Fix `--downloader native`
@@ -58,7 +242,7 @@
 
 * [**Deprecate support for Python 3.6**](https://github.com/yt-dlp/yt-dlp/issues/3764#issuecomment-1154051119)
 * **Add option `--download-sections` to download video partially**
-    * Chapter regex and time ranges are accepted (Eg: `--download-sections *1:10-2:20`)
+    * Chapter regex and time ranges are accepted, e.g. `--download-sections *1:10-2:20`
 * Add option `--alias`
 * Add option `--lazy-playlist` to process entries as they are received
 * Add option `--retry-sleep`
@@ -1222,7 +1406,7 @@
 
 * Add new option `--netrc-location`
 * [outtmpl] Allow alternate fields using `,`
-* [outtmpl] Add format type `B` to treat the value as bytes (eg: to limit the filename to a certain number of bytes)
+* [outtmpl] Add format type `B` to treat the value as bytes, e.g. to limit the filename to a certain number of bytes
 * Separate the options `--ignore-errors` and `--no-abort-on-error`
 * Basic framework for simultaneous download of multiple formats by [nao20010128nao](https://github.com/nao20010128nao)
 * [17live] Add 17.live extractor by [nao20010128nao](https://github.com/nao20010128nao)
@@ -1612,7 +1796,7 @@
 
 * Merge youtube-dl: Upto [commit/a803582](https://github.com/ytdl-org/youtube-dl/commit/a8035827177d6b59aca03bd717acb6a9bdd75ada)
 * Add `--extractor-args` to pass some extractor-specific arguments. See [readme](https://github.com/yt-dlp/yt-dlp#extractor-arguments)
-    * Add extractor option `skip` for `youtube`. Eg: `--extractor-args youtube:skip=hls,dash`
+    * Add extractor option `skip` for `youtube`, e.g. `--extractor-args youtube:skip=hls,dash`
     * Deprecates `--youtube-skip-dash-manifest`, `--youtube-skip-hls-manifest`, `--youtube-include-dash-manifest`, `--youtube-include-hls-manifest`
 * Allow `--list...` options to work with `--print`, `--quiet` and other `--list...` options
 * [youtube] Use `player` API for additional video extraction requests by [coletdjnz](https://github.com/coletdjnz)

Collaborators.md

@@ -28,12 +28,12 @@ You can also find lists of all [contributors of yt-dlp](CONTRIBUTORS) and [autho
 [![gh-sponsor](https://img.shields.io/badge/_-Sponsor-red.svg?logo=githubsponsors&labelColor=555555&style=for-the-badge)](https://github.com/sponsors/coletdjnz)
 
 * YouTube improvements including: age-gate bypass, private playlists, multiple-clients (to avoid throttling) and a lot of under-the-hood improvements
-* Added support for downloading YoutubeWebArchive videos
+* Added support for new websites YoutubeWebArchive, MainStreaming, PRX, nzherald, Mediaklikk, StarTV etc
-* Added support for new websites MainStreaming, PRX, nzherald, etc
+* Improved/fixed support for Patreon, panopto, gfycat, itv, pbs, SouthParkDE etc
 
 
 
-## [Ashish0804](https://github.com/Ashish0804)
+## [Ashish0804](https://github.com/Ashish0804) <sub><sup>[Inactive]</sup></sub>
 
 [![ko-fi](https://img.shields.io/badge/_-Ko--fi-red.svg?logo=kofi&labelColor=555555&style=for-the-badge)](https://ko-fi.com/ashish0804)
 
@@ -48,4 +48,5 @@ You can also find lists of all [contributors of yt-dlp](CONTRIBUTORS) and [autho
 **Monacoin**: mona1q3tf7dzvshrhfe3md379xtvt2n22duhglv5dskr
 
 * Download live from start to end for YouTube
-* Added support for new websites mildom, PixivSketch, skeb, radiko, voicy, mirrativ, openrec, whowatch, damtomo, 17.live, mixch etc
+* Added support for new websites AbemaTV, mildom, PixivSketch, skeb, radiko, voicy, mirrativ, openrec, whowatch, damtomo, 17.live, mixch etc
+* Improved/fixed support for fc2, YahooJapanNews, tver, iwara etc

Makefile

@@ -17,8 +17,8 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
 clean-test:
 	rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
 	*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
-	*.3gp *.ape *.ass *.avi *.desktop *.flac *.flv *.jpeg *.jpg *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 \
+	*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.jpeg *.jpg *.m4a *.mpga *.m4v *.mhtml *.mkv *.mov \
-	*.mp4 *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
+	*.mp3 *.mp4 *.ogg *.opus *.png *.sbv *.srt *.swf *.swp *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
 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

README.md

@@ -71,7 +71,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 # NEW FEATURES
 
-* Merged with **youtube-dl v2021.12.17+ [commit/a03b977](https://github.com/ytdl-org/youtube-dl/commit/a03b9775d544b06a5b4f2aa630214c7c22fc2229)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc v2020.11.11-3+ [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
+* Merged with **youtube-dl v2021.12.17+ [commit/d231b56](https://github.com/ytdl-org/youtube-dl/commit/d231b56717c73ee597d2e077d11b69ed48a1b02d)**<!--([exceptions](https://github.com/yt-dlp/yt-dlp/issues/21))--> and **youtube-dlc v2020.11.11-3+ [commit/f9401f2](https://github.com/blackjack4494/yt-dlc/commit/f9401f2a91987068139c5f757b12fc711d4c0cee)**: You get all the features and patches of [youtube-dlc](https://github.com/blackjack4494/yt-dlc) in addition to the latest [youtube-dl](https://github.com/ytdl-org/youtube-dl)
 
 * **[SponsorBlock Integration](#sponsorblock-options)**: You can mark/remove sponsor sections in youtube videos by utilizing the [SponsorBlock](https://sponsor.ajay.app) API
 
@@ -105,7 +105,7 @@ yt-dlp is a [youtube-dl](https://github.com/ytdl-org/youtube-dl) fork based on t
 
 * **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
+* **Portable Configuration**: Configuration files are automatically loaded from the home and root directories. See [CONFIGURATION](#configuration) for details
 
 * **Output template improvements**: Output templates can now have date-time formatting, numeric offsets, object traversal etc. See [output template](#output-template) for details. Even more advanced operations can also be done with the help of `--parse-metadata` and `--replace-in-metadata`
 
@@ -127,7 +127,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 
 * The options `--auto-number` (`-A`), `--title` (`-t`) and `--literal` (`-l`), no longer work. See [removed options](#Removed) for details
 * `avconv` is not supported as an alternative to `ffmpeg`
-* yt-dlp stores config files in slightly different locations to youtube-dl. See [configuration](#configuration) for a list of correct locations
+* yt-dlp stores config files in slightly different locations to youtube-dl. See [CONFIGURATION](#configuration) for a list of correct locations
 * The default [output template](#output-template) is `%(title)s [%(id)s].%(ext)s`. There is no real reason for this change. This was changed before yt-dlp was ever made public and now there are no plans to change it back to `%(title)s-%(id)s.%(ext)s`. Instead, you may use `--compat-options filename`
 * The default [format sorting](#sorting-formats) is different from youtube-dl and prefers higher resolution and better codecs rather than higher bitrates. You can use the `--format-sort` option to change this to any order you prefer, or use `--compat-options format-sort` to use youtube-dl's sorting order
 * The default format selector is `bv*+ba/b`. This means that if a combined video + audio format that is better than the best video-only format is found, the former will be preferred. Use `-f bv+ba/b` or `--compat-options format-spec` to revert this
@@ -138,16 +138,15 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * Some metadata are embedded into different fields when using `--add-metadata` as compared to youtube-dl. Most notably, `comment` field contains the `webpage_url` and `synopsis` contains the `description`. You can [use `--parse-metadata`](#modifying-metadata) to modify this to your liking or use `--compat-options embed-metadata` to revert this
 * `playlist_index` behaves differently when used with options like `--playlist-reverse` and `--playlist-items`. See [#302](https://github.com/yt-dlp/yt-dlp/issues/302) for details. You can use `--compat-options playlist-index` if you want to keep the earlier behavior
 * The output of `-F` is listed in a new format. Use `--compat-options list-formats` to revert this
-* All *experiences* of a funimation episode are considered as a single video. This behavior breaks existing archives. Use `--compat-options seperate-video-versions` to extract information from only the default player
+* Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading
-* Youtube live chat (if available) is considered as a subtitle. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent live chat from downloading
 * Youtube channel URLs are automatically redirected to `/video`. Append a `/featured` to the URL to download only the videos in the home page. If the channel does not have a videos tab, we try to download the equivalent `UU` playlist instead. For all other tabs, if the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections
 * Unavailable videos are also listed for youtube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this
 * If `ffmpeg` is used as the downloader, the downloading and merging of formats happen in a single step when possible. Use `--compat-options no-direct-merge` to revert this
 * Thumbnail embedding in `mp4` is done with mutagen if possible. Use `--compat-options embed-thumbnail-atomicparsley` to force the use of AtomicParsley instead
 * Some private fields such as filenames are removed by default from the infojson. Use `--no-clean-infojson` or `--compat-options no-clean-infojson` to revert this
 * When `--embed-subs` and `--write-subs` are used together, the subtitles are written to disk and also embedded in the media file. You can use just `--embed-subs` to embed the subs and automatically delete the separate file. See [#630 (comment)](https://github.com/yt-dlp/yt-dlp/issues/630#issuecomment-893659460) for more info. `--compat-options no-keep-subs` can be used to revert this
-* `certifi` will be used for SSL root certificates, if installed. If you want to use only system certificates, use `--compat-options no-certifi`
+* `certifi` will be used for SSL root certificates, if installed. If you want to use system certificates (e.g. self-signed), use `--compat-options no-certifi`
-* youtube-dl tries to remove some superfluous punctuations from filenames. While this can sometimes be helpful, it is often undesirable. So yt-dlp tries to keep the fields in the filenames as close to their original values as possible. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
+* yt-dlp's sanitization of invalid characters in filenames is different/smarter than in youtube-dl. You can use `--compat-options filename-sanitization` to revert to youtube-dl's behavior
 
 For ease of use, a few more compat options are available:
 
@@ -238,7 +237,7 @@ File|Description
 :---|:---
 [yt-dlp](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp)|Platform-independent [zipimport](https://docs.python.org/3/library/zipimport.html) binary. Needs Python (recommended for **Linux/BSD**)
 [yt-dlp.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp.exe)|Windows (Win7 SP1+) standalone x64 binary (recommended for **Windows**)
-[yt-dlp_macos](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos)|MacOS (10.15+) standalone executable (recommended for **MacOS**)
+[yt-dlp_macos](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos)|Universal MacOS (10.15+) standalone executable (recommended for **MacOS**)
 
 #### Alternatives
 
@@ -246,8 +245,8 @@ File|Description
 :---|:---
 [yt-dlp_x86.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_x86.exe)|Windows (Vista SP2+) standalone x86 (32-bit) binary
 [yt-dlp_min.exe](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_min.exe)|Windows (Win7 SP1+) standalone x64 binary built with `py2exe`<br/> ([Not recommended](#standalone-py2exe-builds-windows))
-[yt-dlp_linux](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux)|UNIX standalone x64 binary
+[yt-dlp_linux](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux)|Linux standalone x64 binary
-[yt-dlp_linux.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux.zip)|Unpackaged Unix executable (no auto-update)
+[yt-dlp_linux.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_linux.zip)|Unpackaged Linux executable (no auto-update)
 [yt-dlp_win.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_win.zip)|Unpackaged Windows executable (no auto-update)
 [yt-dlp_macos.zip](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos.zip)|Unpackaged MacOS (10.15+) executable (no auto-update)
 [yt-dlp_macos_legacy](https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp_macos_legacy)|MacOS (10.9+) standalone x64 executable
@@ -305,7 +304,7 @@ While all the other dependencies are optional, `ffmpeg` and `ffprobe` are highly
 
 To use or redistribute the dependencies, you must agree to their respective licensing terms.
 
-The Windows and MacOS standalone release binaries are built with the Python interpreter and the packages marked with **\*** included.
+The standalone release binaries are built with the Python interpreter and the packages marked with **\*** included.
 
 If you do not have the necessary dependencies for a task you are attempting, yt-dlp will warn you. All the currently available dependencies are visible at the top of the `--verbose` output
 
@@ -313,7 +312,7 @@ If you do not have the necessary dependencies for a task you are attempting, yt-
 ## COMPILE
 
 ### Standalone PyInstaller Builds
-To build the Windows/MacOS executable, you must have Python and `pyinstaller` (plus any of yt-dlp's [optional dependencies](#dependencies) if needed). Once you have all the necessary dependencies installed, simply run `pyinst.py`. The executable will be built for the same architecture (32/64 bit) as the Python used.
+To build the standalone executable, you must have Python and `pyinstaller` (plus any of yt-dlp's [optional dependencies](#dependencies) if needed). Once you have all the necessary dependencies installed, simply run `pyinst.py`. The executable will be built for the same architecture (x86/ARM, 32/64 bit) as the Python used.
 
     python3 -m pip install -U pyinstaller -r requirements.txt
     python3 devscripts/make_lazy_extractors.py
@@ -344,7 +343,8 @@ If you wish to build it anyway, install Python and py2exe, and then simply run `
 
 ### Related scripts
 
-* **`devscripts/update-version.py`** - Update the version number based on current timestamp
+* **`devscripts/update-version.py [revision]`** - Update the version number based on current date
+* **`devscripts/set-variant.py variant [-M update_message]`** - Set the build variant of the executable
 * **`devscripts/make_lazy_extractors.py`** - Create lazy extractors. Running this before building the binaries (any variant) will improve their startup performance. Set the environment variable `YTDLP_NO_LAZY_EXTRACTORS=1` if you wish to forcefully disable lazy extractor loading.
 
 You can also fork the project on github and run your fork's [build workflow](.github/workflows/build.yml) to automatically build a full release
@@ -361,8 +361,8 @@ You can also fork the project on github and run your fork's [build workflow](.gi
 ## General Options:
     -h, --help                      Print this help text and exit
     --version                       Print program version and exit
-    -U, --update                    Update this program to latest version
+    -U, --update                    Update this program to the latest version
-    --no-update                     Do not update (default)
+    --no-update                     Do not check for updates (default)
     -i, --ignore-errors             Ignore download and postprocessing errors.
                                     The download will be considered successful
                                     even if the postprocessing fails
@@ -376,7 +376,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     --extractor-descriptions        Output descriptions of all supported
                                     extractors and exit
     --force-generic-extractor       Force extraction to use the generic extractor
-    --default-search PREFIX         Use this prefix for unqualified URLs. Eg:
+    --default-search PREFIX         Use this prefix for unqualified URLs. E.g.
                                     "gvsearch2:python" downloads two videos from
                                     google videos for the search term "python".
                                     Use the value "auto" to let yt-dlp guess
@@ -414,7 +414,8 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     --no-wait-for-video             Do not wait for scheduled streams (default)
     --mark-watched                  Mark videos watched (even with --simulate)
     --no-mark-watched               Do not mark videos watched (default)
-    --no-colors                     Do not emit color codes in output
+    --no-colors                     Do not emit color codes in output (Alias:
+                                    --no-colours)
     --compat-options OPTS           Options that can help keep compatibility
                                     with youtube-dl or youtube-dlc
                                     configurations by reverting some of the
@@ -424,7 +425,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     an alias starts with a dash "-", it is
                                     prefixed with "--". Arguments are parsed
                                     according to the Python string formatting
-                                    mini-language. Eg: --alias get-audio,-X
+                                    mini-language. E.g. --alias get-audio,-X
                                     "-S=aext:{0},abr -x --audio-format {0}"
                                     creates options "--get-audio" and "-X" that
                                     takes an argument (ARG0) and expands to
@@ -438,10 +439,10 @@ You can also fork the project on github and run your fork's [build workflow](.gi
 
 ## Network Options:
     --proxy URL                     Use the specified HTTP/HTTPS/SOCKS proxy. To
-                                    enable SOCKS proxy, specify a proper scheme.
+                                    enable SOCKS proxy, specify a proper scheme,
-                                    Eg: socks5://user:pass@127.0.0.1:1080/. Pass
+                                    e.g. socks5://user:pass@127.0.0.1:1080/.
-                                    in an empty string (--proxy "") for direct
+                                    Pass in an empty string (--proxy "") for
-                                    connection
+                                    direct connection
     --socket-timeout SECONDS        Time to wait before giving up, in seconds
     --source-address IP             Client-side IP address to bind to
     -4, --force-ipv4                Make all connections via IPv4
@@ -470,17 +471,17 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     compatibility, START-STOP is also supported.
                                     Use negative indices to count from the right
                                     and negative STEP to download in reverse
-                                    order. Eg: "-I 1:3,7,-5::2" used on a
+                                    order. E.g. "-I 1:3,7,-5::2" used on a
                                     playlist of size 15 will download the videos
                                     at index 1,2,3,7,11,13,15
-    --min-filesize SIZE             Do not download any videos smaller than SIZE
+    --min-filesize SIZE             Do not download any videos smaller than
-                                    (e.g. 50k or 44.6m)
+                                    SIZE, e.g. 50k or 44.6M
-    --max-filesize SIZE             Do not download any videos larger than SIZE
+    --max-filesize SIZE             Do not download any videos larger than SIZE,
-                                    (e.g. 50k or 44.6m)
+                                    e.g. 50k or 44.6M
     --date DATE                     Download only videos uploaded on this date.
                                     The date can be "YYYYMMDD" or in the format 
                                     [now|today|yesterday][-N[day|week|month|year]].
-                                    Eg: --date today-2weeks
+                                    E.g. --date today-2weeks
     --datebefore DATE               Download only videos uploaded on or before
                                     this date. The date formats accepted is the
                                     same as --date
@@ -490,14 +491,14 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     --match-filters FILTER          Generic video filter. Any "OUTPUT TEMPLATE"
                                     field can be compared with a number or a
                                     string using the operators defined in
-                                    "Filtering formats". You can also simply
+                                    "Filtering Formats". You can also simply
                                     specify a field to match if the field is
                                     present, use "!field" to check if the field
                                     is not present, and "&" to check multiple
                                     conditions. Use a "\" to escape "&" or
                                     quotes if needed. If used multiple times,
                                     the filter matches if atleast one of the
-                                    conditions are met. Eg: --match-filter
+                                    conditions are met. E.g. --match-filter
                                     !is_live --match-filter "like_count>?100 &
                                     description~='(?i)\bcats \& dogs\b'" matches
                                     only videos that are not live OR those that
@@ -535,25 +536,25 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     -N, --concurrent-fragments N    Number of fragments of a dash/hlsnative
                                     video that should be downloaded concurrently
                                     (default is 1)
-    -r, --limit-rate RATE           Maximum download rate in bytes per second
+    -r, --limit-rate RATE           Maximum download rate in bytes per second,
-                                    (e.g. 50K or 4.2M)
+                                    e.g. 50K or 4.2M
     --throttled-rate RATE           Minimum download rate in bytes per second
                                     below which throttling is assumed and the
-                                    video data is re-extracted (e.g. 100K)
+                                    video data is re-extracted, e.g. 100K
     -R, --retries RETRIES           Number of retries (default is 10), or
                                     "infinite"
     --file-access-retries RETRIES   Number of times to retry on file access
                                     error (default is 3), or "infinite"
     --fragment-retries RETRIES      Number of retries for a fragment (default is
                                     10), or "infinite" (DASH, hlsnative and ISM)
-    --retry-sleep [TYPE:]EXPR       An expression for the time to sleep between
+    --retry-sleep [TYPE:]EXPR       Time to sleep between retries in seconds
-                                    retries in seconds (optionally) prefixed by
+                                    (optionally) prefixed by the type of retry
-                                    the type of retry (file_access, fragment,
+                                    (http (default), fragment, file_access,
-                                    http (default)) to apply the sleep to. EXPR
+                                    extractor) to apply the sleep to. EXPR can
-                                    can be a number, linear=START[:END[:STEP=1]]
+                                    be a number, linear=START[:END[:STEP=1]] or
-                                    or exp=START[:END[:BASE=2]]. This option can
+                                    exp=START[:END[:BASE=2]]. This option can be
-                                    be used multiple times to set the sleep for
+                                    used multiple times to set the sleep for the
-                                    the different retry types. Eg: --retry-sleep
+                                    different retry types, e.g. --retry-sleep
                                     linear=1::2 --retry-sleep fragment:exp=1:20
     --skip-unavailable-fragments    Skip unavailable fragments for DASH,
                                     hlsnative and ISM downloads (default)
@@ -565,14 +566,14 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     downloading is finished
     --no-keep-fragments             Delete downloaded fragments after
                                     downloading is finished (default)
-    --buffer-size SIZE              Size of download buffer (e.g. 1024 or 16K)
+    --buffer-size SIZE              Size of download buffer, e.g. 1024 or 16K
                                     (default is 1024)
     --resize-buffer                 The buffer size is automatically resized
                                     from an initial value of --buffer-size
                                     (default)
     --no-resize-buffer              Do not automatically adjust the buffer size
     --http-chunk-size SIZE          Size of a chunk for chunk-based HTTP
-                                    downloading (e.g. 10485760 or 10M) (default
+                                    downloading, e.g. 10485760 or 10M (default
                                     is disabled). May be useful for bypassing
                                     bandwidth throttling imposed by a webserver
                                     (experimental)
@@ -597,10 +598,10 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     the given regular expression. Time ranges
                                     prefixed by a "*" can also be used in place
                                     of chapters to download the specified range.
-                                    Eg: --download-sections "*10:15-15:00"
+                                    Needs ffmpeg. This option can be used
-                                    --download-sections "intro". Needs ffmpeg.
+                                    multiple times to download multiple
-                                    This option can be used multiple times to
+                                    sections, e.g. --download-sections
-                                    download multiple sections
+                                    "*10:15-15:00" --download-sections "intro"
     --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
@@ -608,7 +609,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     aria2c, avconv, axel, curl, ffmpeg, httpie,
                                     wget. You can use this option multiple times
                                     to set different downloaders for different
-                                    protocols. For example, --downloader aria2c
+                                    protocols. E.g. --downloader aria2c
                                     --downloader "dash,m3u8:native" will use
                                     aria2c for http/ftp downloads, and the
                                     native downloader for dash/m3u8 downloads
@@ -790,7 +791,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     "postprocess:",  or "postprocess-title:".
                                     The video's fields are accessible under the
                                     "info" key and the progress attributes are
-                                    accessible under "progress" key. E.g.:
+                                    accessible under "progress" key. E.g.
                                     --console-title --progress-template
                                     "download-title:%(info.id)s-%(progress.eta)s"
     -v, --verbose                   Print various debugging information
@@ -858,10 +859,10 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     downloadable
     -F, --list-formats              List available formats of each video.
                                     Simulate unless --no-simulate is used
-    --merge-output-format FORMAT    If a merge is required (e.g.
+    --merge-output-format FORMAT    Containers that may be used when merging
-                                    bestvideo+bestaudio), output to given
+                                    formats, separated by "/", e.g. "mp4/mkv".
-                                    container format. One of mkv, mp4, ogg,
+                                    Ignored if no merge is required. (currently
-                                    webm, flv. Ignored if no merge is required
+                                    supported: avi, flv, mkv, mov, mp4, webm)
 
 ## Subtitle Options:
     --write-subs                    Write subtitle file
@@ -873,13 +874,13 @@ You can also fork the project on github and run your fork's [build workflow](.gi
     --list-subs                     List available subtitles of each video.
                                     Simulate unless --no-simulate is used
     --sub-format FORMAT             Subtitle format; accepts formats preference,
-                                    Eg: "srt" or "ass/srt/best"
+                                    e.g. "srt" or "ass/srt/best"
     --sub-langs LANGS               Languages of the subtitles to download (can
-                                    be regex) or "all" separated by commas. (Eg:
+                                    be regex) or "all" separated by commas, e.g.
-                                    --sub-langs "en.*,ja") You can prefix the
+                                    --sub-langs "en.*,ja". You can prefix the
                                     language code with a "-" to exclude it from
-                                    the requested languages. (Eg: --sub-langs
+                                    the requested languages, e.g. --sub-langs
-                                    all,-live_chat) Use --list-subs for a list
+                                    all,-live_chat. Use --list-subs for a list
                                     of available language tags
 
 ## Authentication Options:
@@ -915,7 +916,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     (requires ffmpeg and ffprobe)
     --audio-format FORMAT           Format to convert the audio to when -x is
                                     used. (currently supported: best (default),
-                                    mp3, aac, m4a, opus, vorbis, flac, alac,
+                                    aac, alac, flac, m4a, mp3, opus, vorbis,
                                     wav). You can specify multiple rules using
                                     similar syntax as --remux-video
     --audio-quality QUALITY         Specify ffmpeg audio quality to use when
@@ -923,12 +924,12 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     between 0 (best) and 10 (worst) for VBR or a
                                     specific bitrate like 128K (default 5)
     --remux-video FORMAT            Remux the video into another container if
-                                    necessary (currently supported: mp4, mkv,
+                                    necessary (currently supported: avi, flv,
-                                    flv, webm, mov, avi, mka, ogg, mp3, aac,
+                                    mkv, mov, mp4, webm, aac, aiff, alac, flac,
-                                    m4a, opus, vorbis, flac, alac, wav). If
+                                    m4a, mka, mp3, ogg, opus, vorbis, wav). If
                                     target container does not support the
                                     video/audio codec, remuxing will fail. You
-                                    can specify multiple rules; Eg.
+                                    can specify multiple rules; e.g.
                                     "aac>m4a/mov>mp4/mkv" will remux aac to m4a,
                                     mov to mp4 and anything else to mkv
     --recode-video FORMAT           Re-encode the video into another format if
@@ -953,7 +954,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     for 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
+                                    specified input/output file, e.g. --ppa
                                     "Merger+ffmpeg_i1:-v quiet". You can use
                                     this option multiple times to give different
                                     arguments to different postprocessors.
@@ -1024,7 +1025,7 @@ You can also fork the project on github and run your fork's [build workflow](.gi
                                     be used multiple times
     --no-exec                       Remove any previously defined --exec
     --convert-subs FORMAT           Convert the subtitles to another format
-                                    (currently supported: srt, vtt, ass, lrc)
+                                    (currently supported: ass, lrc, srt, vtt)
                                     (Alias: --convert-subtitles)
     --convert-thumbnails FORMAT     Convert the thumbnails to another format
                                     (currently supported: jpg, png, webp). You
@@ -1080,7 +1081,7 @@ Make chapter entries for, or remove various segments (sponsor,
                                     music_offtopic, poi_highlight, all and
                                     default (=all). You can prefix the category
                                     with a "-" to exclude it. See [1] for
-                                    description of the categories. Eg:
+                                    description of the categories. E.g.
                                     --sponsorblock-mark all,-preview
                                     [1] https://wiki.sponsor.ajay.app/w/Segment_Categories
     --sponsorblock-remove CATS      SponsorBlock categories to be removed from
@@ -1139,7 +1140,7 @@ You can configure yt-dlp by placing any supported command line option to a confi
 
 1. **System Configuration**: `/etc/yt-dlp.conf`
 
-For example, with the following configuration file yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
+E.g. with the following configuration file yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
 ```
 # Lines starting with # are comments
 
@@ -1160,6 +1161,12 @@ Note that options in configuration file are just the same options aka switches u
 
 You can use `--ignore-config` if you want to disable all configuration files for a particular yt-dlp run. If `--ignore-config` is found inside any configuration file, no further configuration will be loaded. For example, having the option in the portable configuration file prevents loading of home, user, and system configurations. Additionally, (for backward compatibility) if `--ignore-config` is found inside the system configuration file, the user configuration is not loaded.
 
+### Config file encoding
+
+The config files are decoded according to the UTF BOM if present, and in the encoding from system locale otherwise.
+
+If you want your file to be decoded differently, add `# coding: ENCODING` to the beginning of the file (e.g. `# coding: shift-jis`). There must be no characters before that, even spaces or BOM.
+
 ### Authentication with `.netrc` file
 
 You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every yt-dlp execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per extractor basis. For that you will need to create a `.netrc` file in `--netrc-location` and restrict permissions to read/write by only you:
@@ -1171,7 +1178,7 @@ After that you can add credentials for an extractor in the following format, whe
 ```
 machine <extractor> login <username> password <password>
 ```
-For example:
+E.g.
 ```
 machine youtube login myaccount@gmail.com password my_youtube_password
 machine twitch login my_twitch_account_name password my_twitch_password
@@ -1190,32 +1197,32 @@ The `-o` option is used to indicate a template for the output file names while `
 
 The simplest 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 and could break some post-processing).
 
-It may however also 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/3/library/stdtypes.html#printf-style-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.
+It may however also 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/3/library/stdtypes.html#printf-style-string-formatting), e.g. `%(NAME)s` or `%(NAME)05d`. To clarify, that is a percent symbol followed by a name in parentheses, followed by formatting operations.
 
 The field names themselves (the part inside the parenthesis) can also have some special formatting:
 
-1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a `.` (dot) separator. You can also do python slicing using `:`. Eg: `%(tags.0)s`, `%(subtitles.en.-1.ext)s`, `%(id.3:7:-1)s`, `%(formats.:.format_id)s`. `%()s` refers to the entire infodict. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields
+1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a `.` (dot) separator. You can also do python slicing using `:`. E.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`, `%(id.3:7:-1)s`, `%(formats.:.format_id)s`. `%()s` refers to the entire infodict. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields
 
-1. **Addition**: Addition and subtraction of numeric fields can be done using `+` and `-` respectively. Eg: `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
+1. **Addition**: Addition and subtraction of numeric fields can be done using `+` and `-` respectively. E.g. `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
 
-1. **Date/time Formatting**: Date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it separated from the field name using a `>`. Eg: `%(duration>%H-%M-%S)s`, `%(upload_date>%Y-%m-%d)s`, `%(epoch-3600>%H-%M-%S)s`
+1. **Date/time Formatting**: Date/time fields can be formatted according to [strftime formatting](https://docs.python.org/3/library/datetime.html#strftime-and-strptime-format-codes) by specifying it separated from the field name using a `>`. E.g. `%(duration>%H-%M-%S)s`, `%(upload_date>%Y-%m-%d)s`, `%(epoch-3600>%H-%M-%S)s`
 
-1. **Alternatives**: Alternate fields can be specified separated with a `,`. Eg: `%(release_date>%Y,upload_date>%Y|Unknown)s`
+1. **Alternatives**: Alternate fields can be specified separated with a `,`. E.g. `%(release_date>%Y,upload_date>%Y|Unknown)s`
 
 1. **Replacement**: A replacement value can specified using a `&` separator. If the field is *not* empty, this replacement value will be used instead of the actual field content. This is done after alternate fields are considered; thus the replacement is used if *any* of the alternative fields is *not* empty.
 
-1. **Default**: A literal default value can be specified for when the field is empty using a `|` separator. This overrides `--output-na-template`. Eg: `%(uploader|Unknown)s`
+1. **Default**: A literal default value can be specified for when the field is empty using a `|` separator. This overrides `--output-na-template`. E.g. `%(uploader|Unknown)s`
 
-1. **More Conversions**: In addition to the normal format types `diouxXeEfFgGcrs`, `B`, `j`, `l`, `q`, `D`, `S` can be used for converting to **B**ytes, **j**son (flag `#` for pretty-printing), a comma separated **l**ist (flag `#` for `\n` newline-separated), a string **q**uoted for the terminal (flag `#` to split a list into different arguments), to add **D**ecimal suffixes (Eg: 10M) (flag `#` to use 1024 as factor), and to **S**anitize as filename (flag `#` for restricted), respectively
+1. **More Conversions**: In addition to the normal format types `diouxXeEfFgGcrs`, yt-dlp additionally supports converting to `B` = **B**ytes, `j` = **j**son (flag `#` for pretty-printing), `h` = HTML escaping, `l` = a comma separated **l**ist (flag `#` for `\n` newline-separated), `q` = a string **q**uoted for the terminal (flag `#` to split a list into different arguments), `D` = add **D**ecimal suffixes (e.g. 10M) (flag `#` to use 1024 as factor), and `S` = **S**anitize as filename (flag `#` for restricted)
 
-1. **Unicode normalization**: The format type `U` can be used for NFC [unicode normalization](https://docs.python.org/3/library/unicodedata.html#unicodedata.normalize). The alternate form flag (`#`) changes the normalization to NFD and the conversion flag `+` can be used for NFKC/NFKD compatibility equivalence normalization. Eg: `%(title)+.100U` is NFKC
+1. **Unicode normalization**: The format type `U` can be used for NFC [unicode normalization](https://docs.python.org/3/library/unicodedata.html#unicodedata.normalize). The alternate form flag (`#`) changes the normalization to NFD and the conversion flag `+` can be used for NFKC/NFKD compatibility equivalence normalization. E.g. `%(title)+.100U` is NFKC
 
 To summarize, the general syntax for a field is:
 ```
 %(name[.keys][addition][>strf][,alternate][&replacement][|default])[flags][width][.precision][length]type
 ```
 
-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 file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. 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. If any of the templates is empty, that type of file will not be written. Eg: `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for 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 file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. E.g. `-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. If any of the templates is empty, that type of file will not be written. E.g. `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video.
 
 The available fields are:
 
@@ -1250,7 +1257,7 @@ The available fields are:
  - `average_rating` (numeric): Average rating give by users, the scale used depends on the webpage
  - `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)
- - `live_status` (string): One of "is_live", "was_live", "is_upcoming", "not_live"
+ - `live_status` (string): One of "not_live", "is_live", "is_upcoming", "was_live", "post_live" (was live, but VOD is not yet processed)
  - `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
@@ -1270,6 +1277,7 @@ The available fields are:
  - `vbr` (numeric): Average video bitrate in KBit/s
  - `fps` (numeric): Frame rate
  - `dynamic_range` (string): The dynamic range of the video
+ - `audio_channels` (numeric): The number of audio channels
  - `stretched_ratio` (float): `width:height` of the video's pixels, if not square
  - `vcodec` (string): Name of the video codec in use
  - `container` (string): Name of the container format
@@ -1350,13 +1358,13 @@ Available only in `--sponsorblock-chapter-title`:
  - `category_names` (list): Friendly names of the categories
  - `name` (string): Friendly name of the smallest category
 
-Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. For example for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKc`, this will result in a `yt-dlp test video-BaW_jenozKc.mp4` file created in the current directory.
+Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. E.g. for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKc`, this will result in a `yt-dlp test video-BaW_jenozKc.mp4` file created in the current directory.
 
 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).
 
 **Tip**: Look at the `-j` output to identify which fields are available for the particular URL
 
-For numeric sequences you can use [numeric related formatting](https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting), for example, `%(view_count)05d` will result in a string with view count padded with zeros up to 5 characters, like in `00042`.
+For numeric sequences you can use [numeric related formatting](https://docs.python.org/3/library/stdtypes.html#printf-style-string-formatting); e.g. `%(view_count)05d` will result in a string with view count padded with zeros up to 5 characters, like in `00042`.
 
 Output templates can also contain arbitrary hierarchical path, e.g. `-o "%(playlist)s/%(playlist_index)s - %(title)s.%(ext)s"` which will result in downloading each video in a directory corresponding to this path template. Any missing directory will be automatically created for you.
 
@@ -1426,7 +1434,7 @@ The general syntax for format selection is `-f FORMAT` (or `--format FORMAT`) wh
 **tl;dr:** [navigate me to examples](#format-selection-examples).
 <!-- MANPAGE: END EXCLUDED SECTION -->
 
-The simplest case is requesting a specific format, for example with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific.
+The simplest case is requesting a specific format; e.g. with `-f 22` you can download the format with format code equal to 22. You can get the list of available format codes for particular video using `--list-formats` or `-F`. Note that these format codes are extractor specific.
 
 You can also use a file extension (currently `3gp`, `aac`, `flv`, `m4a`, `mp3`, `mp4`, `ogg`, `wav`, `webm` are supported) to download the best quality format of a particular file extension served as a single file, e.g. `-f webm` will download the best quality format with the `webm` extension served as a single file.
 
@@ -1436,7 +1444,7 @@ You can also use special names to select particular edge case formats:
 
  - `all`: Select **all formats** separately
  - `mergeall`: Select and **merge all formats** (Must be used with `--audio-multistreams`, `--video-multistreams` or both)
- - `b*`, `best*`: Select the best quality format that **contains either** a video or an audio
+ - `b*`, `best*`: Select the best quality format that **contains either** a video or an audio or both (ie; `vcodec!=none or acodec!=none`)
  - `b`, `best`: Select the best quality format that **contains both** video and audio. Equivalent to `best*[vcodec!=none][acodec!=none]`
  - `bv`, `bestvideo`: Select the best quality **video-only** format. Equivalent to `best*[acodec=none]`
  - `bv*`, `bestvideo*`: Select the best quality format that **contains video**. It may also contain audio. Equivalent to `best*[vcodec!=none]`
@@ -1449,19 +1457,19 @@ You can also use special names to select particular edge case formats:
  - `wa`, `worstaudio`: Select the worst quality audio-only format. Equivalent to `worst*[vcodec=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 recommended 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 `-S +size` or more rigorously, `-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 recommended 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 `-S +size` or more rigorously, `-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.
+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; e.g. `-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.
 
 If you want to download several formats of the same video use a comma as a separator, e.g. `-f 22,17,18` will download all these three formats, of course if they are available. Or a more sophisticated example combined with the precedence feature: `-f 136/137/mp4/bestvideo,140/m4a/bestaudio`.
 
-You can merge the video and audio of multiple formats into a single file using `-f <format1>+<format2>+...` (requires ffmpeg installed), for example `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg.
+You can merge the video and audio of multiple formats into a single file using `-f <format1>+<format2>+...` (requires ffmpeg installed); e.g. `-f bestvideo+bestaudio` will download the best video-only format, the best audio-only format and mux them together with ffmpeg.
 
 **Deprecation warning**: Since the *below* described behavior is complex and counter-intuitive, this will be removed and multistreams will be enabled by default in the future. A new operator will be instead added to limit formats to single audio/video
 
-Unless `--video-multistreams` is used, all formats with a video stream except the first one are ignored. Similarly, unless `--audio-multistreams` is used, all formats with an audio stream except the first one are ignored. For example, `-f bestvideo+best+bestaudio --video-multistreams --audio-multistreams` will download and merge all 3 given formats. The resulting file will have 2 video streams and 2 audio streams. But `-f bestvideo+best+bestaudio --no-video-multistreams` will download and merge only `bestvideo` and `bestaudio`. `best` is ignored since another format containing a video stream (`bestvideo`) has already been selected. The order of the formats is therefore important. `-f best+bestaudio --no-audio-multistreams` will download and merge both formats while `-f bestaudio+best --no-audio-multistreams` will ignore `best` and download only `bestaudio`.
+Unless `--video-multistreams` is used, all formats with a video stream except the first one are ignored. Similarly, unless `--audio-multistreams` is used, all formats with an audio stream except the first one are ignored. E.g. `-f bestvideo+best+bestaudio --video-multistreams --audio-multistreams` will download and merge all 3 given formats. The resulting file will have 2 video streams and 2 audio streams. But `-f bestvideo+best+bestaudio --no-video-multistreams` will download and merge only `bestvideo` and `bestaudio`. `best` is ignored since another format containing a video stream (`bestvideo`) has already been selected. The order of the formats is therefore important. `-f best+bestaudio --no-audio-multistreams` will download and merge both formats while `-f bestaudio+best --no-audio-multistreams` will ignore `best` and download only `bestaudio`.
 
 ## Filtering Formats
 
@@ -1492,9 +1500,9 @@ Any string comparison may be prefixed with negation `!` in order to produce an o
 
 Note that none of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
 
-Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter. For example, `-f "all[vcodec=none]"` selects all audio-only formats.
+Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 KBit/s. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
 
-Format selectors can also be grouped using parentheses, for example if you want to download the best pre-merged mp4 and webm formats with a height lower than 480 you can use `-f "(mp4,webm)[height<480]"`.
+Format selectors can also be grouped using parentheses; e.g. `-f "(mp4,webm)[height<480]"` will download the best pre-merged mp4 and webm formats with a height lower than 480.
 
 ## Sorting Formats
 
@@ -1523,6 +1531,7 @@ The available fields are:
  - `res`: Video resolution, calculated as the smallest dimension.
  - `fps`: Framerate of video
  - `hdr`: The dynamic range of the video (`DV` > `HDR12` > `HDR10+` > `HDR10` > `HLG` > `SDR`)
+ - `channels`: The number of audio channels
  - `tbr`: Total average bitrate in KBit/s
  - `vbr`: Average video bitrate in KBit/s
  - `abr`: Average audio bitrate in KBit/s
@@ -1531,11 +1540,11 @@ The available fields are:
  
 **Deprecation warning**: Many of these fields have (currently undocumented) aliases, that may be removed in a future version. It is recommended to use only the documented field names.
 
-All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. Eg: `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred 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 preferred 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.
+All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. E.g. `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred value for the fields, separated by a `:`. E.g. `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 preferred values, the first for video and the second for audio. E.g. `+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. E.g. `filesize~1G` prefers the format with filesize closest to 1 GiB.
 
-The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,codec:vp9.2,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
+The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
 
-Note that the default has `codec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. dolby vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.
+Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. dolby vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.
 
 If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all respects. 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`.
 
@@ -1676,9 +1685,9 @@ Note that any field created by this can be used in the [output template](#output
 
 This option also has a few special uses:
 
-* You can download an additional URL based on the metadata of the currently downloaded video. To do this, set the field `additional_urls` to the URL that you want to download. Eg: `--parse-metadata "description:(?P<additional_urls>https?://www\.vimeo\.com/\d+)` will download the first vimeo video found in the description
+* You can download an additional URL based on the metadata of the currently downloaded video. To do this, set the field `additional_urls` to the URL that you want to download. E.g. `--parse-metadata "description:(?P<additional_urls>https?://www\.vimeo\.com/\d+)` will download the first vimeo video found in the description
 
-* You can use this to change 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. For example, you can use this to set a different "description" and "synopsis". To modify the metadata of individual streams, use the `meta<n>_` prefix (Eg: `meta1_language`). Any value set to the `meta_` field will overwrite all default values.
+* You can use this to change 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". To modify the metadata of individual streams, use the `meta<n>_` prefix (e.g. `meta1_language`). Any value set to the `meta_` field will overwrite all default values.
 
 **Note**: Metadata modification happens before format selection, post-extraction and other post-processing operations. Some fields may be added or changed during these steps, overriding your changes.
 
@@ -1737,21 +1746,19 @@ $ yt-dlp --replace-in-metadata "title,uploader" "[ _]" "-"
 
 # EXTRACTOR ARGUMENTS
 
-Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. Eg: `--extractor-args "youtube:player-client=android_embedded,web;include_live_dash" --extractor-args "funimation:version=uncut"`
+Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;include_live_dash" --extractor-args "funimation:version=uncut"`
 
 The following extractors use this feature:
 
 #### youtube
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (Eg: `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
+* `player_client`: Clients to extract video data from. The main clients are `web`, `android` and `ios` with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb` and `tv_embedded` (agegate bypass) with no variants. By default, `android,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly the music variants are added for `music.youtube.com` urls. You can use `all` to use all the clients, and `default` for the default clients.
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
 * `include_live_dash`: Include live dash formats even without `--live-from-start` (These formats don't download properly)
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
 * `max_comments`: Limit the amount of comments to gather. Comma-separated list of integers representing `max-comments,max-parents,max-replies,max-replies-per-thread`. Default is `all,all,all,all`
     * E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
-* `innertube_host`: Innertube API host to use for all API requests 
+* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
-  * e.g. `studio.youtube.com`, `youtubei.googleapis.com`
-  * Note: Cookies exported from `www.youtube.com` will not work with hosts other than `*.youtube.com`
 * `innertube_key`: Innertube API key to use for all API requests
 
 #### youtubetab (YouTube playlists, channels, feeds, etc.)
@@ -1759,17 +1766,16 @@ The following extractors use this feature:
 * `approximate_date`: Extract approximate `upload_date` in flat-playlist. This may cause date-based filters to be slightly off
 
 #### funimation
-* `language`: Languages to extract. Eg: `funimation:language=english,japanese`
+* `language`: Languages to extract, e.g. `funimation:language=english,japanese`
 * `version`: The video version to extract - `uncut` or `simulcast`
 
 #### crunchyroll
-* `language`: Languages to extract. Eg: `crunchyroll:language=jaJp`
+* `language`: Languages to extract, e.g. `crunchyroll:language=jaJp`
-* `hardsub`: Which hard-sub versions to extract. Eg: `crunchyroll:hardsub=None,enUS`
+* `hardsub`: Which hard-sub versions to extract, e.g. `crunchyroll:hardsub=None,enUS`
 
 #### crunchyrollbeta
-* `format`: Which stream type(s) to extract. Default is `adaptive_hls` Eg: `crunchyrollbeta:format=vo_adaptive_hls`
+* `format`: Which stream type(s) to extract (default: `adaptive_hls`). Potentially useful values include `adaptive_hls`, `adaptive_dash`, `vo_adaptive_hls`, `vo_adaptive_dash`, `download_hls`, `download_dash`, `multitrack_adaptive_hls_v2`
-    * Potentially useful values include `adaptive_hls`, `adaptive_dash`, `vo_adaptive_hls`, `vo_adaptive_dash`, `download_hls`, `trailer_hls`, `trailer_dash`
+* `hardsub`: Preference order for which hardsub versions to extract (default: `None` = no hardsubs), e.g. `crunchyrollbeta:hardsub=en-US,None`
-* `hardsub`: Preference order for which hardsub versions to extract. Default is `None` (no hardsubs). Eg: `crunchyrollbeta:hardsub=en-US,None`
 
 #### vikichannel
 * `video_types`: Types of videos to download - one or more of `episodes`, `movies`, `clips`, `trailers`
@@ -1789,11 +1795,11 @@ The following extractors use this feature:
 * `dr`: dynamic range to ignore - one or more of `sdr`, `hdr10`, `dv`
 
 #### tiktok
-* `app_version`: App version to call mobile APIs with - should be set along with `manifest_app_version`. (e.g. `20.2.1`)
+* `app_version`: App version to call mobile APIs with - should be set along with `manifest_app_version`, e.g. `20.2.1`
-* `manifest_app_version`: Numeric app version to call mobile APIs with. (e.g. `221`)
+* `manifest_app_version`: Numeric app version to call mobile APIs with, e.g. `221`
 
 #### rokfinchannel
-* `tab`: Which tab to download. One of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks`. (E.g. `rokfinchannel:tab=streams`)
+* `tab`: Which tab to download - one of `new`, `top`, `videos`, `podcasts`, `streams`, `stacks`
 
 
 NOTE: These options may be changed/removed in the future without concern for backward compatibility
@@ -2057,7 +2063,7 @@ While these options still work, their use is not recommended since there are oth
     --all-formats                    -f all
     --all-subs                       --sub-langs all --write-subs
     --print-json                     -j --no-simulate
-    --autonumber-size NUMBER         Use string formatting. Eg: %(autonumber)03d
+    --autonumber-size NUMBER         Use string formatting, e.g. %(autonumber)03d
     --autonumber-start NUMBER        Use internal field formatting like %(autonumber+NUMBER)s
     --id                             -o "%(id)s.%(ext)s"
     --metadata-from-title FORMAT     --parse-metadata "%(title)s:FORMAT"
@@ -2125,6 +2131,7 @@ These options may no longer work as intended
     --no-include-ads                 Default
     --write-annotations              No supported site has annotations now
     --no-write-annotations           Default
+    --compat-options seperate-video-versions  No longer needed
 
 #### Removed
 These options were deprecated since 2014 and have now been entirely removed

devscripts/__init__.py

@@ -0,0 +1 @@
+# Empty file needed to make devscripts.utils properly importable from outside

devscripts/lazy_load_template.py

@@ -9,11 +9,13 @@ from ..utils import (
     write_string,
 )
 
+# These bloat the lazy_extractors, so allow them to passthrough silently
+ALLOWED_CLASSMETHODS = {'get_testcases', 'extract_from_webpage'}
+
 
 class LazyLoadMetaClass(type):
     def __getattr__(cls, name):
-        # "_TESTS" bloat the lazy_extractors
+        if '_real_class' not in cls.__dict__ and name not in ALLOWED_CLASSMETHODS:
-        if '_real_class' not in cls.__dict__ and name != 'get_testcases':
             write_string(
                 'WARNING: Falling back to normal extractor since lazy extractor '
                 f'{cls.__name__} does not have attribute {name}{bug_reports_message()}\n')

devscripts/make_issue_template.py

@@ -7,30 +7,69 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-import optparse
+import re
 
+from devscripts.utils import (
+    get_filename_args,
+    read_file,
+    read_version,
+    write_file,
+)
 
-def read(fname):
+VERBOSE_TMPL = '''
-    with open(fname, encoding='utf-8') as f:
+  - type: checkboxes
-        return f.read()
+    id: verbose
+    attributes:
+      label: Provide verbose output that clearly demonstrates the problem
+      options:
+        - label: Run **your** yt-dlp command with **-vU** flag added (`yt-dlp -vU <your command line>`)
+          required: true
+        - label: Copy the WHOLE output (starting with `[debug] Command-line config`) and insert it below
+          required: true
+  - type: textarea
+    id: log
+    attributes:
+      label: Complete Verbose Output
+      description: |
+        It should start like this:
+      placeholder: |
+        [debug] Command-line config: ['-vU', 'test:youtube']
+        [debug] Portable config "yt-dlp.conf": ['-i']
+        [debug] Encodings: locale cp65001, fs utf-8, pref cp65001, out utf-8, error utf-8, screen utf-8
+        [debug] yt-dlp version %(version)s [9d339c4] (win32_exe)
+        [debug] Python 3.8.10 (CPython 64bit) - Windows-10-10.0.22000-SP0
+        [debug] Checking exe version: ffmpeg -bsfs
+        [debug] Checking exe version: ffprobe -bsfs
+        [debug] exe versions: ffmpeg N-106550-g072101bd52-20220410 (fdk,setts), ffprobe N-106624-g391ce570c8-20220415, phantomjs 2.1.1
+        [debug] Optional libraries: Cryptodome-3.15.0, brotli-1.0.9, certifi-2022.06.15, mutagen-1.45.1, sqlite3-2.6.0, websockets-10.3
+        [debug] Proxy map: {}
+        [debug] Fetching release info: https://api.github.com/repos/yt-dlp/yt-dlp/releases/latest
+        Latest version: %(version)s, Current version: %(version)s
+        yt-dlp is up to date (%(version)s)
+        <more lines>
+      render: shell
+    validations:
+      required: true
+'''.strip()
 
-
+NO_SKIP = '''
-# Get the version without importing the package
+  - type: checkboxes
-def read_version(fname):
+    attributes:
-    exec(compile(read(fname), fname, 'exec'))
+      label: DO NOT REMOVE OR SKIP THE ISSUE TEMPLATE
-    return locals()['__version__']
+      description: Fill all fields even if you think it is irrelevant for the issue
+      options:
+        - label: I understand that I will be **blocked** if I remove or skip any mandatory\\* field
+          required: true
+'''.strip()
 
 
 def main():
-    parser = optparse.OptionParser(usage='%prog INFILE OUTFILE')
+    fields = {'version': read_version(), 'no_skip': NO_SKIP}
-    options, args = parser.parse_args()
+    fields['verbose'] = VERBOSE_TMPL % fields
-    if len(args) != 2:
+    fields['verbose_optional'] = re.sub(r'(\n\s+validations:)?\n\s+required: true', '', fields['verbose'])
-        parser.error('Expected an input and an output filename')
 
-    infile, outfile = args
+    infile, outfile = get_filename_args(has_infile=True)
-    with open(outfile, 'w', encoding='utf-8') as outf:
+    write_file(outfile, read_file(infile) % fields)
-        outf.write(
-            read(infile) % {'version': read_version('yt_dlp/version.py')})
 
 
 if __name__ == '__main__':

devscripts/make_lazy_extractors.py

@@ -7,11 +7,12 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-import optparse
 from inspect import getsource
 
+from devscripts.utils import get_filename_args, read_file, write_file
+
 NO_ATTR = object()
-STATIC_CLASS_PROPERTIES = ['IE_NAME', 'IE_DESC', 'SEARCH_KEY', '_WORKING', '_NETRC_MACHINE', 'age_limit']
+STATIC_CLASS_PROPERTIES = ['IE_NAME', 'IE_DESC', 'SEARCH_KEY', '_VALID_URL', '_WORKING', '_NETRC_MACHINE', 'age_limit']
 CLASS_METHODS = [
     'ie_key', 'working', 'description', 'suitable', '_match_valid_url', '_match_id', 'get_temp_id', 'is_suitable'
 ]
@@ -19,17 +20,11 @@ IE_TEMPLATE = '''
 class {name}({bases}):
     _module = {module!r}
 '''
-with open('devscripts/lazy_load_template.py', encoding='utf-8') as f:
+MODULE_TEMPLATE = read_file('devscripts/lazy_load_template.py')
-    MODULE_TEMPLATE = f.read()
 
 
 def main():
-    parser = optparse.OptionParser(usage='%prog [OUTFILE.py]')
+    lazy_extractors_filename = get_filename_args(default_outfile='yt_dlp/extractor/lazy_extractors.py')
-    args = parser.parse_args()[1] or ['yt_dlp/extractor/lazy_extractors.py']
-    if len(args) != 1:
-        parser.error('Expected only an output filename')
-
-    lazy_extractors_filename = args[0]
     if os.path.exists(lazy_extractors_filename):
         os.remove(lazy_extractors_filename)
 
@@ -46,8 +41,7 @@ def main():
         *build_ies(_ALL_CLASSES, (InfoExtractor, SearchInfoExtractor), DummyInfoExtractor),
     ))
 
-    with open(lazy_extractors_filename, 'wt', encoding='utf-8') as f:
+    write_file(lazy_extractors_filename, f'{module_src}\n')
-        f.write(f'{module_src}\n')
 
 
 def get_all_ies():
@@ -94,7 +88,7 @@ def sort_ies(ies, ignored_bases):
         for c in classes[:]:
             bases = set(c.__bases__) - {object, *ignored_bases}
             restart = False
-            for b in bases:
+            for b in sorted(bases, key=lambda x: x.__name__):
                 if b not in classes and b not in returned_classes:
                     assert b.__name__ != 'GenericIE', 'Cannot inherit from GenericIE'
                     classes.insert(0, b)
@@ -116,11 +110,6 @@ def build_lazy_ie(ie, name, attr_base):
     }.get(base.__name__, base.__name__) for base in ie.__bases__)
 
     s = IE_TEMPLATE.format(name=name, module=ie.__module__, bases=bases)
-    valid_url = getattr(ie, '_VALID_URL', None)
-    if not valid_url and hasattr(ie, '_make_valid_url'):
-        valid_url = ie._make_valid_url()
-    if valid_url:
-        s += f'    _VALID_URL = {valid_url!r}\n'
     return s + '\n'.join(extra_ie_code(ie, attr_base))
 
 

devscripts/make_readme.py

@@ -5,10 +5,17 @@ yt-dlp --help | make_readme.py
 This must be run in a console of correct width
 """
 
+# Allow direct execution
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
 
 import functools
 import re
-import sys
+
+from devscripts.utils import read_file, write_file
 
 README_FILE = 'README.md'
 
@@ -38,6 +45,10 @@ switch_col_width = len(re.search(r'(?m)^\s{5,}', options).group())
 delim = f'\n{" " * switch_col_width}'
 
 PATCHES = (
+    (   # Standardize update message
+        r'(?m)^(    -U, --update\s+).+(\n    \s.+)*$',
+        r'\1Update this program to the latest version',
+    ),
     (  # Headings
         r'(?m)^  (\w.+\n)(    (?=\w))?',
         r'## \1'
@@ -63,12 +74,10 @@ PATCHES = (
     ),
 )
 
-with open(README_FILE, encoding='utf-8') as f:
+readme = read_file(README_FILE)
-    readme = f.read()
 
-with open(README_FILE, 'w', encoding='utf-8') as f:
+write_file(README_FILE, ''.join((
-    f.write(''.join((
+    take_section(readme, end=f'## {OPTIONS_START}'),
-        take_section(readme, end=f'## {OPTIONS_START}'),
+    functools.reduce(apply_patch, PATCHES, options),
-        functools.reduce(apply_patch, PATCHES, options),
+    take_section(readme, f'# {OPTIONS_END}'),
-        take_section(readme, f'# {OPTIONS_END}'),
+)))
-    )))

devscripts/make_supportedsites.py

@@ -7,21 +7,13 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
-import optparse
+from devscripts.utils import get_filename_args, write_file
-
 from yt_dlp.extractor import list_extractor_classes
 
 
 def main():
-    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
-    _, args = parser.parse_args()
-    if len(args) != 1:
-        parser.error('Expected an output filename')
-
     out = '\n'.join(ie.description() for ie in list_extractor_classes() if ie.IE_DESC is not False)
-
+    write_file(get_filename_args(), f'# Supported sites\n{out}\n')
-    with open(args[0], 'w', encoding='utf-8') as outf:
-        outf.write(f'# Supported sites\n{out}\n')
 
 
 if __name__ == '__main__':

devscripts/prepare_manpage.py

@@ -1,9 +1,22 @@
 #!/usr/bin/env python3
 
-import optparse
+# Allow direct execution
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
 import os.path
 import re
 
+from devscripts.utils import (
+    compose_functions,
+    get_filename_args,
+    read_file,
+    write_file,
+)
+
 ROOT_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
 README_FILE = os.path.join(ROOT_DIR, 'README.md')
 
@@ -22,25 +35,6 @@ yt\-dlp \- A youtube-dl fork with additional features and patches
 '''
 
 
-def main():
-    parser = optparse.OptionParser(usage='%prog OUTFILE.md')
-    _, args = parser.parse_args()
-    if len(args) != 1:
-        parser.error('Expected an output filename')
-
-    outfile, = args
-
-    with open(README_FILE, encoding='utf-8') as f:
-        readme = f.read()
-
-    readme = filter_excluded_sections(readme)
-    readme = move_sections(readme)
-    readme = filter_options(readme)
-
-    with open(outfile, 'w', encoding='utf-8') as outf:
-        outf.write(PREFIX + readme)
-
-
 def filter_excluded_sections(readme):
     EXCLUDED_SECTION_BEGIN_STRING = re.escape('<!-- MANPAGE: BEGIN EXCLUDED SECTION -->')
     EXCLUDED_SECTION_END_STRING = re.escape('<!-- MANPAGE: END EXCLUDED SECTION -->')
@@ -92,5 +86,12 @@ def filter_options(readme):
     return readme.replace(section, options, 1)
 
 
+TRANSFORM = compose_functions(filter_excluded_sections, move_sections, filter_options)
+
+
+def main():
+    write_file(get_filename_args(), PREFIX + TRANSFORM(read_file(README_FILE)))
+
+
 if __name__ == '__main__':
     main()

devscripts/set-variant.py

@@ -0,0 +1,36 @@
+#!/usr/bin/env python3
+
+# Allow direct execution
+import os
+import sys
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+
+
+import argparse
+import functools
+import re
+
+from devscripts.utils import compose_functions, read_file, write_file
+
+VERSION_FILE = 'yt_dlp/version.py'
+
+
+def parse_options():
+    parser = argparse.ArgumentParser(description='Set the build variant of the package')
+    parser.add_argument('variant', help='Name of the variant')
+    parser.add_argument('-M', '--update-message', default=None, help='Message to show in -U')
+    return parser.parse_args()
+
+
+def property_setter(name, value):
+    return functools.partial(re.sub, rf'(?m)^{name}\s*=\s*.+$', f'{name} = {value!r}')
+
+
+opts = parse_options()
+transform = compose_functions(
+    property_setter('VARIANT', opts.variant),
+    property_setter('UPDATE_HINT', opts.update_message)
+)
+
+write_file(VERSION_FILE, transform(read_file(VERSION_FILE)))

devscripts/update-formulae.py

@@ -1,5 +1,10 @@
 #!/usr/bin/env python3
 
+"""
+Usage: python3 ./devscripts/update-formulae.py <path-to-formulae-rb> <version>
+version can be either 0-aligned (yt-dlp version) or normalized (PyPi version)
+"""
+
 # Allow direct execution
 import os
 import sys
@@ -11,8 +16,7 @@ import json
 import re
 import urllib.request
 
-# usage: python3 ./devscripts/update-formulae.py <path-to-formulae-rb> <version>
+from devscripts.utils import read_file, write_file
-# version can be either 0-aligned (yt-dlp version) or normalized (PyPl version)
 
 filename, version = sys.argv[1:]
 
@@ -27,11 +31,9 @@ tarball_file = next(x for x in pypi_release['urls'] if x['filename'].endswith('.
 sha256sum = tarball_file['digests']['sha256']
 url = tarball_file['url']
 
-with open(filename) as r:
+formulae_text = read_file(filename)
-    formulae_text = r.read()
 
-formulae_text = re.sub(r'sha256 "[0-9a-f]*?"', 'sha256 "%s"' % sha256sum, formulae_text)
+formulae_text = re.sub(r'sha256 "[0-9a-f]*?"', 'sha256 "%s"' % sha256sum, formulae_text, count=1)
-formulae_text = re.sub(r'url "[^"]*?"', 'url "%s"' % url, formulae_text)
+formulae_text = re.sub(r'url "[^"]*?"', 'url "%s"' % url, formulae_text, count=1)
 
-with open(filename, 'w') as w:
+write_file(filename, formulae_text)
-    w.write(formulae_text)

devscripts/update-version.py

@@ -7,32 +7,35 @@ import sys
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
+import contextlib
 import subprocess
 import sys
 from datetime import datetime
 
-with open('yt_dlp/version.py') as f:
+from devscripts.utils import read_version, write_file
-    exec(compile(f.read(), 'yt_dlp/version.py', 'exec'))
-old_version = locals()['__version__']
 
-old_version_list = old_version.split('.')
 
-old_ver = '.'.join(old_version_list[:3])
+def get_new_version(revision):
-old_rev = old_version_list[3] if len(old_version_list) > 3 else ''
+    version = datetime.utcnow().strftime('%Y.%m.%d')
 
-ver = datetime.utcnow().strftime("%Y.%m.%d")
+    if revision:
+        assert revision.isdigit(), 'Revision must be a number'
+    else:
+        old_version = read_version().split('.')
+        if version.split('.') == old_version[:3]:
+            revision = str(int((old_version + [0])[3]) + 1)
 
-rev = (sys.argv[1:] or [''])[0]  # Use first argument, if present as revision number
+    return f'{version}.{revision}' if revision else version
-if not rev:
-    rev = str(int(old_rev or 0) + 1) if old_ver == ver else ''
 
-VERSION = '.'.join((ver, rev)) if rev else ver
 
-try:
+def get_git_head():
-    sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE)
+    with contextlib.suppress(Exception):
-    GIT_HEAD = sp.communicate()[0].decode().strip() or None
+        sp = subprocess.Popen(['git', 'rev-parse', '--short', 'HEAD'], stdout=subprocess.PIPE)
-except Exception:
+        return sp.communicate()[0].decode().strip() or None
-    GIT_HEAD = None
+
+
+VERSION = get_new_version((sys.argv + [''])[1])
+GIT_HEAD = get_git_head()
 
 VERSION_FILE = f'''\
 # Autogenerated by devscripts/update-version.py
@@ -40,10 +43,12 @@ VERSION_FILE = f'''\
 __version__ = {VERSION!r}
 
 RELEASE_GIT_HEAD = {GIT_HEAD!r}
+
+VARIANT = None
+
+UPDATE_HINT = None
 '''
 
-with open('yt_dlp/version.py', 'wt') as f:
+write_file('yt_dlp/version.py', VERSION_FILE)
-    f.write(VERSION_FILE)
+print(f'::set-output name=ytdlp_version::{VERSION}')
-
-print('::set-output name=ytdlp_version::' + VERSION)
 print(f'\nVersion = {VERSION}, Git HEAD = {GIT_HEAD}')

devscripts/utils.py

@@ -0,0 +1,35 @@
+import argparse
+import functools
+
+
+def read_file(fname):
+    with open(fname, encoding='utf-8') as f:
+        return f.read()
+
+
+def write_file(fname, content):
+    with open(fname, 'w', encoding='utf-8') as f:
+        return f.write(content)
+
+
+# Get the version without importing the package
+def read_version(fname='yt_dlp/version.py'):
+    exec(compile(read_file(fname), fname, 'exec'))
+    return locals()['__version__']
+
+
+def get_filename_args(has_infile=False, default_outfile=None):
+    parser = argparse.ArgumentParser()
+    if has_infile:
+        parser.add_argument('infile', help='Input file')
+    kwargs = {'nargs': '?', 'default': default_outfile} if default_outfile else {}
+    parser.add_argument('outfile', **kwargs, help='Output file')
+
+    opts = parser.parse_args()
+    if has_infile:
+        return opts.infile, opts.outfile
+    return opts.outfile
+
+
+def compose_functions(*functions):
+    return lambda x: functools.reduce(lambda y, f: f(y), functions, x)

pyinst.py

@@ -1,24 +1,32 @@
 #!/usr/bin/env python3
 
+# Allow direct execution
 import os
-import platform
 import sys
 
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
+import platform
+
 from PyInstaller.__main__ import run as run_pyinstaller
 
-OS_NAME, ARCH = sys.platform, platform.architecture()[0][:2]
+from devscripts.utils import read_version
+
+OS_NAME, MACHINE, ARCH = sys.platform, platform.machine(), platform.architecture()[0][:2]
+if MACHINE in ('x86_64', 'AMD64') or ('i' in MACHINE and '86' in MACHINE):
+    # NB: Windows x86 has MACHINE = AMD64 irrespective of bitness
+    MACHINE = 'x86' if ARCH == '32' else ''
 
 
 def main():
-    opts = parse_options()
+    opts, version = parse_options(), read_version()
-    version = read_version('yt_dlp/version.py')
 
     onedir = '--onedir' in opts or '-D' in opts
     if not onedir and '-F' not in opts and '--onefile' not in opts:
         opts.append('--onefile')
 
     name, final_file = exe(onedir)
-    print(f'Building yt-dlp v{version} {ARCH}bit for {OS_NAME} with options {opts}')
+    print(f'Building yt-dlp v{version} for {OS_NAME} {platform.machine()} with options {opts}')
     print('Remember to update the version using  "devscripts/update-version.py"')
     if not os.path.isfile('yt_dlp/extractor/lazy_extractors.py'):
         print('WARNING: Building without lazy_extractors. Run  '
@@ -30,9 +38,6 @@ def main():
         '--icon=devscripts/logo.ico',
         '--upx-exclude=vcruntime140.dll',
         '--noconfirm',
-        # NB: Modules that are only imported dynamically must be added here.
-        # --collect-submodules may not work correctly if user has a yt-dlp installed via PIP
-        '--hidden-import=yt_dlp.compat._legacy',
         *dependency_options(),
         *opts,
         'yt_dlp/__main__.py',
@@ -53,19 +58,12 @@ def parse_options():
     return opts
 
 
-# Get the version from yt_dlp/version.py without importing the package
-def read_version(fname):
-    with open(fname, encoding='utf-8') as f:
-        exec(compile(f.read(), fname, 'exec'))
-        return locals()['__version__']
-
-
 def exe(onedir):
     """@returns (name, path)"""
     name = '_'.join(filter(None, (
         'yt-dlp',
         {'win32': '', 'darwin': 'macos'}.get(OS_NAME, OS_NAME),
-        ARCH == '32' and 'x86'
+        MACHINE
     )))
     return name, ''.join(filter(None, (
         'dist/',
@@ -122,7 +120,7 @@ def windows_set_version(exe, version):
     )
 
     version_list = version_to_list(version)
-    suffix = '_x86' if ARCH == '32' else ''
+    suffix = MACHINE and f'_{MACHINE}'
     SetVersion(exe, VSVersionInfo(
         ffi=FixedFileInfo(
             filevers=version_list,
@@ -136,9 +134,9 @@ def windows_set_version(exe, version):
         ),
         kids=[
             StringFileInfo([StringTable('040904B0', [
-                StringStruct('Comments', 'yt-dlp%s Command Line Interface.' % suffix),
+                StringStruct('Comments', 'yt-dlp%s Command Line Interface' % suffix),
                 StringStruct('CompanyName', 'https://github.com/yt-dlp'),
-                StringStruct('FileDescription', 'yt-dlp%s' % (' (32 Bit)' if ARCH == '32' else '')),
+                StringStruct('FileDescription', 'yt-dlp%s' % (MACHINE and f' ({MACHINE})')),
                 StringStruct('FileVersion', version),
                 StringStruct('InternalName', f'yt-dlp{suffix}'),
                 StringStruct('LegalCopyright', 'pukkandan.ytdlp@gmail.com | UNLICENSE'),

setup.cfg

@@ -31,7 +31,7 @@ setenv =
 
 
 [isort]
-py_version = 36
+py_version = 37
 multi_line_output = VERTICAL_HANGING_INDENT
 line_length = 80
 reverse_relative = true

setup.py

@@ -1,6 +1,7 @@
 #!/usr/bin/env python3
 
 import os.path
+import subprocess
 import sys
 import warnings
 
@@ -10,38 +11,39 @@ try:
 except ImportError:
     from distutils.core import Command, setup
     setuptools_available = False
-from distutils.spawn import spawn
 
+from devscripts.utils import read_file, read_version
 
-def read(fname):
+VERSION = read_version()
-    with open(fname, encoding='utf-8') as f:
-        return f.read()
-
-
-# Get the version from yt_dlp/version.py without importing the package
-def read_version(fname):
-    exec(compile(read(fname), fname, 'exec'))
-    return locals()['__version__']
-
-
-VERSION = read_version('yt_dlp/version.py')
 
 DESCRIPTION = 'A youtube-dl fork with additional features and patches'
 
 LONG_DESCRIPTION = '\n\n'.join((
     'Official repository: <https://github.com/yt-dlp/yt-dlp>',
     '**PS**: Some links in this document will not work since this is a copy of the README.md from Github',
-    read('README.md')))
+    read_file('README.md')))
 
-REQUIREMENTS = read('requirements.txt').splitlines()
+REQUIREMENTS = read_file('requirements.txt').splitlines()
 
 
-if sys.argv[1:2] == ['py2exe']:
+def packages():
+    if setuptools_available:
+        return find_packages(exclude=('youtube_dl', 'youtube_dlc', 'test', 'ytdlp_plugins'))
+
+    return [
+        'yt_dlp', 'yt_dlp.extractor', 'yt_dlp.downloader', 'yt_dlp.postprocessor', 'yt_dlp.compat',
+        'yt_dlp.extractor.anvato_token_generator',
+    ]
+
+
+def py2exe_params():
     import py2exe  # noqa: F401
+
     warnings.warn(
         'py2exe builds do not support pycryptodomex and needs VC++14 to run. '
         'The recommended way is to use "pyinst.py" to build using pyinstaller')
-    params = {
+
+    return {
         'console': [{
             'script': './yt_dlp/__main__.py',
             'dest_base': 'yt-dlp',
@@ -50,6 +52,7 @@ if sys.argv[1:2] == ['py2exe']:
             'comments': LONG_DESCRIPTION.split('\n')[0],
             'product_name': 'yt-dlp',
             'product_version': VERSION,
+            'icon_resources': [(1, 'devscripts/logo.ico')],
         }],
         'options': {
             'py2exe': {
@@ -66,7 +69,8 @@ if sys.argv[1:2] == ['py2exe']:
         'zipfile': None
     }
 
-else:
+
+def build_params():
     files_spec = [
         ('share/bash-completion/completions', ['completions/bash/yt-dlp']),
         ('share/zsh/site-functions', ['completions/zsh/_yt-dlp']),
@@ -74,25 +78,23 @@ else:
         ('share/doc/yt_dlp', ['README.txt']),
         ('share/man/man1', ['yt-dlp.1'])
     ]
-    root = os.path.dirname(os.path.abspath(__file__))
     data_files = []
     for dirname, files in files_spec:
         resfiles = []
         for fn in files:
             if not os.path.exists(fn):
-                warnings.warn('Skipping file %s since it is not present. Try running `make pypi-files` first' % fn)
+                warnings.warn(f'Skipping file {fn} since it is not present. Try running " make pypi-files " first')
             else:
                 resfiles.append(fn)
         data_files.append((dirname, resfiles))
 
-    params = {
+    params = {'data_files': data_files}
-        'data_files': data_files,
-    }
 
     if setuptools_available:
         params['entry_points'] = {'console_scripts': ['yt-dlp = yt_dlp:main']}
     else:
         params['scripts'] = ['yt-dlp']
+    return params
 
 
 class build_lazy_extractors(Command):
@@ -106,16 +108,13 @@ class build_lazy_extractors(Command):
         pass
 
     def run(self):
-        spawn([sys.executable, 'devscripts/make_lazy_extractors.py', 'yt_dlp/extractor/lazy_extractors.py'],
+        if self.dry_run:
-              dry_run=self.dry_run)
+            print('Skipping build of lazy extractors in dry run mode')
-
+            return
-
+        subprocess.run([sys.executable, 'devscripts/make_lazy_extractors.py'])
-if setuptools_available:
-    packages = find_packages(exclude=('youtube_dl', 'youtube_dlc', 'test', 'ytdlp_plugins'))
-else:
-    packages = ['yt_dlp', 'yt_dlp.downloader', 'yt_dlp.extractor', 'yt_dlp.postprocessor']
 
 
+params = py2exe_params() if sys.argv[1:2] == ['py2exe'] else build_params()
 setup(
     name='yt-dlp',
     version=VERSION,
@@ -125,8 +124,9 @@ setup(
     long_description=LONG_DESCRIPTION,
     long_description_content_type='text/markdown',
     url='https://github.com/yt-dlp/yt-dlp',
-    packages=packages,
+    packages=packages(),
     install_requires=REQUIREMENTS,
+    python_requires='>=3.7',
     project_urls={
         'Documentation': 'https://github.com/yt-dlp/yt-dlp#readme',
         'Source': 'https://github.com/yt-dlp/yt-dlp',
@@ -138,7 +138,6 @@ setup(
         'Development Status :: 5 - Production/Stable',
         'Environment :: Console',
         'Programming Language :: Python',
-        'Programming Language :: Python :: 3.6',
         'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9',
@@ -150,8 +149,6 @@ setup(
         'License :: Public Domain',
         'Operating System :: OS Independent',
     ],
-    python_requires='>=3.6',
-
     cmdclass={'build_lazy_extractors': build_lazy_extractors},
     **params
 )

supportedsites.md

@@ -4,6 +4,7 @@
  - **17live**
  - **17live:clip**
  - **1tv**: Первый канал
+ - **20.detik.com**
  - **20min**
  - **23video**
  - **247sports**
@@ -17,7 +18,7 @@
  - **8tracks**
  - **91porn**
  - **9c9media**
- - **9gag**
+ - **9gag**: 9GAG
  - **9now.com.au**
  - **abc.net.au**
  - **abc.net.au:iview**
@@ -31,6 +32,8 @@
  - **AcademicEarth:Course**
  - **acast**
  - **acast:channel**
+ - **AcFunBangumi**
+ - **AcFunVideo**
  - **ADN**: [<abbr title="netrc machine"><em>animedigitalnetwork</em></abbr>] Anime Digital Network
  - **AdobeConnect**
  - **adobetv**
@@ -61,6 +64,7 @@
  - **AmericasTestKitchenSeason**
  - **AmHistoryChannel**
  - **anderetijden**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
+ - **Angel**
  - **AnimalPlanet**
  - **AnimeOnDemand**: [<abbr title="netrc machine"><em>animeondemand</em></abbr>]
  - **ant1newsgr:article**: ant1news.gr articles
@@ -94,6 +98,8 @@
  - **ATVAt**
  - **AudiMedia**
  - **AudioBoom**
+ - **Audiodraft:custom**
+ - **Audiodraft:generic**
  - **audiomack**
  - **audiomack:album**
  - **Audius**: Audius.co
@@ -182,6 +188,7 @@
  - **Camdemy**
  - **CamdemyFolder**
  - **CamModels**
+ - **CamtasiaEmbed**
  - **CamWithHer**
  - **CanalAlpha**
  - **canalc2.tv**
@@ -205,6 +212,7 @@
  - **CCMA**
  - **CCTV**: 央视网
  - **CDA**
+ - **Cellebrite**
  - **CeskaTelevize**
  - **CGTN**
  - **channel9**: Channel 9
@@ -226,6 +234,7 @@
  - **Clippit**
  - **ClipRs**
  - **Clipsyndicate**
+ - **ClipYouEmbed**
  - **CloserToTruth**
  - **CloudflareStream**
  - **Cloudy**
@@ -371,6 +380,7 @@
  - **ExtremeTube**
  - **EyedoTV**
  - **facebook**: [<abbr title="netrc machine"><em>facebook</em></abbr>]
+ - **facebook:reel**
  - **FacebookPluginsVideo**
  - **fancode:live**: [<abbr title="netrc machine"><em>fancode</em></abbr>]
  - **fancode:vod**: [<abbr title="netrc machine"><em>fancode</em></abbr>]
@@ -467,6 +477,7 @@
  - **gronkh:feed**
  - **gronkh:vods**
  - **Groupon**
+ - **Harpodeon**
  - **hbo**
  - **HearThisAt**
  - **Heise**
@@ -485,6 +496,7 @@
  - **hitbox:live**
  - **HitRecord**
  - **hketv**: 香港教育局教育電視 (HKETV) Educational Television, Hong Kong Educational Bureau
+ - **Holodex**
  - **HotNewHipHop**
  - **hotstar**
  - **hotstar:playlist**
@@ -496,6 +508,7 @@
  - **HRTiPlaylist**: [<abbr title="netrc machine"><em>hrti</em></abbr>]
  - **HSEProduct**
  - **HSEShow**
+ - **html5**
  - **Huajiao**: 花椒直播
  - **HuffPost**: Huffington Post
  - **Hungama**
@@ -503,6 +516,7 @@
  - **HungamaSong**
  - **huya:live**: huya.com
  - **Hypem**
+ - **Hytale**
  - **Icareus**
  - **ign.com**
  - **IGNArticle**
@@ -566,6 +580,7 @@
  - **KickStarter**
  - **KinjaEmbed**
  - **KinoPoisk**
+ - **KompasVideo**
  - **KonserthusetPlay**
  - **Koo**
  - **KrasView**: Красвью
@@ -615,6 +630,7 @@
  - **linkedin:learning**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **linkedin:learning:course**: [<abbr title="netrc machine"><em>linkedin</em></abbr>]
  - **LinuxAcademy**: [<abbr title="netrc machine"><em>linuxacademy</em></abbr>]
+ - **Liputan6**
  - **LiTV**
  - **LiveJournal**
  - **livestream**
@@ -694,10 +710,12 @@
  - **mixcloud:playlist**
  - **mixcloud:user**
  - **MLB**
+ - **MLBTV**: [<abbr title="netrc machine"><em>mlb</em></abbr>]
  - **MLBVideo**
  - **MLSSoccer**
  - **Mnet**
  - **MNetTV**: [<abbr title="netrc machine"><em>mnettv</em></abbr>]
+ - **MochaVideo**
  - **MoeVideo**: LetitBit video services: moevideo.net, playreplay.net and videochart.net
  - **Mofosex**
  - **MofosexEmbed**
@@ -706,9 +724,11 @@
  - **Motherless**
  - **MotherlessGroup**
  - **Motorsport**: motorsport.com
+ - **MotorTrend**
  - **MovieClips**
  - **MovieFap**
  - **Moviepilot**
+ - **MoviewPlay**
  - **Moviezine**
  - **MovingImage**
  - **MSN**
@@ -881,21 +901,10 @@
  - **openrec:capture**
  - **openrec:movie**
  - **OraTV**
- - **orf:burgenland**: Radio Burgenland
- - **orf:fm4**: radio FM4
  - **orf:fm4:story**: fm4.orf.at stories
  - **orf:iptv**: iptv.ORF.at
- - **orf:kaernten**: Radio Kärnten
+ - **orf:radio**
- - **orf:noe**: Radio Niederösterreich
- - **orf:oberoesterreich**: Radio Oberösterreich
- - **orf:oe1**: Radio Österreich 1
- - **orf:oe3**: Radio Österreich 3
- - **orf:salzburg**: Radio Salzburg
- - **orf:steiermark**: Radio Steiermark
- - **orf:tirol**: Radio Tirol
  - **orf:tvthek**: ORF TVthek
- - **orf:vorarlberg**: Radio Vorarlberg
- - **orf:wien**: Radio Wien
  - **OsnatelTV**: [<abbr title="netrc machine"><em>osnateltv</em></abbr>]
  - **OutsideTV**
  - **PacktPub**: [<abbr title="netrc machine"><em>packtpub</em></abbr>]
@@ -910,10 +919,11 @@
  - **ParamountNetwork**
  - **ParamountPlus**
  - **ParamountPlusSeries**
+ - **Parler**: Posts on parler.com
  - **parliamentlive.tv**: UK parliament videos
  - **Parlview**
  - **Patreon**
- - **PatreonUser**
+ - **PatreonCampaign**
  - **pbs**: Public Broadcasting Service (PBS) and member stations: PBS: Public Broadcasting Service, APT - Alabama Public Television (WBIQ), GPB/Georgia Public Broadcasting (WGTV), Mississippi Public Broadcasting (WMPN), Nashville Public Television (WNPT), WFSU-TV (WFSU), WSRE (WSRE), WTCI (WTCI), WPBA/Channel 30 (WPBA), Alaska Public Media (KAKM), Arizona PBS (KAET), KNME-TV/Channel 5 (KNME), Vegas PBS (KLVX), AETN/ARKANSAS ETV NETWORK (KETS), KET (WKLE), WKNO/Channel 10 (WKNO), LPB/LOUISIANA PUBLIC BROADCASTING (WLPB), OETA (KETA), Ozarks Public Television (KOZK), WSIU Public Broadcasting (WSIU), KEET TV (KEET), KIXE/Channel 9 (KIXE), KPBS San Diego (KPBS), KQED (KQED), KVIE Public Television (KVIE), PBS SoCal/KOCE (KOCE), ValleyPBS (KVPT), CONNECTICUT PUBLIC TELEVISION (WEDH), KNPB Channel 5 (KNPB), SOPTV (KSYS), Rocky Mountain PBS (KRMA), KENW-TV3 (KENW), KUED Channel 7 (KUED), Wyoming PBS (KCWC), Colorado Public Television / KBDI 12 (KBDI), KBYU-TV (KBYU), Thirteen/WNET New York (WNET), WGBH/Channel 2 (WGBH), WGBY (WGBY), NJTV Public Media NJ (WNJT), WLIW21 (WLIW), mpt/Maryland Public Television (WMPB), WETA Television and Radio (WETA), WHYY (WHYY), PBS 39 (WLVT), WVPT - Your Source for PBS and More! (WVPT), Howard University Television (WHUT), WEDU PBS (WEDU), WGCU Public Media (WGCU), WPBT2 (WPBT), WUCF TV (WUCF), WUFT/Channel 5 (WUFT), WXEL/Channel 42 (WXEL), WLRN/Channel 17 (WLRN), WUSF Public Broadcasting (WUSF), ETV (WRLK), UNC-TV (WUNC), PBS Hawaii - Oceanic Cable Channel 10 (KHET), Idaho Public Television (KAID), KSPS (KSPS), OPB (KOPB), KWSU/Channel 10 & KTNW/Channel 31 (KWSU), WILL-TV (WILL), Network Knowledge - WSEC/Springfield (WSEC), WTTW11 (WTTW), Iowa Public Television/IPTV (KDIN), Nine Network (KETC), PBS39 Fort Wayne (WFWA), WFYI Indianapolis (WFYI), Milwaukee Public Television (WMVS), WNIN (WNIN), WNIT Public Television (WNIT), WPT (WPNE), WVUT/Channel 22 (WVUT), WEIU/Channel 51 (WEIU), WQPT-TV (WQPT), WYCC PBS Chicago (WYCC), WIPB-TV (WIPB), WTIU (WTIU), CET  (WCET), ThinkTVNetwork (WPTD), WBGU-TV (WBGU), WGVU TV (WGVU), NET1 (KUON), Pioneer Public Television (KWCM), SDPB Television (KUSD), TPT (KTCA), KSMQ (KSMQ), KPTS/Channel 8 (KPTS), KTWU/Channel 11 (KTWU), East Tennessee PBS (WSJK), WCTE-TV (WCTE), WLJT, Channel 11 (WLJT), WOSU TV (WOSU), WOUB/WOUC (WOUB), WVPB (WVPB), WKYU-PBS (WKYU), KERA 13 (KERA), MPBN (WCBB), Mountain Lake PBS (WCFE), NHPTV (WENH), Vermont PBS (WETK), witf (WITF), WQED Multimedia (WQED), WMHT Educational Telecommunications (WMHT), Q-TV (WDCQ), WTVS Detroit Public TV (WTVS), CMU Public Television (WCMU), WKAR-TV (WKAR), WNMU-TV Public TV 13 (WNMU), WDSE - WRPT (WDSE), WGTE TV (WGTE), Lakeland Public Television (KAWE), KMOS-TV - Channels 6.1, 6.2 and 6.3 (KMOS), MontanaPBS (KUSM), KRWG/Channel 22 (KRWG), KACV (KACV), KCOS/Channel 13 (KCOS), WCNY/Channel 24 (WCNY), WNED (WNED), WPBS (WPBS), WSKG Public TV (WSKG), WXXI (WXXI), WPSU (WPSU), WVIA Public Media Studios (WVIA), WTVI (WTVI), Western Reserve PBS (WNEO), WVIZ/PBS ideastream (WVIZ), KCTS 9 (KCTS), Basin PBS (KPBT), KUHT / Channel 8 (KUHT), KLRN (KLRN), KLRU (KLRU), WTJX Channel 12 (WTJX), WCVE PBS (WCVE), KBTC Public Television (KBTC)
  - **PearVideo**
  - **PeekVids**
@@ -1021,12 +1031,14 @@
  - **radlive:channel**
  - **radlive:season**
  - **Rai**
+ - **RaiNews**
  - **RaiPlay**
  - **RaiPlayLive**
  - **RaiPlayPlaylist**
  - **RaiPlaySound**
  - **RaiPlaySoundLive**
  - **RaiPlaySoundPlaylist**
+ - **RaiSudtirol**
  - **RayWenderlich**
  - **RayWenderlichCourse**
  - **RBMARadio**
@@ -1063,15 +1075,19 @@
  - **RoosterTeethSeries**: [<abbr title="netrc machine"><em>roosterteeth</em></abbr>]
  - **RottenTomatoes**
  - **Rozhlas**
- - **RTBF**
+ - **RTBF**: [<abbr title="netrc machine"><em>rtbf</em></abbr>]
  - **RTDocumentry**
  - **RTDocumentryPlaylist**
  - **rte**: Raidió Teilifís Éireann TV
  - **rte:radio**: Raidió Teilifís Éireann radio
+ - **rtl.lu:article**
+ - **rtl.lu:tele-vod**
  - **rtl.nl**: rtl.nl and rtlxl.nl
  - **rtl2**
  - **rtl2:you**
  - **rtl2:you:series**
+ - **RTLLuLive**
+ - **RTLLuRadio**
  - **RTNews**
  - **RTP**
  - **RTRFM**
@@ -1083,6 +1099,7 @@
  - **rtve.es:television**
  - **RTVNH**
  - **RTVS**
+ - **rtvslo.si**
  - **RUHD**
  - **Rule34Video**
  - **RumbleChannel**
@@ -1130,6 +1147,7 @@
  - **Shahid**: [<abbr title="netrc machine"><em>shahid</em></abbr>]
  - **ShahidShow**
  - **Shared**: shared.sx
+ - **ShareVideosEmbed**
  - **ShemarooMe**
  - **ShowRoomLive**
  - **simplecast**
@@ -1191,6 +1209,7 @@
  - **SRGSSR**
  - **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
  - **stanfordoc**: Stanford Open ClassRoom
+ - **StarTrek**
  - **startv**
  - **Steam**
  - **SteamCommunityBroadcast**
@@ -1218,6 +1237,7 @@
  - **SVTSeries**
  - **SWRMediathek**
  - **Syfy**
+ - **SYVDK**
  - **SztvHu**
  - **t-online.de**
  - **Tagesschau**
@@ -1252,10 +1272,12 @@
  - **TeleQuebecVideo**
  - **TeleTask**
  - **Telewebion**
+ - **Tempo**
  - **TennisTV**: [<abbr title="netrc machine"><em>tennistv</em></abbr>]
  - **TenPlay**: [<abbr title="netrc machine"><em>10play</em></abbr>]
  - **TF1**
  - **TFO**
+ - **TheHoleTv**
  - **TheIntercept**
  - **ThePlatform**
  - **ThePlatformFeed**
@@ -1296,8 +1318,11 @@
  - **TrovoVod**
  - **TrueID**
  - **TruNews**
+ - **Truth**
  - **TruTV**
  - **Tube8**
+ - **TubeTuGraz**: [<abbr title="netrc machine"><em>tubetugraz</em></abbr>] tube.tugraz.at
+ - **TubeTuGrazSeries**: [<abbr title="netrc machine"><em>tubetugraz</em></abbr>]
  - **TubiTv**: [<abbr title="netrc machine"><em>tubitv</em></abbr>]
  - **TubiTvShow**
  - **Tumblr**: [<abbr title="netrc machine"><em>tumblr</em></abbr>]
@@ -1326,6 +1351,7 @@
  - **TVCArticle**
  - **TVer**
  - **tvigle**: Интернет-телевидение Tvigle.ru
+ - **TVIPlayer**
  - **tvland.com**
  - **TVN24**
  - **TVNet**
@@ -1498,7 +1524,10 @@
  - **Weibo**
  - **WeiboMobile**
  - **WeiqiTV**: WQTV
+ - **wetv:episode**
+ - **WeTvSeries**
  - **whowatch**
+ - **wikimedia.org**
  - **Willow**
  - **WimTV**
  - **Wistia**
@@ -1560,7 +1589,7 @@
  - **youtube:clip**
  - **youtube:favorites**: YouTube liked videos; ":ytfav" keyword (requires cookies)
  - **youtube:history**: Youtube watch history; ":ythis" keyword (requires cookies)
- - **youtube:music:search_url**: YouTube music search URLs with selectable sections (Eg: #songs)
+ - **youtube:music:search_url**: YouTube music search URLs with selectable sections, e.g. #songs
  - **youtube:notif**: YouTube notifications; ":ytnotif" keyword (requires cookies)
  - **youtube:playlist**: YouTube playlists
  - **youtube:recommended**: YouTube recommended videos; ":ytrec" keyword

test/helper.py

@@ -92,6 +92,13 @@ def gettestcases(include_onlymatching=False):
         yield from ie.get_testcases(include_onlymatching)
 
 
+def getwebpagetestcases():
+    for ie in yt_dlp.extractor.gen_extractors():
+        for tc in ie.get_webpage_testcases():
+            tc.setdefault('add_ie', []).append('Generic')
+            yield tc
+
+
 md5 = lambda s: hashlib.md5(s.encode()).hexdigest()
 
 

test/test_YoutubeDL.py

@@ -722,7 +722,7 @@ class TestYoutubeDL(unittest.TestCase):
         test('%(id)s', '-abcd', info={'id': '-abcd'})
         test('%(id)s', '.abcd', info={'id': '.abcd'})
         test('%(id)s', 'ab__cd', info={'id': 'ab__cd'})
-        test('%(id)s', ('ab:cd', 'ab -cd'), info={'id': 'ab:cd'})
+        test('%(id)s', ('ab:cd', 'ab：cd'), info={'id': 'ab:cd'})
         test('%(id.0)s', '-', info={'id': '--'})
 
         # Invalid templates
@@ -770,7 +770,7 @@ class TestYoutubeDL(unittest.TestCase):
         test('a%(width|)d', 'a', outtmpl_na_placeholder='none')
 
         FORMATS = self.outtmpl_info['formats']
-        sanitize = lambda x: x.replace(':', ' -').replace('"', "'").replace('\n', ' ')
+        sanitize = lambda x: x.replace(':', '：').replace('"', "＂").replace('\n', ' ')
 
         # Custom type casting
         test('%(formats.:.id)l', 'id 1, id 2, id 3')
@@ -788,13 +788,13 @@ class TestYoutubeDL(unittest.TestCase):
         test('%(filesize)#D', '1Ki')
         test('%(height)5.2D', ' 1.08k')
         test('%(title4)#S', 'foo_bar_test')
-        test('%(title4).10S', ('foo \'bar\' ', 'foo \'bar\'' + ('#' if compat_os_name == 'nt' else ' ')))
+        test('%(title4).10S', ('foo ＂bar＂ ', 'foo ＂bar＂' + ('#' if compat_os_name == 'nt' else ' ')))
         if compat_os_name == 'nt':
-            test('%(title4)q', ('"foo \\"bar\\" test"', "'foo _'bar_' test'"))
+            test('%(title4)q', ('"foo \\"bar\\" test"', "＂foo ⧹＂bar⧹＂ test＂"))
-            test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', "'id 1' 'id 2' 'id 3'"))
+            test('%(formats.:.id)#q', ('"id 1" "id 2" "id 3"', '＂id 1＂ ＂id 2＂ ＂id 3＂'))
-            test('%(formats.0.id)#q', ('"id 1"', "'id 1'"))
+            test('%(formats.0.id)#q', ('"id 1"', '＂id 1＂'))
         else:
-            test('%(title4)q', ('\'foo "bar" test\'', "'foo 'bar' test'"))
+            test('%(title4)q', ('\'foo "bar" test\'', '\'foo ＂bar＂ test\''))
             test('%(formats.:.id)#q', "'id 1' 'id 2' 'id 3'")
             test('%(formats.0.id)#q', "'id 1'")
 
@@ -852,8 +852,8 @@ class TestYoutubeDL(unittest.TestCase):
         # Path expansion and escaping
         test('Hello %(title1)s', 'Hello $PATH')
         test('Hello %(title2)s', 'Hello %PATH%')
-        test('%(title3)s', ('foo/bar\\test', 'foo_bar_test'))
+        test('%(title3)s', ('foo/bar\\test', 'foo⧸bar⧹test'))
-        test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo_bar_test' % os.path.sep))
+        test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo⧸bar⧹test' % os.path.sep))
 
     def test_format_note(self):
         ydl = YoutubeDL()
@@ -1053,6 +1053,7 @@ class TestYoutubeDL(unittest.TestCase):
                            for v in get_downloaded_info_dicts(params, entries)]
                 self.assertEqual(results, list(enumerate(zip(expected_ids, expected_ids))), f'Entries of {name} for {params}')
                 self.assertEqual(sorted(evaluated), expected_eval, f'Evaluation of {name} for {params}')
+
         test_selection({}, INDICES)
         test_selection({'playlistend': 20}, INDICES, True)
         test_selection({'playlistend': 2}, INDICES[:2])

test/test_aes.py

@@ -24,6 +24,8 @@ from yt_dlp.aes import (
     aes_encrypt,
     aes_gcm_decrypt_and_verify,
     aes_gcm_decrypt_and_verify_bytes,
+    key_expansion,
+    pad_block,
 )
 from yt_dlp.dependencies import Cryptodome_AES
 from yt_dlp.utils import bytes_to_intlist, intlist_to_bytes
@@ -112,6 +114,41 @@ class TestAES(unittest.TestCase):
         decrypted = intlist_to_bytes(aes_ecb_decrypt(data, self.key, self.iv))
         self.assertEqual(decrypted.rstrip(b'\x08'), self.secret_msg)
 
+    def test_key_expansion(self):
+        key = '4f6bdaa39e2f8cb07f5e722d9edef314'
+
+        self.assertEqual(key_expansion(bytes_to_intlist(bytearray.fromhex(key))), [
+            0x4F, 0x6B, 0xDA, 0xA3, 0x9E, 0x2F, 0x8C, 0xB0, 0x7F, 0x5E, 0x72, 0x2D, 0x9E, 0xDE, 0xF3, 0x14,
+            0x53, 0x66, 0x20, 0xA8, 0xCD, 0x49, 0xAC, 0x18, 0xB2, 0x17, 0xDE, 0x35, 0x2C, 0xC9, 0x2D, 0x21,
+            0x8C, 0xBE, 0xDD, 0xD9, 0x41, 0xF7, 0x71, 0xC1, 0xF3, 0xE0, 0xAF, 0xF4, 0xDF, 0x29, 0x82, 0xD5,
+            0x2D, 0xAD, 0xDE, 0x47, 0x6C, 0x5A, 0xAF, 0x86, 0x9F, 0xBA, 0x00, 0x72, 0x40, 0x93, 0x82, 0xA7,
+            0xF9, 0xBE, 0x82, 0x4E, 0x95, 0xE4, 0x2D, 0xC8, 0x0A, 0x5E, 0x2D, 0xBA, 0x4A, 0xCD, 0xAF, 0x1D,
+            0x54, 0xC7, 0x26, 0x98, 0xC1, 0x23, 0x0B, 0x50, 0xCB, 0x7D, 0x26, 0xEA, 0x81, 0xB0, 0x89, 0xF7,
+            0x93, 0x60, 0x4E, 0x94, 0x52, 0x43, 0x45, 0xC4, 0x99, 0x3E, 0x63, 0x2E, 0x18, 0x8E, 0xEA, 0xD9,
+            0xCA, 0xE7, 0x7B, 0x39, 0x98, 0xA4, 0x3E, 0xFD, 0x01, 0x9A, 0x5D, 0xD3, 0x19, 0x14, 0xB7, 0x0A,
+            0xB0, 0x4E, 0x1C, 0xED, 0x28, 0xEA, 0x22, 0x10, 0x29, 0x70, 0x7F, 0xC3, 0x30, 0x64, 0xC8, 0xC9,
+            0xE8, 0xA6, 0xC1, 0xE9, 0xC0, 0x4C, 0xE3, 0xF9, 0xE9, 0x3C, 0x9C, 0x3A, 0xD9, 0x58, 0x54, 0xF3,
+            0xB4, 0x86, 0xCC, 0xDC, 0x74, 0xCA, 0x2F, 0x25, 0x9D, 0xF6, 0xB3, 0x1F, 0x44, 0xAE, 0xE7, 0xEC])
+
+    def test_pad_block(self):
+        block = [0x21, 0xA0, 0x43, 0xFF]
+
+        self.assertEqual(pad_block(block, 'pkcs7'),
+                         block + [0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C])
+
+        self.assertEqual(pad_block(block, 'iso7816'),
+                         block + [0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
+
+        self.assertEqual(pad_block(block, 'whitespace'),
+                         block + [0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20])
+
+        self.assertEqual(pad_block(block, 'zero'),
+                         block + [0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
+
+        block = list(range(16))
+        for mode in ('pkcs7', 'iso7816', 'whitespace', 'zero'):
+            self.assertEqual(pad_block(block, mode), block, mode)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_compat.py

@@ -28,7 +28,8 @@ class TestCompat(unittest.TestCase):
         with self.assertWarns(DeprecationWarning):
             compat.WINDOWS_VT_MODE
 
-        compat.asyncio.events  # Must not raise error
+        # TODO: Test submodule
+        # compat.asyncio.events  # Must not raise error
 
     def test_compat_expanduser(self):
         old_home = os.environ.get('HOME')

test/test_download.py

@@ -8,6 +8,7 @@ import unittest
 sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
 
 
+import collections
 import hashlib
 import http.client
 import json
@@ -20,6 +21,7 @@ from test.helper import (
     expect_warnings,
     get_params,
     gettestcases,
+    getwebpagetestcases,
     is_download_test,
     report_warning,
     try_rm,
@@ -32,6 +34,7 @@ from yt_dlp.utils import (
     ExtractorError,
     UnavailableVideoError,
     format_bytes,
+    join_nonempty,
 )
 
 RETRIES = 3
@@ -57,7 +60,9 @@ def _file_md5(fn):
         return hashlib.md5(f.read()).hexdigest()
 
 
-defs = gettestcases()
+normal_test_cases = gettestcases()
+webpage_test_cases = getwebpagetestcases()
+tests_counter = collections.defaultdict(collections.Counter)
 
 
 @is_download_test
@@ -72,24 +77,13 @@ class TestDownload(unittest.TestCase):
 
     def __str__(self):
         """Identify each test with the `add_ie` attribute, if available."""
+        cls, add_ie = type(self), getattr(self, self._testMethodName).add_ie
+        return f'{self._testMethodName} ({cls.__module__}.{cls.__name__}){f" [{add_ie}]" if add_ie else ""}:'
 
-        def strclass(cls):
-            """From 2.7's unittest; 2.6 had _strclass so we can't import it."""
-            return f'{cls.__module__}.{cls.__name__}'
-
-        add_ie = getattr(self, self._testMethodName).add_ie
-        return '%s (%s)%s:' % (self._testMethodName,
-                               strclass(self.__class__),
-                               ' [%s]' % add_ie if add_ie else '')
-
-    def setUp(self):
-        self.defs = defs
 
 # Dynamically generate tests
 
-
 def generator(test_case, tname):
-
     def test_template(self):
         if self.COMPLETED_TESTS.get(tname):
             return
@@ -111,11 +105,11 @@ def generator(test_case, tname):
             info_dict = tc.get('info_dict', {})
             params = tc.get('params', {})
             if not info_dict.get('id'):
-                raise Exception('Test definition incorrect. \'id\' key is not present')
+                raise Exception(f'Test {tname} definition incorrect - "id" key is not present')
             elif not info_dict.get('ext'):
                 if params.get('skip_download') and params.get('ignore_no_formats_error'):
                     continue
-                raise Exception('Test definition incorrect. The output file cannot be known. \'ext\' key is not present')
+                raise Exception(f'Test {tname} definition incorrect - "ext" key must be present to define the output file')
 
         if 'skip' in test_case:
             print_skipping(test_case['skip'])
@@ -167,7 +161,9 @@ def generator(test_case, tname):
                         force_generic_extractor=params.get('force_generic_extractor', False))
                 except (DownloadError, ExtractorError) as err:
                     # Check if the exception is not a network related one
-                    if not err.exc_info[0] in (urllib.error.URLError, socket.timeout, UnavailableVideoError, http.client.BadStatusLine) or (err.exc_info[0] == urllib.error.HTTPError and err.exc_info[1].code == 503):
+                    if (err.exc_info[0] not in (urllib.error.URLError, socket.timeout, UnavailableVideoError, http.client.BadStatusLine)
+                            or (err.exc_info[0] == urllib.error.HTTPError and err.exc_info[1].code == 503)):
+                        err.msg = f'{getattr(err, "msg", err)} ({tname})'
                         raise
 
                     if try_num == RETRIES:
@@ -255,39 +251,43 @@ def generator(test_case, tname):
 
 
 # And add them to TestDownload
-tests_counter = {}
+def inject_tests(test_cases, label=''):
-for test_case in defs:
+    for test_case in test_cases:
-    name = test_case['name']
+        name = test_case['name']
-    i = tests_counter.get(name, 0)
+        tname = join_nonempty('test', name, label, tests_counter[name][label], delim='_')
-    tests_counter[name] = i + 1
+        tests_counter[name][label] += 1
-    tname = f'test_{name}_{i}' if i else f'test_{name}'
+
-    test_method = generator(test_case, tname)
+        test_method = generator(test_case, tname)
-    test_method.__name__ = str(tname)
+        test_method.__name__ = tname
-    ie_list = test_case.get('add_ie')
+        test_method.add_ie = ','.join(test_case.get('add_ie', []))
-    test_method.add_ie = ie_list and ','.join(ie_list)
+        setattr(TestDownload, test_method.__name__, test_method)
-    setattr(TestDownload, test_method.__name__, test_method)
-    del test_method
 
 
-def batch_generator(name, num_tests):
+inject_tests(normal_test_cases)
 
+# TODO: disable redirection to the IE to ensure we are actually testing the webpage extraction
+inject_tests(webpage_test_cases, 'webpage')
+
+
+def batch_generator(name):
     def test_template(self):
-        for i in range(num_tests):
+        for label, num_tests in tests_counter[name].items():
-            test_name = f'test_{name}_{i}' if i else f'test_{name}'
+            for i in range(num_tests):
-            try:
+                test_name = join_nonempty('test', name, label, i, delim='_')
-                getattr(self, test_name)()
+                try:
-            except unittest.SkipTest:
+                    getattr(self, test_name)()
-                print(f'Skipped {test_name}')
+                except unittest.SkipTest:
+                    print(f'Skipped {test_name}')
 
     return test_template
 
 
-for name, num_tests in tests_counter.items():
+for name in tests_counter:
-    test_method = batch_generator(name, num_tests)
+    test_method = batch_generator(name)
     test_method.__name__ = f'test_{name}_all'
     test_method.add_ie = ''
     setattr(TestDownload, test_method.__name__, test_method)
-    del test_method
+del test_method
 
 
 if __name__ == '__main__':

test/test_downloader_http.py

@@ -95,8 +95,8 @@ class TestHttpFD(unittest.TestCase):
         try_rm(encodeFilename(filename))
         self.assertTrue(downloader.real_download(filename, {
             'url': 'http://127.0.0.1:%d/%s' % (self.port, ep),
-        }))
+        }), ep)
-        self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE)
+        self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE, ep)
         try_rm(encodeFilename(filename))
 
     def download_all(self, params):

test/test_http.py

@@ -85,7 +85,7 @@ class TestHTTPS(unittest.TestCase):
 
         ydl = YoutubeDL({'logger': FakeLogger(), 'nocheckcertificate': True})
         r = ydl.extract_info('https://127.0.0.1:%d/video.html' % self.port)
-        self.assertEqual(r['entries'][0]['url'], 'https://127.0.0.1:%d/vid.mp4' % self.port)
+        self.assertEqual(r['url'], 'https://127.0.0.1:%d/vid.mp4' % self.port)
 
 
 class TestClientCert(unittest.TestCase):
@@ -113,7 +113,7 @@ class TestClientCert(unittest.TestCase):
             **params,
         })
         r = ydl.extract_info('https://127.0.0.1:%d/video.html' % self.port)
-        self.assertEqual(r['entries'][0]['url'], 'https://127.0.0.1:%d/vid.mp4' % self.port)
+        self.assertEqual(r['url'], 'https://127.0.0.1:%d/vid.mp4' % self.port)
 
     def test_certificate_combined_nopass(self):
         self._run_test(client_certificate=os.path.join(self.certdir, 'clientwithkey.crt'))

test/test_jsinterp.py

@@ -19,6 +19,9 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function x3(){return 42;}')
         self.assertEqual(jsi.call_function('x3'), 42)
 
+        jsi = JSInterpreter('function x3(){42}')
+        self.assertEqual(jsi.call_function('x3'), None)
+
         jsi = JSInterpreter('var x5 = function(){return 42;}')
         self.assertEqual(jsi.call_function('x5'), 42)
 
@@ -45,14 +48,26 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function f(){return 1 << 5;}')
         self.assertEqual(jsi.call_function('f'), 32)
 
+        jsi = JSInterpreter('function f(){return 2 ** 5}')
+        self.assertEqual(jsi.call_function('f'), 32)
+
         jsi = JSInterpreter('function f(){return 19 & 21;}')
         self.assertEqual(jsi.call_function('f'), 17)
 
         jsi = JSInterpreter('function f(){return 11 >> 2;}')
         self.assertEqual(jsi.call_function('f'), 2)
 
+        jsi = JSInterpreter('function f(){return []? 2+3: 4;}')
+        self.assertEqual(jsi.call_function('f'), 5)
+
+        jsi = JSInterpreter('function f(){return 1 == 2}')
+        self.assertEqual(jsi.call_function('f'), False)
+
+        jsi = JSInterpreter('function f(){return 0 && 1 || 2;}')
+        self.assertEqual(jsi.call_function('f'), 2)
+
     def test_array_access(self):
-        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2] = 7; return x;}')
+        jsi = JSInterpreter('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}')
         self.assertEqual(jsi.call_function('f'), [5, 2, 7])
 
     def test_parens(self):
@@ -62,6 +77,10 @@ class TestJSInterpreter(unittest.TestCase):
         jsi = JSInterpreter('function f(){return (1 + 2) * 3;}')
         self.assertEqual(jsi.call_function('f'), 9)
 
+    def test_quotes(self):
+        jsi = JSInterpreter(R'function f(){return "a\"\\("}')
+        self.assertEqual(jsi.call_function('f'), R'a"\(')
+
     def test_assignments(self):
         jsi = JSInterpreter('function f(){var x = 20; x = 30 + 1; return x;}')
         self.assertEqual(jsi.call_function('f'), 31)
@@ -104,17 +123,28 @@ class TestJSInterpreter(unittest.TestCase):
         }''')
         self.assertEqual(jsi.call_function('x'), [20, 20, 30, 40, 50])
 
+    def test_builtins(self):
+        jsi = JSInterpreter('''
+        function x() { return new Date('Wednesday 31 December 1969 18:01:26 MDT') - 0; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 86000)
+        jsi = JSInterpreter('''
+        function x(dt) { return new Date(dt) - 0; }
+        ''')
+        self.assertEqual(jsi.call_function('x', 'Wednesday 31 December 1969 18:01:26 MDT'), 86000)
+
     def test_call(self):
         jsi = JSInterpreter('''
         function x() { return 2; }
-        function y(a) { return x() + a; }
+        function y(a) { return x() + (a?a:0); }
         function z() { return y(3); }
         ''')
         self.assertEqual(jsi.call_function('z'), 5)
+        self.assertEqual(jsi.call_function('y'), 2)
 
     def test_for_loop(self):
         jsi = JSInterpreter('''
-        function x() { a=0; for (i=0; i-10; i++) {a++} a }
+        function x() { a=0; for (i=0; i-10; i++) {a++} return a }
         ''')
         self.assertEqual(jsi.call_function('x'), 10)
 
@@ -155,19 +185,19 @@ class TestJSInterpreter(unittest.TestCase):
 
     def test_for_loop_continue(self):
         jsi = JSInterpreter('''
-        function x() { a=0; for (i=0; i-10; i++) { continue; a++ } a }
+        function x() { a=0; for (i=0; i-10; i++) { continue; a++ } return a }
         ''')
         self.assertEqual(jsi.call_function('x'), 0)
 
     def test_for_loop_break(self):
         jsi = JSInterpreter('''
-        function x() { a=0; for (i=0; i-10; i++) { break; a++ } a }
+        function x() { a=0; for (i=0; i-10; i++) { break; a++ } return a }
         ''')
         self.assertEqual(jsi.call_function('x'), 0)
 
     def test_literal_list(self):
         jsi = JSInterpreter('''
-        function x() { [1, 2, "asdf", [5, 6, 7]][3] }
+        function x() { return [1, 2, "asdf", [5, 6, 7]][3] }
         ''')
         self.assertEqual(jsi.call_function('x'), [5, 6, 7])
 
@@ -177,6 +207,23 @@ class TestJSInterpreter(unittest.TestCase):
         ''')
         self.assertEqual(jsi.call_function('x'), 7)
 
+        jsi = JSInterpreter('''
+        function x() { a=5; return (a -= 1, a+=3, a); }
+        ''')
+        self.assertEqual(jsi.call_function('x'), 7)
+
+    def test_void(self):
+        jsi = JSInterpreter('''
+        function x() { return void 42; }
+        ''')
+        self.assertEqual(jsi.call_function('x'), None)
+
+    def test_return_function(self):
+        jsi = JSInterpreter('''
+        function x() { return [1, function(){return 1}][1] }
+        ''')
+        self.assertEqual(jsi.call_function('x')([]), 1)
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_utils.py

@@ -39,6 +39,7 @@ from yt_dlp.utils import (
     datetime_from_str,
     detect_exe_version,
     determine_ext,
+    determine_file_encoding,
     dfxp2srt,
     dict_get,
     encode_base_n,
@@ -52,6 +53,7 @@ from yt_dlp.utils import (
     fix_xml_ampersands,
     float_or_none,
     format_bytes,
+    get_compatible_ext,
     get_element_by_attribute,
     get_element_by_class,
     get_element_html_by_attribute,
@@ -138,13 +140,13 @@ class TestUtil(unittest.TestCase):
 
         self.assertEqual(sanitize_filename('123'), '123')
 
-        self.assertEqual('abc_de', sanitize_filename('abc/de'))
+        self.assertEqual('abc⧸de', sanitize_filename('abc/de'))
         self.assertFalse('/' in sanitize_filename('abc/de///'))
 
-        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de'))
+        self.assertEqual('abc_de', sanitize_filename('abc/<>\\*|de', is_id=False))
-        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|'))
+        self.assertEqual('xxx', sanitize_filename('xxx/<>\\*|', is_id=False))
-        self.assertEqual('yes no', sanitize_filename('yes? no'))
+        self.assertEqual('yes no', sanitize_filename('yes? no', is_id=False))
-        self.assertEqual('this - that', sanitize_filename('this: that'))
+        self.assertEqual('this - that', sanitize_filename('this: that', is_id=False))
 
         self.assertEqual(sanitize_filename('AT&T'), 'AT&T')
         aumlaut = 'ä'
@@ -367,6 +369,7 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_strdate('2012/10/11 01:56:38 +0000'), '20121011')
         self.assertEqual(unified_strdate('1968 12 10'), '19681210')
         self.assertEqual(unified_strdate('1968-12-10'), '19681210')
+        self.assertEqual(unified_strdate('31-07-2022 20:00'), '20220731')
         self.assertEqual(unified_strdate('28/01/2014 21:00:00 +0100'), '20140128')
         self.assertEqual(
             unified_strdate('11/26/2014 11:30:00 AM PST', day_first=False),
@@ -410,6 +413,10 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
         self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
 
+        self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
+        self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
+        self.assertEqual(unified_timestamp('12/31/1969 20:01:18 EDT', False), 78)
+
     def test_determine_ext(self):
         self.assertEqual(determine_ext('http://example.com/foo/bar.mp4/?download'), 'mp4')
         self.assertEqual(determine_ext('http://example.com/foo/bar/?download', None), None)
@@ -895,7 +902,7 @@ class TestUtil(unittest.TestCase):
             'dynamic_range': 'HDR10',
         })
         self.assertEqual(parse_codecs('av01.0.12M.10.0.110.09.16.09.0'), {
-            'vcodec': 'av01.0.12M.10',
+            'vcodec': 'av01.0.12M.10.0.110.09.16.09.0',
             'acodec': 'none',
             'dynamic_range': 'HDR10',
         })
@@ -1822,6 +1829,50 @@ Line 1
             with contextlib.suppress(OSError):
                 os.remove(FILE)
 
+    def test_determine_file_encoding(self):
+        self.assertEqual(determine_file_encoding(b''), (None, 0))
+        self.assertEqual(determine_file_encoding(b'--verbose -x --audio-format mkv\n'), (None, 0))
+
+        self.assertEqual(determine_file_encoding(b'\xef\xbb\xbf'), ('utf-8', 3))
+        self.assertEqual(determine_file_encoding(b'\x00\x00\xfe\xff'), ('utf-32-be', 4))
+        self.assertEqual(determine_file_encoding(b'\xff\xfe'), ('utf-16-le', 2))
+
+        self.assertEqual(determine_file_encoding(b'\xff\xfe# coding: utf-8\n--verbose'), ('utf-16-le', 2))
+
+        self.assertEqual(determine_file_encoding(b'# coding: utf-8\n--verbose'), ('utf-8', 0))
+        self.assertEqual(determine_file_encoding(b'# coding: someencodinghere-12345\n--verbose'), ('someencodinghere-12345', 0))
+
+        self.assertEqual(determine_file_encoding(b'#coding:utf-8\n--verbose'), ('utf-8', 0))
+        self.assertEqual(determine_file_encoding(b'#  coding:   utf-8   \r\n--verbose'), ('utf-8', 0))
+
+        self.assertEqual(determine_file_encoding('# coding: utf-32-be'.encode('utf-32-be')), ('utf-32-be', 0))
+        self.assertEqual(determine_file_encoding('# coding: utf-16-le'.encode('utf-16-le')), ('utf-16-le', 0))
+
+    def test_get_compatible_ext(self):
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None, None], vexts=['mp4'], aexts=['m4a', 'm4a']), 'mkv')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None], vexts=['flv'], aexts=['flv']), 'flv')
+
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None], vexts=['mp4'], aexts=['m4a']), 'mp4')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None], vexts=['mp4'], aexts=['webm']), 'mkv')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None], vexts=['webm'], aexts=['m4a']), 'mkv')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=[None], acodecs=[None], vexts=['webm'], aexts=['webm']), 'webm')
+
+        self.assertEqual(get_compatible_ext(
+            vcodecs=['h264'], acodecs=['mp4a'], vexts=['mov'], aexts=['m4a']), 'mp4')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=['av01.0.12M.08'], acodecs=['opus'], vexts=['mp4'], aexts=['webm']), 'webm')
+
+        self.assertEqual(get_compatible_ext(
+            vcodecs=['vp9'], acodecs=['opus'], vexts=['webm'], aexts=['webm'], preferences=['flv', 'mp4']), 'mp4')
+        self.assertEqual(get_compatible_ext(
+            vcodecs=['av1'], acodecs=['mp4a'], vexts=['webm'], aexts=['m4a'], preferences=('webm', 'mkv')), 'mkv')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_youtube_signature.py

@@ -94,6 +94,14 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/5dd88d1d/player-plasma-ias-phone-en_US.vflset/base.js',
         'kSxKFLeqzv_ZyHSAt', 'n8gS8oRlHOxPFA',
     ),
+    (
+        'https://www.youtube.com/s/player/324f67b9/player_ias.vflset/en_US/base.js',
+        'xdftNy7dh9QGnhW', '22qLGxrmX8F1rA',
+    ),
+    (
+        'https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js',
+        'TDCstCG66tEAO5pR9o', 'dbxNtZ14c-yWyw',
+    ),
 ]
 
 
@@ -101,6 +109,7 @@ _NSIG_TESTS = [
 class TestPlayerInfo(unittest.TestCase):
     def test_youtube_extract_player_info(self):
         PLAYER_URLS = (
+            ('https://www.youtube.com/s/player/4c3f79c5/player_ias.vflset/en_US/base.js', '4c3f79c5'),
             ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/en_US/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player_ias.vflset/fr_FR/base.js', '64dddad9'),
             ('https://www.youtube.com/s/player/64dddad9/player-plasma-ias-phone-en_US.vflset/base.js', '64dddad9'),

yt_dlp/YoutubeDL.py

@@ -24,7 +24,6 @@ import urllib.request
 from string import ascii_letters
 
 from .cache import Cache
-from .compat import HAS_LEGACY as compat_has_legacy
 from .compat import compat_os_name, compat_shlex_quote
 from .cookies import load_cookies
 from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
@@ -43,14 +42,17 @@ from .postprocessor import (
     FFmpegFixupTimestampPP,
     FFmpegMergerPP,
     FFmpegPostProcessor,
+    FFmpegVideoConvertorPP,
     MoveFilesAfterDownloadPP,
     get_postprocessor,
 )
+from .postprocessor.ffmpeg import resolve_mapping as resolve_recode_mapping
 from .update import detect_variant
 from .utils import (
     DEFAULT_OUTTMPL,
     IDENTITY,
     LINK_TEMPLATES,
+    MEDIA_EXTENSIONS,
     NO_DEFAULT,
     NUMBER_RE,
     OUTTMPL_TYPES,
@@ -79,17 +81,20 @@ from .utils import (
     RejectedVideoReached,
     SameFileError,
     UnavailableVideoError,
+    UserNotLive,
     YoutubeDLCookieProcessor,
     YoutubeDLHandler,
     YoutubeDLRedirectHandler,
     age_restricted,
     args_to_str,
+    bug_reports_message,
     date_from_str,
     determine_ext,
     determine_protocol,
     encode_compat_str,
     encodeFilename,
     error_to_compat_str,
+    escapeHTML,
     expand_path,
     filter_dict,
     float_or_none,
@@ -97,11 +102,13 @@ from .utils import (
     format_decimal_suffix,
     format_field,
     formatSeconds,
+    get_compatible_ext,
     get_domain,
     int_or_none,
     iri_to_uri,
     join_nonempty,
     locked_file,
+    make_archive_id,
     make_dir,
     make_HTTPS_handler,
     merge_headers,
@@ -128,6 +135,7 @@ from .utils import (
     timetuple_from_msec,
     to_high_limit_path,
     traverse_obj,
+    try_call,
     try_get,
     url_basename,
     variadic,
@@ -136,7 +144,7 @@ from .utils import (
     write_json_file,
     write_string,
 )
-from .version import RELEASE_GIT_HEAD, __version__
+from .version import RELEASE_GIT_HEAD, VARIANT, __version__
 
 if compat_os_name == 'nt':
     import ctypes
@@ -264,7 +272,7 @@ class YoutubeDL:
     subtitleslangs:    List of languages of the subtitles to download (can be regex).
                        The list may contain "all" to refer to all the available
                        subtitles. The language can be prefixed with a "-" to
-                       exclude it from the requested languages. Eg: ['all', '-live_chat']
+                       exclude it from the requested languages, e.g. ['all', '-live_chat']
     keepvideo:         Keep the video file after post-processing
     daterange:         A DateRange object, download only if the upload_date is in the range.
     skip_download:     Skip the actual download of the video file
@@ -293,8 +301,8 @@ class YoutubeDL:
                        should act on each input URL as opposed to for the entire queue
     cookiefile:        File name or text stream from where cookies should be read and dumped to
     cookiesfrombrowser:  A tuple containing the name of the browser, the profile
-                       name/pathfrom where cookies are loaded, and the name of the
+                       name/path from where cookies are loaded, and the name of the
-                       keyring. Eg: ('chrome', ) or ('vivaldi', 'default', 'BASICTEXT')
+                       keyring, e.g. ('chrome', ) or ('vivaldi', 'default', 'BASICTEXT')
     legacyserverconnect: Explicitly allow HTTPS connection to servers that do not
                        support RFC 5746 secure renegotiation
     nocheckcertificate:  Do not verify SSL certificates
@@ -303,7 +311,7 @@ class YoutubeDL:
     client_certificate_password:  Password for client certificate private key, if encrypted.
                         If not provided and the key is encrypted, yt-dlp will ask interactively
     prefer_insecure:   Use HTTP instead of HTTPS to retrieve information.
-                       At the moment, this is only supported by YouTube.
+                       (Only supported by some extractors)
     http_headers:      A dictionary of custom headers to be used for all requests
     proxy:             URL of the proxy server to use
     geo_verification_proxy:  URL of the proxy to use for IP address verification
@@ -315,9 +323,14 @@ class YoutubeDL:
     default_search:    Prepend this string if an input url is not valid.
                        'auto' for elaborate guessing
     encoding:          Use this encoding instead of the system-specified.
-    extract_flat:      Do not resolve URLs, return the immediate result.
+    extract_flat:      Whether to resolve and process url_results further
-                       Pass in 'in_playlist' to only show this behavior for
+                       * False:     Always process (default)
-                       playlist items.
+                       * True:      Never process
+                       * 'in_playlist': Do not process inside playlist/multi_video
+                       * 'discard': Always process, but don't return the result
+                                    from inside playlist/multi_video
+                       * 'discard_in_playlist': Same as "discard", but only for
+                                    playlists (not multi_video)
     wait_for_video:    If given, wait for scheduled streams to become available.
                        The value should be a tuple containing the range
                        (min_secs, max_secs) to wait between retries
@@ -361,7 +374,7 @@ class YoutubeDL:
 
                        Progress hooks are guaranteed to be called at least twice
                        (with status "started" and "finished") if the processing is successful.
-    merge_output_format: Extension to use when merging formats.
+    merge_output_format: "/" separated list of extensions to use when merging formats.
     final_ext:         Expected final extension; used to detect when the file was
                        already downloaded and converted
     fixup:             Automatically correct known faults of the file.
@@ -421,19 +434,22 @@ class YoutubeDL:
     retry_sleep_functions: Dictionary of functions that takes the number of attempts
                        as argument and returns the time to sleep in seconds.
                        Allowed keys are 'http', 'fragment', 'file_access'
-    download_ranges:   A function that gets called for every video with the signature
+    download_ranges:   A callback function that gets called for every video with
-                       (info_dict, *, ydl) -> Iterable[Section].
+                       the signature (info_dict, ydl) -> Iterable[Section].
-                       Only the returned sections will be downloaded. Each Section contains:
+                       Only the returned sections will be downloaded.
+                       Each Section is a dict with the following keys:
                        * start_time: Start time of the section in seconds
                        * end_time: End time of the section in seconds
                        * title: Section title (Optional)
                        * index: Section number (Optional)
+    force_keyframes_at_cuts: Re-encode the video when downloading ranges to get precise cuts
+    noprogress:        Do not print the progress bar
 
     The following parameters are not used by YoutubeDL itself, they are used by
     the downloader (see yt_dlp/downloader/common.py):
     nopart, updatetime, buffersize, ratelimit, throttledratelimit, min_filesize,
     max_filesize, test, noresizebuffer, retries, file_access_retries, fragment_retries,
-    continuedl, noprogress, xattr_set_filesize, hls_use_mpegts, http_chunk_size,
+    continuedl, xattr_set_filesize, hls_use_mpegts, http_chunk_size,
     external_downloader_args, concurrent_fragment_downloads.
 
     The following options are used by the post processors:
@@ -454,7 +470,7 @@ class YoutubeDL:
                        discontinuities such as ad breaks (default: False)
     extractor_args:    A dictionary of arguments to be passed to the extractors.
                        See "EXTRACTOR ARGUMENTS" for details.
-                       Eg: {'youtube': {'skip': ['dash', 'hls']}}
+                       E.g. {'youtube': {'skip': ['dash', 'hls']}}
     mark_watched:      Mark videos watched (even with --simulate). Only for YouTube
 
     The following options are deprecated and may be removed in the future:
@@ -511,7 +527,8 @@ class YoutubeDL:
     """
 
     _NUMERIC_FIELDS = {
-        'width', 'height', 'tbr', 'abr', 'asr', 'vbr', 'fps', 'filesize', 'filesize_approx',
+        'width', 'height', 'asr', 'audio_channels', 'fps',
+        'tbr', 'abr', 'vbr', 'filesize', 'filesize_approx',
         'timestamp', 'release_timestamp',
         'duration', 'view_count', 'like_count', 'dislike_count', 'repost_count',
         'average_rating', 'comment_count', 'age_limit',
@@ -523,7 +540,7 @@ class YoutubeDL:
     _format_fields = {
         # NB: Keep in sync with the docstring of extractor/common.py
         'url', 'manifest_url', 'manifest_stream_number', 'ext', 'format', 'format_id', 'format_note',
-        'width', 'height', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr',
+        'width', 'height', 'resolution', 'dynamic_range', 'tbr', 'abr', 'acodec', 'asr', 'audio_channels',
         'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx',
         'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start',
         'preference', 'language', 'language_preference', 'quality', 'source_preference',
@@ -531,9 +548,9 @@ class YoutubeDL:
         'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time'
     }
     _format_selection_exts = {
-        'audio': {'m4a', 'mp3', 'ogg', 'aac'},
+        'audio': set(MEDIA_EXTENSIONS.common_audio),
-        'video': {'mp4', 'flv', 'webm', '3gp'},
+        'video': set(MEDIA_EXTENSIONS.common_video + ('3gp', )),
-        'storyboards': {'mhtml'},
+        'storyboards': set(MEDIA_EXTENSIONS.storyboards),
     }
 
     def __init__(self, params=None, auto_init=True):
@@ -573,12 +590,13 @@ class YoutubeDL:
             for type_, stream in self._out_files.items_ if type_ != 'console'
         })
 
-        MIN_SUPPORTED, MIN_RECOMMENDED = (3, 6), (3, 7)
+        # The code is left like this to be reused for future deprecations
+        MIN_SUPPORTED, MIN_RECOMMENDED = (3, 7), (3, 7)
         current_version = sys.version_info[:2]
         if current_version < MIN_RECOMMENDED:
             msg = ('Support for Python version %d.%d has been deprecated. '
-                   'See  https://github.com/yt-dlp/yt-dlp/issues/3764  for more details. '
+                   'See  https://github.com/yt-dlp/yt-dlp/issues/3764  for more details.'
-                   'You will recieve only one more update on this version')
+                   '\n                    You will no longer receive updates on this version')
             if current_version < MIN_SUPPORTED:
                 msg = 'Python version %d.%d is no longer supported'
             self.deprecation_warning(
@@ -611,8 +629,6 @@ class YoutubeDL:
             self.deprecation_warning(msg)
 
         self.params['compat_opts'] = set(self.params.get('compat_opts', ()))
-        if not compat_has_legacy:
-            self.params['compat_opts'].add('no-compat-legacy')
         if 'list-formats' in self.params['compat_opts']:
             self.params['listformats_table'] = False
 
@@ -1030,7 +1046,7 @@ class YoutubeDL:
 
         # outtmpl should be expand_path'ed before template dict substitution
         # because meta fields may contain env variables we don't want to
-        # be expanded. For example, for outtmpl "%(title)s.%(ext)s" and
+        # be expanded. E.g. for outtmpl "%(title)s.%(ext)s" and
         # title "Hello $PATH", we don't want `$PATH` to be expanded.
         return expand_path(outtmpl).replace(sep, '')
 
@@ -1046,7 +1062,7 @@ class YoutubeDL:
     def validate_outtmpl(cls, outtmpl):
         ''' @return None or Exception object '''
         outtmpl = re.sub(
-            STR_FORMAT_RE_TMPL.format('[^)]*', '[ljqBUDS]'),
+            STR_FORMAT_RE_TMPL.format('[^)]*', '[ljhqBUDS]'),
             lambda mobj: f'{mobj.group(0)[:-1]}s',
             cls._outtmpl_expandpath(outtmpl))
         try:
@@ -1089,7 +1105,7 @@ class YoutubeDL:
         }
 
         TMPL_DICT = {}
-        EXTERNAL_FORMAT_RE = re.compile(STR_FORMAT_RE_TMPL.format('[^)]*', f'[{STR_FORMAT_TYPES}ljqBUDS]'))
+        EXTERNAL_FORMAT_RE = re.compile(STR_FORMAT_RE_TMPL.format('[^)]*', f'[{STR_FORMAT_TYPES}ljhqBUDS]'))
         MATH_FUNCTIONS = {
             '+': float.__add__,
             '-': float.__sub__,
@@ -1150,6 +1166,9 @@ class YoutubeDL:
             if mdict['strf_format']:
                 value = strftime_or_none(value, mdict['strf_format'].replace('\\,', ','))
 
+            # XXX: Workaround for https://github.com/yt-dlp/yt-dlp/issues/4485
+            if sanitize and value == '':
+                value = None
             return value
 
         na = self.params.get('outtmpl_na_placeholder', 'NA')
@@ -1198,6 +1217,8 @@ class YoutubeDL:
                 value, fmt = delim.join(map(str, variadic(value, allowed_types=(str, bytes)))), str_fmt
             elif fmt[-1] == 'j':  # json
                 value, fmt = json.dumps(value, default=_dumpjson_default, indent=4 if '#' in flags else None), str_fmt
+            elif fmt[-1] == 'h':  # html
+                value, fmt = escapeHTML(value), str_fmt
             elif fmt[-1] == 'q':  # quoted
                 value = map(str, variadic(value) if '#' in flags else [value])
                 value, fmt = ' '.join(map(compat_shlex_quote, value)), str_fmt
@@ -1297,7 +1318,7 @@ class YoutubeDL:
     def _match_entry(self, info_dict, incomplete=False, silent=False):
         """ Returns None if the file should be downloaded """
 
-        video_title = info_dict.get('title', info_dict.get('id', 'video'))
+        video_title = info_dict.get('title', info_dict.get('id', 'entry'))
 
         def check_filter():
             if 'title' in info_dict:
@@ -1444,7 +1465,7 @@ class YoutubeDL:
                 break
         return wrapper
 
-    def _wait_for_video(self, ie_result):
+    def _wait_for_video(self, ie_result={}):
         if (not self.params.get('wait_for_video')
                 or ie_result.get('_type', 'video') != 'video'
                 or ie_result.get('formats') or ie_result.get('url')):
@@ -1455,7 +1476,12 @@ class YoutubeDL:
 
         def progress(msg):
             nonlocal last_msg
-            self.to_screen(msg + ' ' * (len(last_msg) - len(msg)) + '\r', skip_eol=True)
+            full_msg = f'{msg}\n'
+            if not self.params.get('noprogress'):
+                full_msg = msg + ' ' * (len(last_msg) - len(msg)) + '\r'
+            elif last_msg:
+                return
+            self.to_screen(full_msg, skip_eol=True)
             last_msg = msg
 
         min_wait, max_wait = self.params.get('wait_for_video')
@@ -1463,7 +1489,7 @@ class YoutubeDL:
         if diff is None and ie_result.get('live_status') == 'is_upcoming':
             diff = round(random.uniform(min_wait, max_wait) if (max_wait and min_wait) else (max_wait or min_wait), 0)
             self.report_warning('Release time of video is not known')
-        elif (diff or 0) <= 0:
+        elif ie_result and (diff or 0) <= 0:
             self.report_warning('Video should already be available according to extracted info')
         diff = min(max(diff or 0, min_wait or 0), max_wait or float('inf'))
         self.to_screen(f'[wait] Waiting for {format_dur(diff)} - Press Ctrl+C to try now')
@@ -1487,8 +1513,16 @@ class YoutubeDL:
 
     @_handle_extraction_exceptions
     def __extract_info(self, url, ie, download, extra_info, process):
-        ie_result = ie.extract(url)
+        try:
+            ie_result = ie.extract(url)
+        except UserNotLive as e:
+            if process:
+                if self.params.get('wait_for_video'):
+                    self.report_warning(e)
+                self._wait_for_video()
+            raise
         if ie_result is None:  # Finished already (backwards compatibility; listformats and friends should be moved here)
+            self.report_warning(f'Extractor {ie.IE_NAME} returned nothing{bug_reports_message()}')
             return
         if isinstance(ie_result, list):
             # Backwards compatibility: old IE result format
@@ -1536,7 +1570,8 @@ class YoutubeDL:
         result_type = ie_result.get('_type', 'video')
 
         if result_type in ('url', 'url_transparent'):
-            ie_result['url'] = sanitize_url(ie_result['url'])
+            ie_result['url'] = sanitize_url(
+                ie_result['url'], scheme='http' if self.params.get('prefer_insecure') else 'https')
             if ie_result.get('original_url'):
                 extra_info.setdefault('original_url', ie_result['original_url'])
 
@@ -1659,22 +1694,38 @@ class YoutubeDL:
         return make_dir(path, self.report_error)
 
     @staticmethod
-    def _playlist_infodict(ie_result, **kwargs):
+    def _playlist_infodict(ie_result, strict=False, **kwargs):
-        return {
+        info = {
-            **ie_result,
+            'playlist_count': ie_result.get('playlist_count'),
             'playlist': ie_result.get('title') or ie_result.get('id'),
             'playlist_id': ie_result.get('id'),
             'playlist_title': ie_result.get('title'),
             'playlist_uploader': ie_result.get('uploader'),
             'playlist_uploader_id': ie_result.get('uploader_id'),
-            'playlist_index': 0,
             **kwargs,
         }
+        if strict:
+            return info
+        return {
+            **info,
+            'playlist_index': 0,
+            '__last_playlist_index': max(ie_result['requested_entries'] or (0, 0)),
+            'extractor': ie_result['extractor'],
+            'webpage_url': ie_result['webpage_url'],
+            'webpage_url_basename': url_basename(ie_result['webpage_url']),
+            'webpage_url_domain': get_domain(ie_result['webpage_url']),
+            'extractor_key': ie_result['extractor_key'],
+        }
 
     def __process_playlist(self, ie_result, download):
         """Process each entry in the playlist"""
-        title = ie_result.get('title') or ie_result.get('id') or '<Untitled>'
+        assert ie_result['_type'] in ('playlist', 'multi_video')
-        self.to_screen(f'[download] Downloading playlist: {title}')
+
+        common_info = self._playlist_infodict(ie_result, strict=True)
+        title = common_info.get('playlist') or '<Untitled>'
+        if self._match_entry(common_info, incomplete=True) is not None:
+            return
+        self.to_screen(f'[download] Downloading {ie_result["_type"]}: {title}')
 
         all_entries = PlaylistEntries(self, ie_result)
         entries = orderedSet(all_entries.get_requested_items(), lazy=True)
@@ -1691,12 +1742,14 @@ class YoutubeDL:
             # Better to do this after potentially exhausting entries
             ie_result['playlist_count'] = all_entries.get_full_count()
 
+        extra = self._playlist_infodict(ie_result, n_entries=int_or_none(n_entries))
+        ie_copy = collections.ChainMap(ie_result, extra)
+
         _infojson_written = False
         write_playlist_files = self.params.get('allow_playlist_files', True)
         if write_playlist_files and self.params.get('list_thumbnails'):
             self.list_thumbnails(ie_result)
         if write_playlist_files and not self.params.get('simulate'):
-            ie_copy = self._playlist_infodict(ie_result, n_entries=int_or_none(n_entries))
             _infojson_written = self._write_info_json(
                 'playlist', ie_result, self.prepare_filename(ie_copy, 'pl_infojson'))
             if _infojson_written is None:
@@ -1705,7 +1758,7 @@ class YoutubeDL:
                                        self.prepare_filename(ie_copy, 'pl_description')) is None:
                 return
             # TODO: This should be passed to ThumbnailsConvertor if necessary
-            self._write_thumbnails('playlist', ie_copy, self.prepare_filename(ie_copy, 'pl_thumbnail'))
+            self._write_thumbnails('playlist', ie_result, self.prepare_filename(ie_copy, 'pl_thumbnail'))
 
         if lazy:
             if self.params.get('playlistreverse') or self.params.get('playlistrandom'):
@@ -1718,50 +1771,56 @@ class YoutubeDL:
         self.to_screen(f'[{ie_result["extractor"]}] Playlist {title}: Downloading {n_entries} videos'
                        f'{format_field(ie_result, "playlist_count", " of %s")}')
 
+        keep_resolved_entries = self.params.get('extract_flat') != 'discard'
+        if self.params.get('extract_flat') == 'discard_in_playlist':
+            keep_resolved_entries = ie_result['_type'] != 'playlist'
+        if keep_resolved_entries:
+            self.write_debug('The information of all playlist entries will be held in memory')
+
         failures = 0
         max_failures = self.params.get('skip_playlist_after_errors') or float('inf')
         for i, (playlist_index, entry) in enumerate(entries):
             if lazy:
                 resolved_entries.append((playlist_index, entry))
-
+            if not entry:
-            # TODO: Add auto-generated fields
-            if not entry or self._match_entry(entry, incomplete=True) is not None:
                 continue
 
-            self.to_screen('[download] Downloading video %s of %s' % (
-                self._format_screen(i + 1, self.Styles.ID), self._format_screen(n_entries, self.Styles.EMPHASIS)))
-
             entry['__x_forwarded_for_ip'] = ie_result.get('__x_forwarded_for_ip')
             if not lazy and 'playlist-index' in self.params.get('compat_opts', []):
                 playlist_index = ie_result['requested_entries'][i]
 
-            entry_result = self.__process_iterable_entry(entry, download, {
+            entry_copy = collections.ChainMap(entry, {
+                **common_info,
                 'n_entries': int_or_none(n_entries),
-                '__last_playlist_index': max(ie_result['requested_entries'] or (0, 0)),
-                'playlist_count': ie_result.get('playlist_count'),
                 'playlist_index': playlist_index,
                 'playlist_autonumber': i + 1,
-                'playlist': title,
-                'playlist_id': ie_result.get('id'),
-                'playlist_title': ie_result.get('title'),
-                'playlist_uploader': ie_result.get('uploader'),
-                'playlist_uploader_id': ie_result.get('uploader_id'),
-                'extractor': ie_result['extractor'],
-                'webpage_url': ie_result['webpage_url'],
-                'webpage_url_basename': url_basename(ie_result['webpage_url']),
-                'webpage_url_domain': get_domain(ie_result['webpage_url']),
-                'extractor_key': ie_result['extractor_key'],
             })
+
+            if self._match_entry(entry_copy, incomplete=True) is not None:
+                # For compatabilty with youtube-dl. See https://github.com/yt-dlp/yt-dlp/issues/4369
+                resolved_entries[i] = (playlist_index, NO_DEFAULT)
+                continue
+
+            self.to_screen('[download] Downloading video %s of %s' % (
+                self._format_screen(i + 1, self.Styles.ID), self._format_screen(n_entries, self.Styles.EMPHASIS)))
+
+            extra.update({
+                'playlist_index': playlist_index,
+                'playlist_autonumber': i + 1,
+            })
+            entry_result = self.__process_iterable_entry(entry, download, extra)
             if not entry_result:
                 failures += 1
             if failures >= max_failures:
                 self.report_error(
                     f'Skipping the remaining entries in playlist "{title}" since {failures} items failed extraction')
                 break
-            resolved_entries[i] = (playlist_index, entry_result)
+            if keep_resolved_entries:
+                resolved_entries[i] = (playlist_index, entry_result)
 
         # Update with processed data
-        ie_result['requested_entries'], ie_result['entries'] = tuple(zip(*resolved_entries)) or ([], [])
+        ie_result['requested_entries'] = [i for i, e in resolved_entries if e is not NO_DEFAULT]
+        ie_result['entries'] = [e for _, e in resolved_entries if e is not NO_DEFAULT]
 
         # Write the updated info to json
         if _infojson_written is True and self._write_info_json(
@@ -1918,8 +1977,8 @@ class YoutubeDL:
                     filter_parts.append(string)
 
         def _remove_unused_ops(tokens):
-            # Remove operators that we don't use and join them with the surrounding strings
+            # Remove operators that we don't use and join them with the surrounding strings.
-            # for example: 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
+            # E.g. 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
             ALLOWED_OPS = ('/', '+', ',', '(', ')')
             last_string, last_start, last_end, last_line = None, None, None, None
             for type, string, start, end, line in tokens:
@@ -2035,14 +2094,13 @@ class YoutubeDL:
             the_only_video = video_fmts[0] if len(video_fmts) == 1 else None
             the_only_audio = audio_fmts[0] if len(audio_fmts) == 1 else None
 
-            output_ext = self.params.get('merge_output_format')
+            output_ext = get_compatible_ext(
-            if not output_ext:
+                vcodecs=[f.get('vcodec') for f in video_fmts],
-                if the_only_video:
+                acodecs=[f.get('acodec') for f in audio_fmts],
-                    output_ext = the_only_video['ext']
+                vexts=[f['ext'] for f in video_fmts],
-                elif the_only_audio and not video_fmts:
+                aexts=[f['ext'] for f in audio_fmts],
-                    output_ext = the_only_audio['ext']
+                preferences=(try_call(lambda: self.params['merge_output_format'].split('/'))
-                else:
+                             or self.params.get('prefer_free_formats') and ('webm', 'mkv')))
-                    output_ext = 'mkv'
 
             filtered = lambda *keys: filter(None, (traverse_obj(fmt, *keys) for fmt in formats_info))
 
@@ -2075,6 +2133,7 @@ class YoutubeDL:
                     'acodec': the_only_audio.get('acodec'),
                     'abr': the_only_audio.get('abr'),
                     'asr': the_only_audio.get('asr'),
+                    'audio_channels': the_only_audio.get('audio_channels')
                 })
 
             return new_dict
@@ -2377,13 +2436,18 @@ class YoutubeDL:
             self.report_warning('"duration" field is negative, there is an error in extractor')
 
         chapters = info_dict.get('chapters') or []
+        if chapters and chapters[0].get('start_time'):
+            chapters.insert(0, {'start_time': 0})
+
         dummy_chapter = {'end_time': 0, 'start_time': info_dict.get('duration')}
-        for prev, current, next_ in zip(
+        for idx, (prev, current, next_) in enumerate(zip(
-                (dummy_chapter, *chapters), chapters, (*chapters[1:], dummy_chapter)):
+                (dummy_chapter, *chapters), chapters, (*chapters[1:], dummy_chapter)), 1):
             if current.get('start_time') is None:
                 current['start_time'] = prev.get('end_time')
             if not current.get('end_time'):
                 current['end_time'] = next_.get('start_time')
+            if not current.get('title'):
+                current['title'] = f'<Untitled Chapter {idx}>'
 
         if 'playlist' not in info_dict:
             # It isn't part of a playlist
@@ -2430,7 +2494,7 @@ class YoutubeDL:
         info_dict['_has_drm'] = any(f.get('has_drm') for f in formats) or None
         if not self.params.get('allow_unplayable_formats'):
             formats = [f for f in formats if not f.get('has_drm')]
-            if info_dict['_has_drm'] and all(
+            if info_dict['_has_drm'] and formats and all(
                     f.get('acodec') == f.get('vcodec') == 'none' for f in formats):
                 self.report_warning(
                     'This video is DRM protected and only images are available for download. '
@@ -3009,33 +3073,9 @@ class YoutubeDL:
                         return
 
                 if info_dict.get('requested_formats') is not None:
-
-                    def compatible_formats(formats):
-                        # TODO: some formats actually allow this (mkv, webm, ogg, mp4), but not all of them.
-                        video_formats = [format for format in formats if format.get('vcodec') != 'none']
-                        audio_formats = [format for format in formats if format.get('acodec') != 'none']
-                        if len(video_formats) > 2 or len(audio_formats) > 2:
-                            return False
-
-                        # Check extension
-                        exts = {format.get('ext') for format in formats}
-                        COMPATIBLE_EXTS = (
-                            {'mp3', 'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'ismv', 'isma'},
-                            {'webm'},
-                        )
-                        for ext_sets in COMPATIBLE_EXTS:
-                            if ext_sets.issuperset(exts):
-                                return True
-                        # TODO: Check acodec/vcodec
-                        return False
-
                     requested_formats = info_dict['requested_formats']
                     old_ext = info_dict['ext']
                     if self.params.get('merge_output_format') is None:
-                        if not compatible_formats(requested_formats):
-                            info_dict['ext'] = 'mkv'
-                            self.report_warning(
-                                'Requested formats are incompatible for merge and will be merged into mkv')
                         if (info_dict['ext'] == 'webm'
                                 and info_dict.get('thumbnails')
                                 # check with type instead of pp_key, __name__, or isinstance
@@ -3173,22 +3213,23 @@ class YoutubeDL:
                             self.report_warning(f'{vid}: {msg}. Install ffmpeg to fix this automatically')
 
                     stretched_ratio = info_dict.get('stretched_ratio')
-                    ffmpeg_fixup(
+                    ffmpeg_fixup(stretched_ratio not in (1, None),
-                        stretched_ratio not in (1, None),
+                                 f'Non-uniform pixel ratio {stretched_ratio}',
-                        f'Non-uniform pixel ratio {stretched_ratio}',
+                                 FFmpegFixupStretchedPP)
-                        FFmpegFixupStretchedPP)
-
-                    ffmpeg_fixup(
-                        (info_dict.get('requested_formats') is None
-                         and info_dict.get('container') == 'm4a_dash'
-                         and info_dict.get('ext') == 'm4a'),
-                        'writing DASH m4a. Only some players support this container',
-                        FFmpegFixupM4aPP)
 
                     downloader = get_suitable_downloader(info_dict, self.params) if 'protocol' in info_dict else None
                     downloader = downloader.FD_NAME if downloader else None
 
-                    if info_dict.get('requested_formats') is None:  # Not necessary if doing merger
+                    ext = info_dict.get('ext')
+                    postprocessed_by_ffmpeg = info_dict.get('requested_formats') or any((
+                        isinstance(pp, FFmpegVideoConvertorPP)
+                        and resolve_recode_mapping(ext, pp.mapping)[0] not in (ext, None)
+                    ) for pp in self._pps['post_process'])
+
+                    if not postprocessed_by_ffmpeg:
+                        ffmpeg_fixup(ext == 'm4a' and info_dict.get('container') == 'm4a_dash',
+                                     'writing DASH m4a. Only some players support this container',
+                                     FFmpegFixupM4aPP)
                         ffmpeg_fixup(downloader == 'hlsnative' and not self.params.get('hls_use_mpegts')
                                      or info_dict.get('is_live') and self.params.get('hls_use_mpegts') is None,
                                      'Possible MPEG-TS in MP4 container or malformed AAC timestamps',
@@ -3394,18 +3435,16 @@ class YoutubeDL:
                     break
             else:
                 return
-        return f'{extractor.lower()} {video_id}'
+        return make_archive_id(extractor, video_id)
 
     def in_download_archive(self, info_dict):
         fn = self.params.get('download_archive')
         if fn is None:
             return False
 
-        vid_id = self._make_archive_id(info_dict)
+        vid_ids = [self._make_archive_id(info_dict)]
-        if not vid_id:
+        vid_ids.extend(info_dict.get('_old_archive_ids', []))
-            return False  # Incomplete video information
+        return any(id_ in self.archive for id_ in vid_ids)
-
-        return vid_id in self.archive
 
     def record_download_archive(self, info_dict):
         fn = self.params.get('download_archive')
@@ -3512,27 +3551,39 @@ class YoutubeDL:
                 ] for f in formats if f.get('preference') is None or f['preference'] >= -1000]
             return render_table(['format code', 'extension', 'resolution', 'note'], table, extra_gap=1)
 
+        def simplified_codec(f, field):
+            assert field in ('acodec', 'vcodec')
+            codec = f.get(field, 'unknown')
+            if not codec:
+                return 'unknown'
+            elif codec != 'none':
+                return '.'.join(codec.split('.')[:4])
+
+            if field == 'vcodec' and f.get('acodec') == 'none':
+                return 'images'
+            elif field == 'acodec' and f.get('vcodec') == 'none':
+                return ''
+            return self._format_out('audio only' if field == 'vcodec' else 'video only',
+                                    self.Styles.SUPPRESS)
+
         delim = self._format_out('\u2502', self.Styles.DELIM, '|', test_encoding=True)
         table = [
             [
                 self._format_out(format_field(f, 'format_id'), self.Styles.ID),
                 format_field(f, 'ext'),
                 format_field(f, func=self.format_resolution, ignore=('audio only', 'images')),
-                format_field(f, 'fps', '\t%d'),
+                format_field(f, 'fps', '\t%d', func=round),
                 format_field(f, 'dynamic_range', '%s', ignore=(None, 'SDR')).replace('HDR', ''),
+                format_field(f, 'audio_channels', '\t%s'),
                 delim,
                 format_field(f, 'filesize', ' \t%s', func=format_bytes) + format_field(f, 'filesize_approx', '~\t%s', func=format_bytes),
-                format_field(f, 'tbr', '\t%dk'),
+                format_field(f, 'tbr', '\t%dk', func=round),
                 shorten_protocol_name(f.get('protocol', '')),
                 delim,
-                format_field(f, 'vcodec', default='unknown').replace(
+                simplified_codec(f, 'vcodec'),
-                    'none', 'images' if f.get('acodec') == 'none'
+                format_field(f, 'vbr', '\t%dk', func=round),
-                            else self._format_out('audio only', self.Styles.SUPPRESS)),
+                simplified_codec(f, 'acodec'),
-                format_field(f, 'vbr', '\t%dk'),
+                format_field(f, 'abr', '\t%dk', func=round),
-                format_field(f, 'acodec', default='unknown').replace(
-                    'none', '' if f.get('vcodec') == 'none'
-                            else self._format_out('video only', self.Styles.SUPPRESS)),
-                format_field(f, 'abr', '\t%dk'),
                 format_field(f, 'asr', '\t%s', func=format_decimal_suffix),
                 join_nonempty(
                     self._format_out('UNSUPPORTED', 'light red') if f.get('ext') in ('f4f', 'f4m') else None,
@@ -3543,7 +3594,7 @@ class YoutubeDL:
                     delim=' '),
             ] for f in formats if f.get('preference') is None or f['preference'] >= -1000]
         header_line = self._list_format_headers(
-            'ID', 'EXT', 'RESOLUTION', '\tFPS', 'HDR', delim, '\tFILESIZE', '\tTBR', 'PROTO',
+            'ID', 'EXT', 'RESOLUTION', '\tFPS', 'HDR', 'CH', delim, '\tFILESIZE', '\tTBR', 'PROTO',
             delim, 'VCODEC', '\tVBR', 'ACODEC', '\tABR', '\tASR', 'MORE INFO')
 
         return render_table(
@@ -3628,6 +3679,8 @@ class YoutubeDL:
             write_debug = lambda msg: self._write_string(f'[debug] {msg}\n')
 
         source = detect_variant()
+        if VARIANT not in (None, 'pip'):
+            source += '*'
         write_debug(join_nonempty(
             'yt-dlp version', __version__,
             f'[{RELEASE_GIT_HEAD}]' if RELEASE_GIT_HEAD else '',

yt_dlp/__init__.py

@@ -1,7 +1,12 @@
-f'You are using an unsupported version of Python. Only Python versions 3.6 and above are supported by yt-dlp'  # noqa: F541
+try:
+    import contextvars  # noqa: F401
+except Exception:
+    raise Exception(
+        f'You are using an unsupported version of Python. Only Python versions 3.7 and above are supported by yt-dlp')  # noqa: F541
 
 __license__ = 'Public Domain'
 
+import collections
 import getpass
 import itertools
 import optparse
@@ -19,6 +24,8 @@ from .extractor.common import InfoExtractor
 from .options import parseOpts
 from .postprocessor import (
     FFmpegExtractAudioPP,
+    FFmpegMergerPP,
+    FFmpegPostProcessor,
     FFmpegSubtitlesConvertorPP,
     FFmpegThumbnailsConvertorPP,
     FFmpegVideoConvertorPP,
@@ -221,6 +228,8 @@ def validate_options(opts):
         validate_regex('format sorting', f, InfoExtractor.FormatSort.regex)
 
     # Postprocessor formats
+    validate_regex('merge output format', opts.merge_output_format,
+                   r'({0})(/({0}))*'.format('|'.join(map(re.escape, FFmpegMergerPP.SUPPORTED_EXTS))))
     validate_regex('audio format', opts.audioformat, FFmpegExtractAudioPP.FORMAT_RE)
     validate_in('subtitle format', opts.convertsubtitles, FFmpegSubtitlesConvertorPP.SUPPORTED_EXTS)
     validate_regex('thumbnail format', opts.convertthumbnails, FFmpegThumbnailsConvertorPP.FORMAT_RE)
@@ -516,7 +525,7 @@ def validate_options(opts):
         # Do not unnecessarily download audio
         opts.format = 'bestaudio/best'
 
-    if opts.getcomments and opts.writeinfojson is None:
+    if opts.getcomments and opts.writeinfojson is None and not opts.embed_infojson:
         # If JSON is not printed anywhere, but comments are requested, save it to file
         if not opts.dumpjson or opts.print_json or opts.dump_single_json:
             opts.writeinfojson = True
@@ -665,8 +674,11 @@ def get_postprocessors(opts):
         }
 
 
+ParsedOptions = collections.namedtuple('ParsedOptions', ('parser', 'options', 'urls', 'ydl_opts'))
+
+
 def parse_options(argv=None):
-    """ @returns (parser, opts, urls, ydl_opts) """
+    """@returns ParsedOptions(parser, opts, urls, ydl_opts)"""
     parser, opts, urls = parseOpts(argv)
     urls = get_urls(urls, opts.batchfile, opts.verbose)
 
@@ -684,13 +696,28 @@ def parse_options(argv=None):
         'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
     ))
 
+    playlist_pps = [pp for pp in postprocessors if pp.get('when') == 'playlist']
+    write_playlist_infojson = (opts.writeinfojson and not opts.clean_infojson
+                               and opts.allow_playlist_files and opts.outtmpl.get('pl_infojson') != '')
+    if not any((
+        opts.extract_flat,
+        opts.dump_single_json,
+        opts.forceprint.get('playlist'),
+        opts.print_to_file.get('playlist'),
+        write_playlist_infojson,
+    )):
+        if not playlist_pps:
+            opts.extract_flat = 'discard'
+        elif playlist_pps == [{'key': 'FFmpegConcat', 'only_multi_video': True, 'when': 'playlist'}]:
+            opts.extract_flat = 'discard_in_playlist'
+
     final_ext = (
         opts.recodevideo if opts.recodevideo in FFmpegVideoConvertorPP.SUPPORTED_EXTS
         else opts.remuxvideo if opts.remuxvideo in FFmpegVideoRemuxerPP.SUPPORTED_EXTS
         else opts.audioformat if (opts.extractaudio and opts.audioformat in FFmpegExtractAudioPP.SUPPORTED_EXTS)
         else None)
 
-    return parser, opts, urls, {
+    return ParsedOptions(parser, opts, urls, {
         'usenetrc': opts.usenetrc,
         'netrc_location': opts.netrc_location,
         'username': opts.username,
@@ -863,7 +890,7 @@ def parse_options(argv=None):
         '_warnings': warnings,
         '_deprecation_warnings': deprecation_warnings,
         'compat_opts': opts.compat_opts,
-    }
+    })
 
 
 def _real_main(argv=None):
@@ -880,6 +907,11 @@ def _real_main(argv=None):
     if print_extractor_information(opts, all_urls):
         return
 
+    # We may need ffmpeg_location without having access to the YoutubeDL instance
+    # See https://github.com/yt-dlp/yt-dlp/issues/2191
+    if opts.ffmpeg_location:
+        FFmpegPostProcessor._ffmpeg_location.set(opts.ffmpeg_location)
+
     with YoutubeDL(ydl_opts) as ydl:
         pre_process = opts.update_self or opts.rm_cachedir
         actual_use = all_urls or opts.load_info_filename

yt_dlp/aes.py

@@ -24,6 +24,10 @@ else:
         return intlist_to_bytes(aes_gcm_decrypt_and_verify(*map(bytes_to_intlist, (data, key, tag, nonce))))
 
 
+def aes_cbc_encrypt_bytes(data, key, iv, **kwargs):
+    return intlist_to_bytes(aes_cbc_encrypt(*map(bytes_to_intlist, (data, key, iv)), **kwargs))
+
+
 def unpad_pkcs7(data):
     return data[:-compat_ord(data[-1])]
 
@@ -31,6 +35,33 @@ def unpad_pkcs7(data):
 BLOCK_SIZE_BYTES = 16
 
 
+def pad_block(block, padding_mode):
+    """
+    Pad a block with the given padding mode
+    @param {int[]} block        block to pad
+    @param padding_mode         padding mode
+    """
+    padding_size = BLOCK_SIZE_BYTES - len(block)
+
+    PADDING_BYTE = {
+        'pkcs7': padding_size,
+        'iso7816': 0x0,
+        'whitespace': 0x20,
+        'zero': 0x0,
+    }
+
+    if padding_size < 0:
+        raise ValueError('Block size exceeded')
+    elif padding_mode not in PADDING_BYTE:
+        raise NotImplementedError(f'Padding mode {padding_mode} is not implemented')
+
+    if padding_mode == 'iso7816' and padding_size:
+        block = block + [0x80]  # NB: += mutates list
+        padding_size -= 1
+
+    return block + [PADDING_BYTE[padding_mode]] * padding_size
+
+
 def aes_ecb_encrypt(data, key, iv=None):
     """
     Encrypt with aes in ECB mode
@@ -137,13 +168,14 @@ def aes_cbc_decrypt(data, key, iv):
     return decrypted_data
 
 
-def aes_cbc_encrypt(data, key, iv):
+def aes_cbc_encrypt(data, key, iv, *, padding_mode='pkcs7'):
     """
-    Encrypt with aes in CBC mode. Using PKCS#7 padding
+    Encrypt with aes in CBC mode
 
     @param {int[]} data        cleartext
     @param {int[]} key         16/24/32-Byte cipher key
     @param {int[]} iv          16-Byte IV
+    @param padding_mode        Padding mode to use
     @returns {int[]}           encrypted data
     """
     expanded_key = key_expansion(key)
@@ -153,8 +185,8 @@ def aes_cbc_encrypt(data, key, iv):
     previous_cipher_block = iv
     for i in range(block_count):
         block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
-        remaining_length = BLOCK_SIZE_BYTES - len(block)
+        block = pad_block(block, padding_mode)
-        block += [remaining_length] * remaining_length
+
         mixed_block = xor(block, previous_cipher_block)
 
         encrypted_block = aes_encrypt(mixed_block, expanded_key)
@@ -502,13 +534,22 @@ def ghash(subkey, data):
 
 
 __all__ = [
-    'aes_ctr_decrypt',
     'aes_cbc_decrypt',
     'aes_cbc_decrypt_bytes',
+    'aes_ctr_decrypt',
     'aes_decrypt_text',
-    'aes_encrypt',
+    'aes_decrypt',
+    'aes_ecb_decrypt',
     'aes_gcm_decrypt_and_verify',
     'aes_gcm_decrypt_and_verify_bytes',
+
+    'aes_cbc_encrypt',
+    'aes_cbc_encrypt_bytes',
+    'aes_ctr_encrypt',
+    'aes_ecb_encrypt',
+    'aes_encrypt',
+
     'key_expansion',
+    'pad_block',
     'unpad_pkcs7',
 ]

yt_dlp/compat/__init__.py

@@ -3,19 +3,12 @@ import sys
 import warnings
 import xml.etree.ElementTree as etree
 
-from . import re
 from ._deprecated import *  # noqa: F401, F403
 from .compat_utils import passthrough_module
 
 # XXX: Implement this the same way as other DeprecationWarnings without circular import
-try:
+passthrough_module(__name__, '._legacy', callback=lambda attr: warnings.warn(
-    passthrough_module(__name__, '._legacy', callback=lambda attr: warnings.warn(
+    DeprecationWarning(f'{__name__}.{attr} is deprecated'), stacklevel=3))
-        DeprecationWarning(f'{__name__}.{attr} is deprecated'), stacklevel=2))
-    HAS_LEGACY = True
-except ModuleNotFoundError:
-    # Keep working even without _legacy module
-    HAS_LEGACY = False
-del passthrough_module
 
 
 # HTMLParseError has been deprecated in Python 3.3 and removed in
@@ -39,6 +32,7 @@ compat_os_name = os._name if os.name == 'java' else os.name
 
 if compat_os_name == 'nt':
     def compat_shlex_quote(s):
+        import re
         return s if re.match(r'^[-_\w./]+$', s) else '"%s"' % s.replace('"', '\\"')
 else:
     from shlex import quote as compat_shlex_quote  # noqa: F401
@@ -76,3 +70,9 @@ if compat_os_name in ('nt', 'ce'):
         return userhome + path[i:]
 else:
     compat_expanduser = os.path.expanduser
+
+
+# NB: Add modules that are imported dynamically here so that PyInstaller can find them
+# See https://github.com/pyinstaller/pyinstaller-hooks-contrib/issues/438
+if False:
+    from . import _legacy  # noqa: F401

yt_dlp/compat/_legacy.py

@@ -22,10 +22,14 @@ import urllib.request
 import xml.etree.ElementTree as etree
 from subprocess import DEVNULL
 
-from .compat_utils import passthrough_module  # isort: split
+# isort: split
-from .asyncio import run as compat_asyncio_run  # noqa: F401
+import asyncio  # noqa: F401
-from .re import Pattern as compat_Pattern  # noqa: F401
+import re  # noqa: F401
-from .re import match as compat_Match  # noqa: F401
+from asyncio import run as compat_asyncio_run  # noqa: F401
+from re import Pattern as compat_Pattern  # noqa: F401
+from re import match as compat_Match  # noqa: F401
+
+from .compat_utils import passthrough_module
 from ..dependencies import Cryptodome_AES as compat_pycrypto_AES  # noqa: F401
 from ..dependencies import brotli as compat_brotli  # noqa: F401
 from ..dependencies import websockets as compat_websockets  # noqa: F401

yt_dlp/compat/asyncio.py

@@ -1,23 +0,0 @@
-# flake8: noqa: F405
-from asyncio import *  # noqa: F403
-
-from .compat_utils import passthrough_module
-
-passthrough_module(__name__, 'asyncio')
-del passthrough_module
-
-try:
-    run  # >= 3.7
-except NameError:
-    def run(coro):
-        try:
-            loop = get_event_loop()
-        except RuntimeError:
-            loop = new_event_loop()
-            set_event_loop(loop)
-        loop.run_until_complete(coro)
-
-try:
-    all_tasks  # >= 3.7
-except NameError:
-    all_tasks = Task.all_tasks

yt_dlp/compat/imghdr.py

@@ -2,13 +2,15 @@ tests = {
     'webp': lambda h: h[0:4] == b'RIFF' and h[8:] == b'WEBP',
     'png': lambda h: h[:8] == b'\211PNG\r\n\032\n',
     'jpeg': lambda h: h[6:10] in (b'JFIF', b'Exif'),
+    'gif': lambda h: h[:6] in (b'GIF87a', b'GIF89a'),
 }
 
 
-def what(path):
+def what(file=None, h=None):
-    """Detect format of image (Currently supports jpeg, png, webp only)
+    """Detect format of image (Currently supports jpeg, png, webp, gif only)
     Ref: https://github.com/python/cpython/blob/3.10/Lib/imghdr.py
     """
-    with open(path, 'rb') as f:
+    if h is None:
-        head = f.read(12)
+        with open(file, 'rb') as f:
-    return next((type_ for type_, test in tests.items() if test(head)), None)
+            h = f.read(12)
+    return next((type_ for type_, test in tests.items() if test(h)), None)

yt_dlp/compat/re.py

@@ -1,18 +0,0 @@
-# flake8: noqa: F405
-from re import *  # F403
-
-from .compat_utils import passthrough_module
-
-passthrough_module(__name__, 're')
-del passthrough_module
-
-try:
-    Pattern  # >= 3.7
-except NameError:
-    Pattern = type(compile(''))
-
-
-try:
-    Match  # >= 3.7
-except NameError:
-    Match = type(compile('').match(''))

yt_dlp/cookies.py

@@ -1,6 +1,5 @@
 import base64
 import contextlib
-import ctypes
 import http.cookiejar
 import json
 import os
@@ -876,10 +875,12 @@ def _decrypt_windows_dpapi(ciphertext, logger):
     References:
         - https://docs.microsoft.com/en-us/windows/win32/api/dpapi/nf-dpapi-cryptunprotectdata
     """
-    from ctypes.wintypes import DWORD
+
+    import ctypes
+    import ctypes.wintypes
 
     class DATA_BLOB(ctypes.Structure):
-        _fields_ = [('cbData', DWORD),
+        _fields_ = [('cbData', ctypes.wintypes.DWORD),
                     ('pbData', ctypes.POINTER(ctypes.c_char))]
 
     buffer = ctypes.create_string_buffer(ciphertext)

yt_dlp/dependencies.py

@@ -28,7 +28,7 @@ try:
 except ImportError:
     try:
         from Crypto.Cipher import AES as Cryptodome_AES
-    except ImportError:
+    except (ImportError, SyntaxError):  # Old Crypto gives SyntaxError in newer Python
         Cryptodome_AES = None
     else:
         try:

yt_dlp/downloader/common.py

@@ -1,5 +1,6 @@
 import contextlib
 import errno
+import functools
 import os
 import random
 import re
@@ -12,14 +13,15 @@ from ..minicurses import (
     QuietMultilinePrinter,
 )
 from ..utils import (
+    IDENTITY,
+    NO_DEFAULT,
     NUMBER_RE,
     LockingUnsupportedError,
     Namespace,
+    RetryManager,
     classproperty,
     decodeArgument,
     encodeFilename,
-    error_to_compat_str,
-    float_or_none,
     format_bytes,
     join_nonempty,
     sanitize_open,
@@ -215,27 +217,24 @@ class FileDownloader:
         return filename + '.ytdl'
 
     def wrap_file_access(action, *, fatal=False):
-        def outer(func):
+        def error_callback(err, count, retries, *, fd):
-            def inner(self, *args, **kwargs):
+            return RetryManager.report_retry(
-                file_access_retries = self.params.get('file_access_retries', 0)
+                err, count, retries, info=fd.__to_screen,
-                retry = 0
+                warn=lambda e: (time.sleep(0.01), fd.to_screen(f'[download] Unable to {action} file: {e}')),
-                while True:
+                error=None if fatal else lambda e: fd.report_error(f'Unable to {action} file: {e}'),
-                    try:
+                sleep_func=fd.params.get('retry_sleep_functions', {}).get('file_access'))
-                        return func(self, *args, **kwargs)
+
-                    except OSError as err:
+        def wrapper(self, func, *args, **kwargs):
-                        retry = retry + 1
+            for retry in RetryManager(self.params.get('file_access_retries'), error_callback, fd=self):
-                        if retry > file_access_retries or err.errno not in (errno.EACCES, errno.EINVAL):
+                try:
-                            if not fatal:
+                    return func(self, *args, **kwargs)
-                                self.report_error(f'unable to {action} file: {err}')
+                except OSError as err:
-                                return
+                    if err.errno in (errno.EACCES, errno.EINVAL):
-                            raise
+                        retry.error = err
-                        self.to_screen(
+                        continue
-                            f'[download] Unable to {action} file due to file access error. '
+                    retry.error_callback(err, 1, 0)
-                            f'Retrying (attempt {retry} of {self.format_retries(file_access_retries)}) ...')
+
-                        if not self.sleep_retry('file_access', retry):
+        return functools.partial(functools.partialmethod, wrapper)
-                            time.sleep(0.01)
-            return inner
-        return outer
 
     @wrap_file_access('open', fatal=True)
     def sanitize_open(self, filename, open_mode):
@@ -335,7 +334,10 @@ class FileDownloader:
         if s['status'] == 'finished':
             if self.params.get('noprogress'):
                 self.to_screen('[download] Download completed')
+            speed = try_call(lambda: s['total_bytes'] / s['elapsed'])
             s.update({
+                'speed': speed,
+                '_speed_str': self.format_speed(speed).strip(),
                 '_total_bytes_str': format_bytes(s.get('total_bytes')),
                 '_elapsed_str': self.format_seconds(s.get('elapsed')),
                 '_percent_str': self.format_percent(100),
@@ -344,6 +346,7 @@ class FileDownloader:
                 '100%%',
                 with_fields(('total_bytes', 'of %(_total_bytes_str)s')),
                 with_fields(('elapsed', 'in %(_elapsed_str)s')),
+                with_fields(('speed', 'at %(_speed_str)s')),
                 delim=' '))
 
         if s['status'] != 'downloading':
@@ -378,25 +381,20 @@ class FileDownloader:
         """Report attempt to resume at given byte."""
         self.to_screen('[download] Resuming download at byte %s' % resume_len)
 
-    def report_retry(self, err, count, retries):
+    def report_retry(self, err, count, retries, frag_index=NO_DEFAULT, fatal=True):
-        """Report retry in case of HTTP error 5xx"""
+        """Report retry"""
-        self.__to_screen(
+        is_frag = False if frag_index is NO_DEFAULT else 'fragment'
-            '[download] Got server HTTP error: %s. Retrying (attempt %d of %s) ...'
+        RetryManager.report_retry(
-            % (error_to_compat_str(err), count, self.format_retries(retries)))
+            err, count, retries, info=self.__to_screen,
-        self.sleep_retry('http', count)
+            warn=lambda msg: self.__to_screen(f'[download] Got error: {msg}'),
+            error=IDENTITY if not fatal else lambda e: self.report_error(f'\r[download] Got error: {e}'),
+            sleep_func=self.params.get('retry_sleep_functions', {}).get(is_frag or 'http'),
+            suffix=f'fragment{"s" if frag_index is None else f" {frag_index}"}' if is_frag else None)
 
     def report_unable_to_resume(self):
         """Report it was impossible to resume download."""
         self.to_screen('[download] Unable to resume')
 
-    def sleep_retry(self, retry_type, count):
-        sleep_func = self.params.get('retry_sleep_functions', {}).get(retry_type)
-        delay = float_or_none(sleep_func(n=count - 1)) if sleep_func else None
-        if delay:
-            self.__to_screen(f'Sleeping {delay:.2f} seconds ...')
-            time.sleep(delay)
-        return sleep_func is not None
-
     @staticmethod
     def supports_manifest(manifest):
         """ Whether the downloader can download the fragments from the manifest.
@@ -450,8 +448,7 @@ class FileDownloader:
         raise NotImplementedError('This method must be implemented by subclasses')
 
     def _hook_progress(self, status, info_dict):
-        if not self._progress_hooks:
+        # Ideally we want to make a copy of the dict, but that is too slow
-            return
         status['info_dict'] = info_dict
         # youtube-dl passes the same status object to all the hooks.
         # Some third party scripts seems to be relying on this.

yt_dlp/downloader/external.py

@@ -10,6 +10,7 @@ from ..compat import functools
 from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
 from ..utils import (
     Popen,
+    RetryManager,
     _configuration_args,
     check_executable,
     classproperty,
@@ -134,29 +135,22 @@ class ExternalFD(FragmentFD):
                 self.to_stderr(stderr)
             return returncode
 
-        fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
-        count = 0
+        retry_manager = RetryManager(self.params.get('fragment_retries'), self.report_retry,
-        while count <= fragment_retries:
+                                     frag_index=None, fatal=not skip_unavailable_fragments)
+        for retry in retry_manager:
             _, stderr, returncode = Popen.run(cmd, text=True, stderr=subprocess.PIPE)
             if not returncode:
                 break
-
             # TODO: Decide whether to retry based on error code
             # https://aria2.github.io/manual/en/html/aria2c.html#exit-status
             if stderr:
                 self.to_stderr(stderr)
-            count += 1
+            retry.error = Exception()
-            if count <= fragment_retries:
+            continue
-                self.to_screen(
+        if not skip_unavailable_fragments and retry_manager.error:
-                    '[%s] Got error. Retrying fragments (attempt %d of %s)...'
+            return -1
-                    % (self.get_basename(), count, self.format_retries(fragment_retries)))
-                self.sleep_retry('fragment', count)
-        if count > fragment_retries:
-            if not skip_unavailable_fragments:
-                self.report_error('Giving up after %s fragment retries' % fragment_retries)
-                return -1
 
         decrypt_fragment = self.decrypter(info_dict)
         dest, _ = self.sanitize_open(tmpfilename, 'wb')

yt_dlp/downloader/f4m.py

@@ -184,7 +184,7 @@ def build_fragments_list(boot_info):
     first_frag_number = fragment_run_entry_table[0]['first']
     fragments_counter = itertools.count(first_frag_number)
     for segment, fragments_count in segment_run_table['segment_run']:
-        # In some live HDS streams (for example Rai), `fragments_count` is
+        # In some live HDS streams (e.g. Rai), `fragments_count` is
         # abnormal and causing out-of-memory errors. It's OK to change the
         # number of fragments for live streams as they are updated periodically
         if fragments_count == 4294967295 and boot_info['live']:

yt_dlp/downloader/fragment.py

@@ -14,8 +14,8 @@ from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
 from ..compat import compat_os_name
 from ..utils import (
     DownloadError,
+    RetryManager,
     encodeFilename,
-    error_to_compat_str,
     sanitized_Request,
     traverse_obj,
 )
@@ -65,10 +65,9 @@ class FragmentFD(FileDownloader):
     """
 
     def report_retry_fragment(self, err, frag_index, count, retries):
-        self.to_screen(
+        self.deprecation_warning(
-            '\r[download] Got server HTTP error: %s. Retrying fragment %d (attempt %d of %s) ...'
+            'yt_dlp.downloader.FragmentFD.report_retry_fragment is deprecated. Use yt_dlp.downloader.FileDownloader.report_retry instead')
-            % (error_to_compat_str(err), frag_index, count, self.format_retries(retries)))
+        return self.report_retry(err, count, retries, frag_index)
-        self.sleep_retry('fragment', count)
 
     def report_skip_fragment(self, frag_index, err=None):
         err = f' {err};' if err else ''
@@ -347,6 +346,8 @@ class FragmentFD(FileDownloader):
             return _key_cache[url]
 
         def decrypt_fragment(fragment, frag_content):
+            if frag_content is None:
+                return
             decrypt_info = fragment.get('decrypt_info')
             if not decrypt_info or decrypt_info['METHOD'] != 'AES-128':
                 return frag_content
@@ -432,7 +433,6 @@ class FragmentFD(FileDownloader):
         if not interrupt_trigger:
             interrupt_trigger = (True, )
 
-        fragment_retries = self.params.get('fragment_retries', 0)
         is_fatal = (
             ((lambda _: False) if info_dict.get('is_live') else (lambda idx: idx == 0))
             if self.params.get('skip_unavailable_fragments', True) else (lambda _: True))
@@ -452,32 +452,25 @@ class FragmentFD(FileDownloader):
                 headers['Range'] = 'bytes=%d-%d' % (byte_range['start'], byte_range['end'] - 1)
 
             # Never skip the first fragment
-            fatal, count = is_fatal(fragment.get('index') or (frag_index - 1)), 0
+            fatal = is_fatal(fragment.get('index') or (frag_index - 1))
-            while count <= fragment_retries:
+
+            def error_callback(err, count, retries):
+                if fatal and count > retries:
+                    ctx['dest_stream'].close()
+                self.report_retry(err, count, retries, frag_index, fatal)
+                ctx['last_error'] = err
+
+            for retry in RetryManager(self.params.get('fragment_retries'), error_callback):
                 try:
                     ctx['fragment_count'] = fragment.get('fragment_count')
-                    if self._download_fragment(ctx, fragment['url'], info_dict, headers):
+                    if not self._download_fragment(ctx, fragment['url'], info_dict, headers):
-                        break
+                        return
-                    return
                 except (urllib.error.HTTPError, http.client.IncompleteRead) as err:
-                    # Unavailable (possibly temporary) fragments may be served.
+                    retry.error = err
-                    # First we try to retry then either skip or abort.
+                    continue
-                    # See https://github.com/ytdl-org/youtube-dl/issues/10165,
+                except DownloadError:  # has own retry settings
-                    # https://github.com/ytdl-org/youtube-dl/issues/10448).
+                    if fatal:
-                    count += 1
+                        raise
-                    ctx['last_error'] = err
-                    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 and fatal:
-                ctx['dest_stream'].close()
-                self.report_error('Giving up after %s fragment retries' % fragment_retries)
 
         def append_fragment(frag_content, frag_index, ctx):
             if frag_content:

yt_dlp/downloader/http.py

@@ -9,6 +9,7 @@ import urllib.error
 from .common import FileDownloader
 from ..utils import (
     ContentTooShortError,
+    RetryManager,
     ThrottledDownload,
     XAttrMetadataError,
     XAttrUnavailableError,
@@ -72,9 +73,6 @@ class HttpFD(FileDownloader):
 
         ctx.is_resume = ctx.resume_len > 0
 
-        count = 0
-        retries = self.params.get('retries', 0)
-
         class SucceedDownload(Exception):
             pass
 
@@ -206,6 +204,12 @@ class HttpFD(FileDownloader):
             except RESPONSE_READ_EXCEPTIONS as err:
                 raise RetryDownload(err)
 
+        def close_stream():
+            if ctx.stream is not None:
+                if not ctx.tmpfilename == '-':
+                    ctx.stream.close()
+                ctx.stream = None
+
         def download():
             data_len = ctx.data.info().get('Content-length', None)
 
@@ -239,12 +243,9 @@ class HttpFD(FileDownloader):
             before = start  # start measuring
 
             def retry(e):
-                to_stdout = ctx.tmpfilename == '-'
+                close_stream()
-                if ctx.stream is not None:
+                ctx.resume_len = (byte_counter if ctx.tmpfilename == '-'
-                    if not to_stdout:
+                                  else os.path.getsize(encodeFilename(ctx.tmpfilename)))
-                        ctx.stream.close()
-                    ctx.stream = None
-                ctx.resume_len = byte_counter if to_stdout else os.path.getsize(encodeFilename(ctx.tmpfilename))
                 raise RetryDownload(e)
 
             while True:
@@ -346,9 +347,7 @@ class HttpFD(FileDownloader):
 
             if data_len is not None and byte_counter != data_len:
                 err = ContentTooShortError(byte_counter, int(data_len))
-                if count <= retries:
+                retry(err)
-                    retry(err)
-                raise err
 
             self.try_rename(ctx.tmpfilename, ctx.filename)
 
@@ -367,21 +366,20 @@ class HttpFD(FileDownloader):
 
             return True
 
-        while count <= retries:
+        for retry in RetryManager(self.params.get('retries'), self.report_retry):
             try:
                 establish_connection()
                 return download()
-            except RetryDownload as e:
+            except RetryDownload as err:
-                count += 1
+                retry.error = err.source_error
-                if count <= retries:
-                    self.report_retry(e.source_error, count, retries)
-                else:
-                    self.to_screen(f'[download] Got server HTTP error: {e.source_error}')
                 continue
             except NextFragment:
+                retry.error = None
+                retry.attempt -= 1
                 continue
             except SucceedDownload:
                 return True
-
+            except:  # noqa: E722
-        self.report_error('giving up after %s retries' % retries)
+                close_stream()
+                raise
         return False

yt_dlp/downloader/ism.py

@@ -5,6 +5,7 @@ import time
 import urllib.error
 
 from .fragment import FragmentFD
+from ..utils import RetryManager
 
 u8 = struct.Struct('>B')
 u88 = struct.Struct('>Bx')
@@ -245,7 +246,6 @@ class IsmFD(FragmentFD):
             'ism_track_written': False,
         })
 
-        fragment_retries = self.params.get('fragment_retries', 0)
         skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
 
         frag_index = 0
@@ -253,8 +253,10 @@ class IsmFD(FragmentFD):
             frag_index += 1
             if frag_index <= ctx['fragment_index']:
                 continue
-            count = 0
+
-            while count <= fragment_retries:
+            retry_manager = RetryManager(self.params.get('fragment_retries'), self.report_retry,
+                                         frag_index=frag_index, fatal=not skip_unavailable_fragments)
+            for retry in retry_manager:
                 try:
                     success = self._download_fragment(ctx, segment['url'], info_dict)
                     if not success:
@@ -267,18 +269,14 @@ class IsmFD(FragmentFD):
                         write_piff_header(ctx['dest_stream'], info_dict['_download_params'])
                         extra_state['ism_track_written'] = True
                     self._append_fragment(ctx, frag_content)
-                    break
                 except urllib.error.HTTPError as err:
-                    count += 1
+                    retry.error = err
-                    if count <= fragment_retries:
-                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
-            if count > fragment_retries:
-                if skip_unavailable_fragments:
-                    self.report_skip_fragment(frag_index)
                     continue
-                self.report_error('giving up after %s fragment retries' % fragment_retries)
+
-                return False
+            if retry_manager.error:
+                if not skip_unavailable_fragments:
+                    return False
+                self.report_skip_fragment(frag_index)
 
         self._finish_frag_download(ctx, info_dict)
-
         return True

yt_dlp/downloader/mhtml.py

@@ -4,6 +4,7 @@ import re
 import uuid
 
 from .fragment import FragmentFD
+from ..compat import imghdr
 from ..utils import escapeHTML, formatSeconds, srt_subtitles_timecode, urljoin
 from ..version import __version__ as YT_DLP_VERSION
 
@@ -166,21 +167,13 @@ body > figure > img {
                 continue
             frag_content = self._read_fragment(ctx)
 
-            mime_type = b'image/jpeg'
-            if frag_content.startswith(b'\x89PNG\r\n\x1a\n'):
-                mime_type = b'image/png'
-            if frag_content.startswith((b'GIF87a', b'GIF89a')):
-                mime_type = b'image/gif'
-            if frag_content.startswith(b'RIFF') and frag_content[8:12] == b'WEBP':
-                mime_type = b'image/webp'
-
             frag_header = io.BytesIO()
             frag_header.write(
                 b'--%b\r\n' % frag_boundary.encode('us-ascii'))
             frag_header.write(
                 b'Content-ID: <%b>\r\n' % self._gen_cid(i, fragment, frag_boundary).encode('us-ascii'))
             frag_header.write(
-                b'Content-type: %b\r\n' % mime_type)
+                b'Content-type: %b\r\n' % f'image/{imghdr.what(h=frag_content) or "jpeg"}'.encode())
             frag_header.write(
                 b'Content-length: %u\r\n' % len(frag_content))
             frag_header.write(

yt_dlp/downloader/websocket.py

@@ -1,3 +1,4 @@
+import asyncio
 import contextlib
 import os
 import signal
@@ -5,7 +6,6 @@ import threading
 
 from .common import FileDownloader
 from .external import FFmpegFD
-from ..compat import asyncio
 from ..dependencies import websockets
 
 

yt_dlp/downloader/youtube_live_chat.py

@@ -3,7 +3,13 @@ import time
 import urllib.error
 
 from .fragment import FragmentFD
-from ..utils import RegexNotFoundError, dict_get, int_or_none, try_get
+from ..utils import (
+    RegexNotFoundError,
+    RetryManager,
+    dict_get,
+    int_or_none,
+    try_get,
+)
 
 
 class YoutubeLiveChatFD(FragmentFD):
@@ -16,7 +22,6 @@ class YoutubeLiveChatFD(FragmentFD):
             self.report_warning('Live chat download runs until the livestream ends. '
                                 'If you wish to download the video simultaneously, run a separate yt-dlp instance')
 
-        fragment_retries = self.params.get('fragment_retries', 0)
         test = self.params.get('test', False)
 
         ctx = {
@@ -104,8 +109,7 @@ class YoutubeLiveChatFD(FragmentFD):
             return continuation_id, live_offset, click_tracking_params
 
         def download_and_parse_fragment(url, frag_index, request_data=None, headers=None):
-            count = 0
+            for retry in RetryManager(self.params.get('fragment_retries'), self.report_retry, frag_index=frag_index):
-            while count <= fragment_retries:
                 try:
                     success = dl_fragment(url, request_data, headers)
                     if not success:
@@ -120,21 +124,15 @@ class YoutubeLiveChatFD(FragmentFD):
                     live_chat_continuation = try_get(
                         data,
                         lambda x: x['continuationContents']['liveChatContinuation'], dict) or {}
-                    if info_dict['protocol'] == 'youtube_live_chat_replay':
+
-                        if frag_index == 1:
+                    func = (info_dict['protocol'] == 'youtube_live_chat' and parse_actions_live
-                            continuation_id, offset, click_tracking_params = try_refresh_replay_beginning(live_chat_continuation)
+                            or frag_index == 1 and try_refresh_replay_beginning
-                        else:
+                            or parse_actions_replay)
-                            continuation_id, offset, click_tracking_params = parse_actions_replay(live_chat_continuation)
+                    return (True, *func(live_chat_continuation))
-                    elif info_dict['protocol'] == 'youtube_live_chat':
-                        continuation_id, offset, click_tracking_params = parse_actions_live(live_chat_continuation)
-                    return True, continuation_id, offset, click_tracking_params
                 except urllib.error.HTTPError as err:
-                    count += 1
+                    retry.error = err
-                    if count <= fragment_retries:
+                    continue
-                        self.report_retry_fragment(err, frag_index, count, fragment_retries)
+            return False, None, None, None
-            if count > fragment_retries:
-                self.report_error('giving up after %s fragment retries' % fragment_retries)
-                return False, None, None, None
 
         self._prepare_and_start_frag_download(ctx, info_dict)
 

yt_dlp/extractor/_extractors.py

@@ -22,6 +22,7 @@ from .acast import (
     ACastIE,
     ACastChannelIE,
 )
+from .acfun import AcFunVideoIE, AcFunBangumiIE
 from .adn import ADNIE
 from .adobeconnect import AdobeConnectIE
 from .adobetv import (
@@ -59,6 +60,7 @@ from .americastestkitchen import (
     AmericasTestKitchenIE,
     AmericasTestKitchenSeasonIE,
 )
+from .angel import AngelIE
 from .animeondemand import AnimeOnDemandIE
 from .anvato import AnvatoIE
 from .aol import AolIE
@@ -104,6 +106,10 @@ from .atttechchannel import ATTTechChannelIE
 from .atvat import ATVAtIE
 from .audimedia import AudiMediaIE
 from .audioboom import AudioBoomIE
+from .audiodraft import (
+    AudiodraftCustomIE,
+    AudiodraftGenericIE,
+)
 from .audiomack import AudiomackIE, AudiomackAlbumIE
 from .audius import (
     AudiusIE,
@@ -213,6 +219,7 @@ from .camdemy import (
     CamdemyFolderIE
 )
 from .cammodels import CamModelsIE
+from .camtasia import CamtasiaEmbedIE
 from .camwithher import CamWithHerIE
 from .canalalpha import CanalAlphaIE
 from .canalplus import CanalplusIE
@@ -258,6 +265,7 @@ from .ccc import (
 from .ccma import CCMAIE
 from .cctv import CCTVIE
 from .cda import CDAIE
+from .cellebrite import CellebriteIE
 from .ceskatelevize import CeskaTelevizeIE
 from .cgtn import CGTNIE
 from .channel9 import Channel9IE
@@ -376,6 +384,7 @@ from .deezer import (
     DeezerAlbumIE,
 )
 from .democracynow import DemocracynowIE
+from .detik import Detik20IE
 from .dfb import DFBIE
 from .dhm import DHMIE
 from .digg import DiggIE
@@ -401,6 +410,7 @@ from .dplay import (
     DiscoveryLifeIE,
     AnimalPlanetIE,
     TLCIE,
+    MotorTrendIE,
     DiscoveryPlusIndiaIE,
     DiscoveryNetworksDeIE,
     DiscoveryPlusItalyIE,
@@ -436,7 +446,7 @@ from .dw import (
     DWIE,
     DWArticleIE,
 )
-from .eagleplatform import EaglePlatformIE
+from .eagleplatform import EaglePlatformIE, ClipYouEmbedIE
 from .ebaumsworld import EbaumsWorldIE
 from .echomsk import EchoMskIE
 from .egghead import (
@@ -490,6 +500,7 @@ from .facebook import (
     FacebookIE,
     FacebookPluginsVideoIE,
     FacebookRedirectURLIE,
+    FacebookReelIE,
 )
 from .fancode import (
     FancodeVodIE,
@@ -621,6 +632,7 @@ from .gronkh import (
     GronkhVodsIE
 )
 from .groupon import GrouponIE
+from .harpodeon import HarpodeonIE
 from .hbo import HBOIE
 from .hearthisat import HearThisAtIE
 from .heise import HeiseIE
@@ -633,6 +645,7 @@ from .hidive import HiDiveIE
 from .historicfilms import HistoricFilmsIE
 from .hitbox import HitboxIE, HitboxLiveIE
 from .hitrecord import HitRecordIE
+from .holodex import HolodexIE
 from .hotnewhiphop import HotNewHipHopIE
 from .hotstar import (
     HotStarIE,
@@ -651,6 +664,7 @@ from .hse import (
     HSEShowIE,
     HSEProductIE,
 )
+from .genericembeds import HTML5MediaEmbedIE
 from .huajiao import HuajiaoIE
 from .huya import HuyaLiveIE
 from .huffpost import HuffPostIE
@@ -660,6 +674,7 @@ from .hungama import (
     HungamaAlbumPlaylistIE,
 )
 from .hypem import HypemIE
+from .hytale import HytaleIE
 from .icareus import IcareusIE
 from .ichinanalive import (
     IchinanaLiveIE,
@@ -752,6 +767,7 @@ from .kicker import KickerIE
 from .kickstarter import KickStarterIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
+from .kompas import KompasVideoIE
 from .konserthusetplay import KonserthusetPlayIE
 from .koo import KooIE
 from .kth import KTHIE
@@ -830,6 +846,7 @@ from .linkedin import (
     LinkedInLearningCourseIE,
 )
 from .linuxacademy import LinuxAcademyIE
+from .liputan6 import Liputan6IE
 from .litv import LiTVIE
 from .livejournal import LiveJournalIE
 from .livestream import (
@@ -940,9 +957,11 @@ from .mixcloud import (
 from .mlb import (
     MLBIE,
     MLBVideoIE,
+    MLBTVIE,
 )
 from .mlssoccer import MLSSoccerIE
 from .mnet import MnetIE
+from .mocha import MochaVideoIE
 from .moevideo import MoeVideoIE
 from .mofosex import (
     MofosexIE,
@@ -957,6 +976,7 @@ from .motherless import (
 from .motorsport import MotorsportIE
 from .movieclips import MovieClipsIE
 from .moviepilot import MoviepilotIE
+from .moview import MoviewPlayIE
 from .moviezine import MoviezineIE
 from .movingimage import MovingImageIE
 from .msn import MSNIE
@@ -1195,19 +1215,8 @@ from .openrec import (
 from .ora import OraTVIE
 from .orf import (
     ORFTVthekIE,
-    ORFFM4IE,
     ORFFM4StoryIE,
-    ORFOE1IE,
+    ORFRadioIE,
-    ORFOE3IE,
-    ORFNOEIE,
-    ORFWIEIE,
-    ORFBGLIE,
-    ORFOOEIE,
-    ORFSTMIE,
-    ORFKTNIE,
-    ORFSBGIE,
-    ORFTIRIE,
-    ORFVBGIE,
     ORFIPTVIE,
 )
 from .outsidetv import OutsideTVIE
@@ -1230,11 +1239,11 @@ from .paramountplus import (
     ParamountPlusIE,
     ParamountPlusSeriesIE,
 )
-from .parliamentliveuk import ParliamentLiveUKIE
+from .parler import ParlerIE
 from .parlview import ParlviewIE
 from .patreon import (
     PatreonIE,
-    PatreonUserIE
+    PatreonCampaignIE
 )
 from .pbs import PBSIE
 from .pearvideo import PearVideoIE
@@ -1381,6 +1390,8 @@ from .rai import (
     RaiPlaySoundIE,
     RaiPlaySoundLiveIE,
     RaiPlaySoundPlaylistIE,
+    RaiNewsIE,
+    RaiSudtirolIE,
     RaiIE,
 )
 from .raywenderlich import (
@@ -1399,6 +1410,7 @@ from .rcti import (
     RCTIPlusTVIE,
 )
 from .rds import RDSIE
+from .redbee import ParliamentLiveUKIE, RTBFIE
 from .redbulltv import (
     RedBullTVIE,
     RedBullEmbedIE,
@@ -1432,9 +1444,14 @@ from .rokfin import (
 from .roosterteeth import RoosterTeethIE, RoosterTeethSeriesIE
 from .rottentomatoes import RottenTomatoesIE
 from .rozhlas import RozhlasIE
-from .rtbf import RTBFIE
 from .rte import RteIE, RteRadioIE
-from .rtlnl import RtlNlIE
+from .rtlnl import (
+    RtlNlIE,
+    RTLLuTeleVODIE,
+    RTLLuArticleIE,
+    RTLLuLiveIE,
+    RTLLuRadioIE,
+)
 from .rtl2 import (
     RTL2IE,
     RTL2YouIE,
@@ -1458,6 +1475,7 @@ from .rtve import (
 )
 from .rtvnh import RTVNHIE
 from .rtvs import RTVSIE
+from .rtvslo import RTVSLOIE
 from .ruhd import RUHDIE
 from .rule34video import Rule34VideoIE
 from .rumble import (
@@ -1531,6 +1549,7 @@ from .shared import (
     SharedIE,
     VivoIE,
 )
+from .sharevideos import ShareVideosEmbedIE
 from .shemaroome import ShemarooMeIE
 from .showroomlive import ShowRoomLiveIE
 from .simplecast import (
@@ -1608,6 +1627,7 @@ from .spike import (
     BellatorIE,
     ParamountNetworkIE,
 )
+from .startrek import StarTrekIE
 from .stitcher import (
     StitcherIE,
     StitcherShowIE,
@@ -1665,6 +1685,7 @@ from .svt import (
     SVTSeriesIE,
 )
 from .swrmediathek import SWRMediathekIE
+from .syvdk import SYVDKIE
 from .syfy import SyfyIE
 from .sztvhu import SztvHuIE
 from .tagesschau import TagesschauIE
@@ -1706,11 +1727,13 @@ from .telequebec import (
 )
 from .teletask import TeleTaskIE
 from .telewebion import TelewebionIE
+from .tempo import TempoIE
 from .tennistv import TennisTVIE
 from .tenplay import TenPlayIE
 from .testurl import TestURLIE
 from .tf1 import TF1IE
 from .tfo import TFOIE
+from .theholetv import TheHoleTvIE
 from .theintercept import TheInterceptIE
 from .theplatform import (
     ThePlatformIE,
@@ -1773,8 +1796,10 @@ from .trovo import (
 )
 from .trueid import TrueIDIE
 from .trunews import TruNewsIE
+from .truth import TruthIE
 from .trutv import TruTVIE
 from .tube8 import Tube8IE
+from .tubetugraz import TubeTuGrazIE, TubeTuGrazSeriesIE
 from .tubitv import (
     TubiTvIE,
     TubiTvShowIE,
@@ -1823,6 +1848,7 @@ from .tvc import (
 )
 from .tver import TVerIE
 from .tvigle import TvigleIE
+from .tviplayer import TVIPlayerIE
 from .tvland import TVLandIE
 from .tvn24 import TVN24IE
 from .tvnet import TVNetIE
@@ -2066,6 +2092,8 @@ from .weibo import (
     WeiboMobileIE
 )
 from .weiqitv import WeiqiTVIE
+from .wetv import WeTvEpisodeIE, WeTvSeriesIE
+from .wikimedia import WikimediaIE
 from .willow import WillowIE
 from .wimtv import WimTVIE
 from .whowatch import WhoWatchIE

yt_dlp/extractor/abematv.py

@@ -1,5 +1,6 @@
 import base64
 import binascii
+import functools
 import hashlib
 import hmac
 import io
@@ -20,11 +21,11 @@ from ..utils import (
     decode_base_n,
     int_or_none,
     intlist_to_bytes,
+    OnDemandPagedList,
     request_to_url,
     time_seconds,
     traverse_obj,
     update_url_query,
-    urljoin,
 )
 
 # NOTE: network handler related code is temporary thing until network stack overhaul PRs are merged (#2861/#2862)
@@ -145,17 +146,106 @@ class AbemaLicenseHandler(urllib.request.BaseHandler):
 
 
 class AbemaTVBaseIE(InfoExtractor):
+    _USERTOKEN = None
+    _DEVICE_ID = None
+    _MEDIATOKEN = None
+
+    _SECRETKEY = b'v+Gjs=25Aw5erR!J8ZuvRrCx*rGswhB&qdHd_SYerEWdU&a?3DzN9BRbp5KwY4hEmcj5#fykMjJ=AuWz5GSMY-d@H7DMEh3M@9n2G552Us$$k9cD=3TxwWe86!x#Zyhe'
+
+    @classmethod
+    def _generate_aks(cls, deviceid):
+        deviceid = deviceid.encode('utf-8')
+        # add 1 hour and then drop minute and secs
+        ts_1hour = int((time_seconds(hours=9) // 3600 + 1) * 3600)
+        time_struct = time.gmtime(ts_1hour)
+        ts_1hour_str = str(ts_1hour).encode('utf-8')
+
+        tmp = None
+
+        def mix_once(nonce):
+            nonlocal tmp
+            h = hmac.new(cls._SECRETKEY, digestmod=hashlib.sha256)
+            h.update(nonce)
+            tmp = h.digest()
+
+        def mix_tmp(count):
+            nonlocal tmp
+            for i in range(count):
+                mix_once(tmp)
+
+        def mix_twist(nonce):
+            nonlocal tmp
+            mix_once(base64.urlsafe_b64encode(tmp).rstrip(b'=') + nonce)
+
+        mix_once(cls._SECRETKEY)
+        mix_tmp(time_struct.tm_mon)
+        mix_twist(deviceid)
+        mix_tmp(time_struct.tm_mday % 5)
+        mix_twist(ts_1hour_str)
+        mix_tmp(time_struct.tm_hour % 5)
+
+        return base64.urlsafe_b64encode(tmp).rstrip(b'=').decode('utf-8')
+
+    def _get_device_token(self):
+        if self._USERTOKEN:
+            return self._USERTOKEN
+
+        AbemaTVBaseIE._DEVICE_ID = str(uuid.uuid4())
+        aks = self._generate_aks(self._DEVICE_ID)
+        user_data = self._download_json(
+            'https://api.abema.io/v1/users', None, note='Authorizing',
+            data=json.dumps({
+                'deviceId': self._DEVICE_ID,
+                'applicationKeySecret': aks,
+            }).encode('utf-8'),
+            headers={
+                'Content-Type': 'application/json',
+            })
+        AbemaTVBaseIE._USERTOKEN = user_data['token']
+
+        # don't allow adding it 2 times or more, though it's guarded
+        remove_opener(self._downloader, AbemaLicenseHandler)
+        add_opener(self._downloader, AbemaLicenseHandler(self))
+
+        return self._USERTOKEN
+
+    def _get_media_token(self, invalidate=False, to_show=True):
+        if not invalidate and self._MEDIATOKEN:
+            return self._MEDIATOKEN
+
+        AbemaTVBaseIE._MEDIATOKEN = self._download_json(
+            'https://api.abema.io/v1/media/token', None, note='Fetching media token' if to_show else False,
+            query={
+                'osName': 'android',
+                'osVersion': '6.0.1',
+                'osLang': 'ja_JP',
+                'osTimezone': 'Asia/Tokyo',
+                'appId': 'tv.abema',
+                'appVersion': '3.27.1'
+            }, headers={
+                'Authorization': f'bearer {self._get_device_token()}',
+            })['token']
+
+        return self._MEDIATOKEN
+
+    def _call_api(self, endpoint, video_id, query=None, note='Downloading JSON metadata'):
+        return self._download_json(
+            f'https://api.abema.io/{endpoint}', video_id, query=query or {},
+            note=note,
+            headers={
+                'Authorization': f'bearer {self._get_device_token()}',
+            })
+
     def _extract_breadcrumb_list(self, webpage, video_id):
         for jld in re.finditer(
                 r'(?is)</span></li></ul><script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>',
                 webpage):
             jsonld = self._parse_json(jld.group('json_ld'), video_id, fatal=False)
-            if jsonld:
+            if traverse_obj(jsonld, '@type') != 'BreadcrumbList':
-                if jsonld.get('@type') != 'BreadcrumbList':
+                continue
-                    continue
+            items = traverse_obj(jsonld, ('itemListElement', ..., 'name'))
-                trav = traverse_obj(jsonld, ('itemListElement', ..., 'name'))
+            if items:
-                if trav:
+                return items
-                    return trav
         return []
 
 
@@ -207,87 +297,7 @@ class AbemaTVIE(AbemaTVBaseIE):
         },
         'skip': 'Not supported until yt-dlp implements native live downloader OR AbemaTV can start a local HTTP server',
     }]
-    _USERTOKEN = None
-    _DEVICE_ID = None
     _TIMETABLE = None
-    _MEDIATOKEN = None
-
-    _SECRETKEY = b'v+Gjs=25Aw5erR!J8ZuvRrCx*rGswhB&qdHd_SYerEWdU&a?3DzN9BRbp5KwY4hEmcj5#fykMjJ=AuWz5GSMY-d@H7DMEh3M@9n2G552Us$$k9cD=3TxwWe86!x#Zyhe'
-
-    def _generate_aks(self, deviceid):
-        deviceid = deviceid.encode('utf-8')
-        # add 1 hour and then drop minute and secs
-        ts_1hour = int((time_seconds(hours=9) // 3600 + 1) * 3600)
-        time_struct = time.gmtime(ts_1hour)
-        ts_1hour_str = str(ts_1hour).encode('utf-8')
-
-        tmp = None
-
-        def mix_once(nonce):
-            nonlocal tmp
-            h = hmac.new(self._SECRETKEY, digestmod=hashlib.sha256)
-            h.update(nonce)
-            tmp = h.digest()
-
-        def mix_tmp(count):
-            nonlocal tmp
-            for i in range(count):
-                mix_once(tmp)
-
-        def mix_twist(nonce):
-            nonlocal tmp
-            mix_once(base64.urlsafe_b64encode(tmp).rstrip(b'=') + nonce)
-
-        mix_once(self._SECRETKEY)
-        mix_tmp(time_struct.tm_mon)
-        mix_twist(deviceid)
-        mix_tmp(time_struct.tm_mday % 5)
-        mix_twist(ts_1hour_str)
-        mix_tmp(time_struct.tm_hour % 5)
-
-        return base64.urlsafe_b64encode(tmp).rstrip(b'=').decode('utf-8')
-
-    def _get_device_token(self):
-        if self._USERTOKEN:
-            return self._USERTOKEN
-
-        self._DEVICE_ID = str(uuid.uuid4())
-        aks = self._generate_aks(self._DEVICE_ID)
-        user_data = self._download_json(
-            'https://api.abema.io/v1/users', None, note='Authorizing',
-            data=json.dumps({
-                'deviceId': self._DEVICE_ID,
-                'applicationKeySecret': aks,
-            }).encode('utf-8'),
-            headers={
-                'Content-Type': 'application/json',
-            })
-        self._USERTOKEN = user_data['token']
-
-        # don't allow adding it 2 times or more, though it's guarded
-        remove_opener(self._downloader, AbemaLicenseHandler)
-        add_opener(self._downloader, AbemaLicenseHandler(self))
-
-        return self._USERTOKEN
-
-    def _get_media_token(self, invalidate=False, to_show=True):
-        if not invalidate and self._MEDIATOKEN:
-            return self._MEDIATOKEN
-
-        self._MEDIATOKEN = self._download_json(
-            'https://api.abema.io/v1/media/token', None, note='Fetching media token' if to_show else False,
-            query={
-                'osName': 'android',
-                'osVersion': '6.0.1',
-                'osLang': 'ja_JP',
-                'osTimezone': 'Asia/Tokyo',
-                'appId': 'tv.abema',
-                'appVersion': '3.27.1'
-            }, headers={
-                'Authorization': 'bearer ' + self._get_device_token()
-            })['token']
-
-        return self._MEDIATOKEN
 
     def _perform_login(self, username, password):
         if '@' in username:  # don't strictly check if it's email address or not
@@ -301,13 +311,13 @@ class AbemaTVIE(AbemaTVBaseIE):
                 method: username,
                 'password': password
             }).encode('utf-8'), headers={
-                'Authorization': 'bearer ' + self._get_device_token(),
+                'Authorization': f'bearer {self._get_device_token()}',
                 'Origin': 'https://abema.tv',
                 'Referer': 'https://abema.tv/',
                 'Content-Type': 'application/json',
             })
 
-        self._USERTOKEN = login_response['token']
+        AbemaTVBaseIE._USERTOKEN = login_response['token']
         self._get_media_token(True)
 
     def _real_extract(self, url):
@@ -355,7 +365,7 @@ class AbemaTVIE(AbemaTVBaseIE):
         # read breadcrumb on top of page
         breadcrumb = self._extract_breadcrumb_list(webpage, video_id)
         if breadcrumb:
-            # breadcrumb list translates to: (example is 1st test for this IE)
+            # breadcrumb list translates to: (e.g. 1st test for this IE)
             # Home > Anime (genre) > Isekai Shokudo 2 (series name) > Episode 1 "Cheese cakes" "Morning again" (episode title)
             # hence this works
             info['series'] = breadcrumb[-2]
@@ -442,6 +452,7 @@ class AbemaTVIE(AbemaTVBaseIE):
 
 class AbemaTVTitleIE(AbemaTVBaseIE):
     _VALID_URL = r'https?://abema\.tv/video/title/(?P<id>[^?/]+)'
+    _PAGE_SIZE = 25
 
     _TESTS = [{
         'url': 'https://abema.tv/video/title/90-1597',
@@ -457,18 +468,39 @@ class AbemaTVTitleIE(AbemaTVBaseIE):
             'title': '真心が届く~僕とスターのオフィス・ラブ!?~',
         },
         'playlist_mincount': 16,
+    }, {
+        'url': 'https://abema.tv/video/title/25-102',
+        'info_dict': {
+            'id': '25-102',
+            'title': 'ソードアート・オンライン アリシゼーション',
+        },
+        'playlist_mincount': 24,
     }]
 
+    def _fetch_page(self, playlist_id, series_version, page):
+        programs = self._call_api(
+            f'v1/video/series/{playlist_id}/programs', playlist_id,
+            note=f'Downloading page {page + 1}',
+            query={
+                'seriesVersion': series_version,
+                'offset': str(page * self._PAGE_SIZE),
+                'order': 'seq',
+                'limit': str(self._PAGE_SIZE),
+            })
+        yield from (
+            self.url_result(f'https://abema.tv/video/episode/{x}')
+            for x in traverse_obj(programs, ('programs', ..., 'id'), default=[]))
+
+    def _entries(self, playlist_id, series_version):
+        return OnDemandPagedList(
+            functools.partial(self._fetch_page, playlist_id, series_version),
+            self._PAGE_SIZE)
+
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        playlist_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        series_info = self._call_api(f'v1/video/series/{playlist_id}', playlist_id)
 
-        playlist_title, breadcrumb = None, self._extract_breadcrumb_list(webpage, video_id)
+        return self.playlist_result(
-        if breadcrumb:
+            self._entries(playlist_id, series_info['version']), playlist_id=playlist_id,
-            playlist_title = breadcrumb[-1]
+            playlist_title=series_info.get('title'),
-
+            playlist_description=series_info.get('content'))
-        playlist = [
-            self.url_result(urljoin('https://abema.tv/', mobj.group(1)))
-            for mobj in re.finditer(r'<li\s*class=".+?EpisodeList.+?"><a\s*href="(/[^"]+?)"', webpage)]
-
-        return self.playlist_result(playlist, playlist_title=playlist_title, playlist_id=video_id)

yt_dlp/extractor/acfun.py

@@ -0,0 +1,200 @@
+from .common import InfoExtractor
+from ..utils import (
+    float_or_none,
+    format_field,
+    int_or_none,
+    traverse_obj,
+    parse_codecs,
+    parse_qs,
+)
+
+
+class AcFunVideoBaseIE(InfoExtractor):
+    def _extract_metadata(self, video_id, video_info):
+        playjson = self._parse_json(video_info['ksPlayJson'], video_id)
+
+        formats, subtitles = [], {}
+        for video in traverse_obj(playjson, ('adaptationSet', 0, 'representation')):
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(video['url'], video_id, 'mp4', fatal=False)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+            for f in fmts:
+                f.update({
+                    'fps': float_or_none(video.get('frameRate')),
+                    'width': int_or_none(video.get('width')),
+                    'height': int_or_none(video.get('height')),
+                    'tbr': float_or_none(video.get('avgBitrate')),
+                    **parse_codecs(video.get('codecs', ''))
+                })
+
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'formats': formats,
+            'subtitles': subtitles,
+            'duration': float_or_none(video_info.get('durationMillis'), 1000),
+            'timestamp': int_or_none(video_info.get('uploadTime'), 1000),
+            'http_headers': {'Referer': 'https://www.acfun.cn/'},
+        }
+
+
+class AcFunVideoIE(AcFunVideoBaseIE):
+    _VALID_URL = r'https?://www\.acfun\.cn/v/ac(?P<id>[_\d]+)'
+
+    _TESTS = [{
+        'url': 'https://www.acfun.cn/v/ac35457073',
+        'info_dict': {
+            'id': '35457073',
+            'ext': 'mp4',
+            'duration': 174.208,
+            'timestamp': 1656403967,
+            'title': '1 8 岁 现 状',
+            'description': '“赶紧回去！班主任查班了！”',
+            'uploader': '锤子game',
+            'uploader_id': '51246077',
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
+            'upload_date': '20220628',
+            'like_count': int,
+            'view_count': int,
+            'comment_count': int,
+            'tags': list,
+        },
+    }, {
+        # example for len(video_list) > 1
+        'url': 'https://www.acfun.cn/v/ac35468952_2',
+        'info_dict': {
+            'id': '35468952_2',
+            'ext': 'mp4',
+            'title': '【动画剧集】Rocket & Groot Season 1（2022）/火箭浣熊与格鲁特第1季 P02 S01E02 十拿九穩',
+            'duration': 90.459,
+            'uploader': '比令',
+            'uploader_id': '37259967',
+            'upload_date': '20220629',
+            'timestamp': 1656479962,
+            'tags': list,
+            'like_count': int,
+            'view_count': int,
+            'comment_count': int,
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
+            'description': 'md5:67583aaf3a0f933bd606bc8a2d3ebb17',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+        json_all = self._search_json(r'window.videoInfo\s*=\s*', webpage, 'videoInfo', video_id)
+
+        title = json_all.get('title')
+        video_list = json_all.get('videoList') or []
+        video_internal_id = traverse_obj(json_all, ('currentVideoInfo', 'id'))
+        if video_internal_id and len(video_list) > 1:
+            part_idx, part_video_info = next(
+                (idx + 1, v) for (idx, v) in enumerate(video_list)
+                if v['id'] == video_internal_id)
+            title = f'{title} P{part_idx:02d} {part_video_info["title"]}'
+
+        return {
+            **self._extract_metadata(video_id, json_all['currentVideoInfo']),
+            'title': title,
+            'thumbnail': json_all.get('coverUrl'),
+            'description': json_all.get('description'),
+            'uploader': traverse_obj(json_all, ('user', 'name')),
+            'uploader_id': traverse_obj(json_all, ('user', 'href')),
+            'tags': traverse_obj(json_all, ('tagList', ..., 'name')),
+            'view_count': int_or_none(json_all.get('viewCount')),
+            'like_count': int_or_none(json_all.get('likeCountShow')),
+            'comment_count': int_or_none(json_all.get('commentCountShow')),
+        }
+
+
+class AcFunBangumiIE(AcFunVideoBaseIE):
+    _VALID_URL = r'https?://www\.acfun\.cn/bangumi/(?P<id>aa[_\d]+)'
+
+    _TESTS = [{
+        'url': 'https://www.acfun.cn/bangumi/aa6002917_36188_1745457?ac=2',
+        'info_dict': {
+            'id': 'aa6002917_36188_1745457__2',
+            'ext': 'mp4',
+            'title': '【7月】租借女友 水原千鹤角色曲『DATE』特别PV',
+            'upload_date': '20200916',
+            'timestamp': 1600243813,
+            'duration': 92.091,
+        },
+    }, {
+        'url': 'https://www.acfun.cn/bangumi/aa5023171_36188_1750645',
+        'info_dict': {
+            'id': 'aa5023171_36188_1750645',
+            'ext': 'mp4',
+            'title': '红孩儿之趴趴蛙寻石记 第5话 ',
+            'duration': 760.0,
+            'season': '红孩儿之趴趴蛙寻石记',
+            'season_id': 5023171,
+            'season_number': 1,  # series has only 1 season
+            'episode': 'Episode 5',
+            'episode_number': 5,
+            'upload_date': '20181223',
+            'timestamp': 1545552185,
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
+            'comment_count': int,
+        },
+    }, {
+        'url': 'https://www.acfun.cn/bangumi/aa6065485_36188_1885061',
+        'info_dict': {
+            'id': 'aa6065485_36188_1885061',
+            'ext': 'mp4',
+            'title': '叽歪老表（第二季） 第5话 坚不可摧',
+            'season': '叽歪老表（第二季）',
+            'season_number': 2,
+            'season_id': 6065485,
+            'episode': '坚不可摧',
+            'episode_number': 5,
+            'upload_date': '20220324',
+            'timestamp': 1648082786,
+            'duration': 105.002,
+            'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)',
+            'comment_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        ac_idx = parse_qs(url).get('ac', [None])[-1]
+        video_id = f'{video_id}{format_field(ac_idx, template="__%s")}'
+
+        webpage = self._download_webpage(url, video_id)
+        json_bangumi_data = self._search_json(r'window.bangumiData\s*=\s*', webpage, 'bangumiData', video_id)
+
+        if ac_idx:
+            video_info = json_bangumi_data['hlVideoInfo']
+            return {
+                **self._extract_metadata(video_id, video_info),
+                'title': video_info.get('title'),
+            }
+
+        video_info = json_bangumi_data['currentVideoInfo']
+
+        season_id = json_bangumi_data.get('bangumiId')
+        season_number = season_id and next((
+            idx for idx, v in enumerate(json_bangumi_data.get('relatedBangumis') or [], 1)
+            if v.get('id') == season_id), 1)
+
+        json_bangumi_list = self._search_json(
+            r'window\.bangumiList\s*=\s*', webpage, 'bangumiList', video_id, fatal=False)
+        video_internal_id = int_or_none(traverse_obj(json_bangumi_data, ('currentVideoInfo', 'id')))
+        episode_number = video_internal_id and next((
+            idx for idx, v in enumerate(json_bangumi_list.get('items') or [], 1)
+            if v.get('videoId') == video_internal_id), None)
+
+        return {
+            **self._extract_metadata(video_id, video_info),
+            'title': json_bangumi_data.get('showTitle'),
+            'thumbnail': json_bangumi_data.get('image'),
+            'season': json_bangumi_data.get('bangumiTitle'),
+            'season_id': season_id,
+            'season_number': season_number,
+            'episode': json_bangumi_data.get('title'),
+            'episode_number': episode_number,
+            'comment_count': int_or_none(json_bangumi_data.get('commentCount')),
+        }

yt_dlp/extractor/adobetv.py

@@ -232,6 +232,7 @@ class AdobeTVChannelIE(AdobeTVPlaylistBaseIE):
 class AdobeTVVideoIE(AdobeTVBaseIE):
     IE_NAME = 'adobetv:video'
     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=[\'"](?P<url>(?:https?:)?//video\.tv\.adobe\.com/v/\d+[^"]+)[\'"]']
 
     _TEST = {
         # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners

yt_dlp/extractor/aenetworks.py

@@ -28,14 +28,17 @@ class AENetworksBaseIE(ThePlatformIE):
     }
 
     def _extract_aen_smil(self, smil_url, video_id, auth=None):
-        query = {'mbr': 'true'}
+        query = {
+            'mbr': 'true',
+            'formats': 'M3U+none,MPEG-DASH+none,MPEG4,MP3',
+        }
         if auth:
             query['auth'] = auth
         TP_SMIL_QUERY = [{
             'assetTypes': 'high_video_ak',
-            'switch': 'hls_high_ak'
+            'switch': 'hls_high_ak',
         }, {
-            'assetTypes': 'high_video_s3'
+            'assetTypes': 'high_video_s3',
         }, {
             'assetTypes': 'high_video_s3',
             'switch': 'hls_high_fastly',

yt_dlp/extractor/angel.py

@@ -0,0 +1,56 @@
+import re
+
+from .common import InfoExtractor
+from ..utils import url_or_none, merge_dicts
+
+
+class AngelIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?angel\.com/watch/(?P<series>[^/?#]+)/episode/(?P<id>[\w-]+)/season-(?P<season_number>\d+)/episode-(?P<episode_number>\d+)/(?P<title>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.angel.com/watch/tuttle-twins/episode/2f3d0382-ea82-4cdc-958e-84fbadadc710/season-1/episode-1/when-laws-give-you-lemons',
+        'md5': '4734e5cfdd64a568e837246aa3eaa524',
+        'info_dict': {
+            'id': '2f3d0382-ea82-4cdc-958e-84fbadadc710',
+            'ext': 'mp4',
+            'title': 'Tuttle Twins Season 1, Episode 1: When Laws Give You Lemons',
+            'description': 'md5:73b704897c20ab59c433a9c0a8202d5e',
+            'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
+            'duration': 1359.0
+        }
+    }, {
+        'url': 'https://www.angel.com/watch/the-chosen/episode/8dfb714d-bca5-4812-8125-24fb9514cd10/season-1/episode-1/i-have-called-you-by-name',
+        'md5': 'e4774bad0a5f0ad2e90d175cafdb797d',
+        'info_dict': {
+            'id': '8dfb714d-bca5-4812-8125-24fb9514cd10',
+            'ext': 'mp4',
+            'title': 'The Chosen Season 1, Episode 1: I Have Called You By Name',
+            'description': 'md5:aadfb4827a94415de5ff6426e6dee3be',
+            'thumbnail': r're:^https?://images.angelstudios.com/image/upload/angel-app/.*$',
+            'duration': 3276.0
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+
+        json_ld = self._search_json_ld(webpage, video_id)
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(
+            json_ld.pop('url'), video_id, note='Downloading HD m3u8 information')
+
+        info_dict = {
+            'id': video_id,
+            'title': self._og_search_title(webpage),
+            'description': self._og_search_description(webpage),
+            'formats': formats,
+            'subtitles': subtitles
+        }
+
+        # Angel uses cloudinary in the background and supports image transformations.
+        # We remove these transformations and return the source file
+        base_thumbnail_url = url_or_none(self._og_search_thumbnail(webpage)) or json_ld.pop('thumbnails')
+        if base_thumbnail_url:
+            info_dict['thumbnail'] = re.sub(r'(/upload)/.+(/angel-app/.+)$', r'\1\2', base_thumbnail_url)
+
+        return merge_dicts(info_dict, json_ld)

yt_dlp/extractor/ant1newsgr.py

@@ -1,4 +1,3 @@
-import re
 import urllib.parse
 
 from .common import InfoExtractor
@@ -7,7 +6,6 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     scale_thumbnails_to_max_format_width,
-    unescapeHTML,
 )
 
 
@@ -91,7 +89,7 @@ class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
         info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle')
-        embed_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage))
+        embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage))
         if not embed_urls:
             raise ExtractorError('no videos found for %s' % video_id, expected=True)
         return self.playlist_from_matches(
@@ -104,6 +102,7 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
     IE_DESC = 'ant1news.gr embedded videos'
     _BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player'
     _VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)'
+    _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
     _API_PATH = '/news/templates/data/jsonPlayer'
 
     _TESTS = [{
@@ -117,16 +116,6 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE):
         },
     }]
 
-    @classmethod
-    def _extract_urls(cls, webpage):
-        _EMBED_URL_RE = rf'{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+'
-        _EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_EMBED_URL_RE})(?P=_q1)'
-        for mobj in re.finditer(_EMBED_RE, webpage):
-            url = unescapeHTML(mobj.group('url'))
-            if not cls.suitable(url):
-                continue
-            yield url
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/anvato.py

@@ -340,30 +340,16 @@ class AnvatoIE(InfoExtractor):
             'subtitles': subtitles,
         }
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(ie, webpage, video_id):
+    def _extract_from_webpage(cls, url, webpage):
-        entries = []
+        for mobj in re.finditer(cls._ANVP_RE, webpage):
-        for mobj in re.finditer(AnvatoIE._ANVP_RE, webpage):
+            anvplayer_data = unescapeHTML(json.loads(mobj.group('anvp'))) or {}
-            anvplayer_data = ie._parse_json(
+            video_id, access_key = anvplayer_data.get('video'), anvplayer_data.get('accessKey')
-                mobj.group('anvp'), video_id, transform_source=unescapeHTML,
-                fatal=False)
-            if not anvplayer_data:
-                continue
-            video = anvplayer_data.get('video')
-            if not isinstance(video, compat_str) or not video.isdigit():
-                continue
-            access_key = anvplayer_data.get('accessKey')
-            if not access_key:
-                mcp = anvplayer_data.get('mcp')
-                if mcp:
-                    access_key = AnvatoIE._MCP_TO_ACCESS_KEY_TABLE.get(
-                        mcp.lower())
             if not access_key:
+                access_key = cls._MCP_TO_ACCESS_KEY_TABLE.get((anvplayer_data.get('mcp') or '').lower())
+            if not (video_id or '').isdigit() or not access_key:
                 continue
-            entries.append(ie.url_result(
+            yield cls.url_result(f'anvato:{access_key}:{video_id}', AnvatoIE, video_id)
-                'anvato:%s:%s' % (access_key, video), ie=AnvatoIE.ie_key(),
-                video_id=video))
-        return entries
 
     def _extract_anvato_videos(self, webpage, video_id):
         anvplayer_data = self._parse_json(

yt_dlp/extractor/apa.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -10,6 +8,7 @@ from ..utils import (
 
 class APAIE(InfoExtractor):
     _VALID_URL = r'(?P<base_url>https?://[^/]+\.apa\.at)/embed/(?P<id>[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12})'
+    _EMBED_REGEX = [r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1']
     _TESTS = [{
         'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
         'md5': '2b12292faeb0a7d930c778c7a5b4759b',
@@ -30,14 +29,6 @@ class APAIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<iframe[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//[^/]+\.apa\.at/embed/[\da-f]{8}-[\da-f]{4}-[\da-f]{4}-[\da-f]{4}-[\da-f]{12}.*?)\1',
-                webpage)]
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id, base_url = mobj.group('id', 'base_url')

yt_dlp/extractor/aparat.py

@@ -10,6 +10,7 @@ from ..utils import (
 
 class AparatIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?aparat\.com/(?:v/|video/video/embed/videohash/)(?P<id>[a-zA-Z0-9]+)'
+    _EMBED_REGEX = [r'<iframe .*?src="(?P<url>http://www\.aparat\.com/video/[^"]+)"']
 
     _TESTS = [{
         'url': 'http://www.aparat.com/v/wP8On',

yt_dlp/extractor/archiveorg.py

@@ -49,6 +49,11 @@ class ArchiveOrgIE(InfoExtractor):
             'upload_date': '20100315',
             'creator': 'SRI International',
             'uploader': 'laura@archive.org',
+            'thumbnail': r're:https://archive\.org/download/.*\.jpg',
+            'release_year': 1968,
+            'display_id': 'XD300-23_68HighlightsAResearchCntAugHumanIntellect.cdr',
+            'track': 'XD300-23 68HighlightsAResearchCntAugHumanIntellect',
+
         },
     }, {
         'url': 'https://archive.org/details/Cops1922',
@@ -57,33 +62,43 @@ class ArchiveOrgIE(InfoExtractor):
             'id': 'Cops1922',
             'ext': 'mp4',
             'title': 'Buster Keaton\'s "Cops" (1922)',
-            'description': 'md5:43a603fd6c5b4b90d12a96b921212b9c',
+            'description': 'md5:cd6f9910c35aedd5fc237dbc3957e2ca',
             'uploader': 'yorkmba99@hotmail.com',
             'timestamp': 1387699629,
             'upload_date': '20131222',
+            'display_id': 'Cops-v2.mp4',
+            'thumbnail': r're:https://archive\.org/download/.*\.jpg',
+            'duration': 1091.96,
         },
     }, {
         'url': 'http://archive.org/embed/XD300-23_68HighlightsAResearchCntAugHumanIntellect',
         'only_matching': True,
     }, {
         'url': 'https://archive.org/details/Election_Ads',
-        'md5': '284180e857160cf866358700bab668a3',
+        'md5': 'eec5cddebd4793c6a653b69c3b11f2e6',
         'info_dict': {
             'id': 'Election_Ads/Commercial-JFK1960ElectionAdCampaignJingle.mpg',
             'title': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
-            'ext': 'mp4',
+            'ext': 'mpg',
+            'thumbnail': r're:https://archive\.org/download/.*\.jpg',
+            'duration': 59.77,
+            'display_id': 'Commercial-JFK1960ElectionAdCampaignJingle.mpg',
         },
     }, {
         'url': 'https://archive.org/details/Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
-        'md5': '7915213ef02559b5501fe630e1a53f59',
+        'md5': 'ea1eed8234e7d4165f38c8c769edef38',
         'info_dict': {
             'id': 'Election_Ads/Commercial-Nixon1960ElectionAdToughonDefense.mpg',
             'title': 'Commercial-Nixon1960ElectionAdToughonDefense.mpg',
-            'ext': 'mp4',
+            'ext': 'mpg',
             'timestamp': 1205588045,
             'uploader': 'mikedavisstripmaster@yahoo.com',
             'description': '1960 Presidential Campaign Election Commercials John F Kennedy, Richard M Nixon',
             'upload_date': '20080315',
+            'display_id': 'Commercial-Nixon1960ElectionAdToughonDefense.mpg',
+            'duration': 59.51,
+            'license': 'http://creativecommons.org/licenses/publicdomain/',
+            'thumbnail': r're:https://archive\.org/download/.*\.jpg',
         },
     }, {
         'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16',
@@ -92,6 +107,12 @@ class ArchiveOrgIE(InfoExtractor):
             'id': 'gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t01.flac',
             'title': 'Turning',
             'ext': 'flac',
+            'track': 'Turning',
+            'creator': 'Grateful Dead',
+            'display_id': 'gd1977-05-08d01t01.flac',
+            'track_number': 1,
+            'album': '1977-05-08 - Barton Hall - Cornell University',
+            'duration': 39.8,
         },
     }, {
         'url': 'https://archive.org/details/gd1977-05-08.shure57.stevenson.29303.flac16/gd1977-05-08d01t07.flac',
@@ -102,11 +123,20 @@ class ArchiveOrgIE(InfoExtractor):
             'ext': 'flac',
             'timestamp': 1205895624,
             'uploader': 'mvernon54@yahoo.com',
-            'description': 'md5:6a31f1996db0aa0fc9da6d6e708a1bb0',
+            'description': 'md5:6c921464414814720c6593810a5c7e3d',
             'upload_date': '20080319',
             'location': 'Barton Hall - Cornell University',
+            'duration': 438.68,
+            'track': 'Deal',
+            'creator': 'Grateful Dead',
+            'album': '1977-05-08 - Barton Hall - Cornell University',
+            'release_date': '19770508',
+            'display_id': 'gd1977-05-08d01t07.flac',
+            'release_year': 1977,
+            'track_number': 7,
         },
     }, {
+        # FIXME: give a better error message than just IndexError when all available formats are restricted
         'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik',
         'md5': '7cb019baa9b332e82ea7c10403acd180',
         'info_dict': {
@@ -114,6 +144,7 @@ class ArchiveOrgIE(InfoExtractor):
             'title': 'Bells Of Rostov',
             'ext': 'mp3',
         },
+        'skip': 'restricted'
     }, {
         'url': 'https://archive.org/details/lp_the-music-of-russia_various-artists-a-askaryan-alexander-melik/disc1/02.02.+Song+And+Chorus+In+The+Polovetsian+Camp+From+%22Prince+Igor%22+(Act+2%2C+Scene+1).mp3',
         'md5': '1d0aabe03edca83ca58d9ed3b493a3c3',
@@ -126,6 +157,52 @@ class ArchiveOrgIE(InfoExtractor):
             'description': 'md5:012b2d668ae753be36896f343d12a236',
             'upload_date': '20190928',
         },
+        'skip': 'restricted'
+    }, {
+        # Original formats are private
+        'url': 'https://archive.org/details/irelandthemakingofarepublic',
+        'info_dict': {
+            'id': 'irelandthemakingofarepublic',
+            'title': 'Ireland: The Making of a Republic',
+            'upload_date': '20160610',
+            'description': 'md5:f70956a156645a658a0dc9513d9e78b7',
+            'uploader': 'dimitrios@archive.org',
+            'creator': ['British Broadcasting Corporation', 'Time-Life Films'],
+            'timestamp': 1465594947,
+        },
+        'playlist': [
+            {
+                'md5': '0b211261b26590d49df968f71b90690d',
+                'info_dict': {
+                    'id': 'irelandthemakingofarepublic/irelandthemakingofarepublicreel1_01.mov',
+                    'ext': 'mp4',
+                    'title': 'irelandthemakingofarepublicreel1_01.mov',
+                    'duration': 130.46,
+                    'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_01_000117.jpg',
+                    'display_id': 'irelandthemakingofarepublicreel1_01.mov',
+                },
+            }, {
+                'md5': '67335ee3b23a0da930841981c1e79b02',
+                'info_dict': {
+                    'id': 'irelandthemakingofarepublic/irelandthemakingofarepublicreel1_02.mov',
+                    'ext': 'mp4',
+                    'duration': 1395.13,
+                    'title': 'irelandthemakingofarepublicreel1_02.mov',
+                    'display_id': 'irelandthemakingofarepublicreel1_02.mov',
+                    'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel1_02_001374.jpg',
+                },
+            }, {
+                'md5': 'e470e86787893603f4a341a16c281eb5',
+                'info_dict': {
+                    'id': 'irelandthemakingofarepublic/irelandthemakingofarepublicreel2.mov',
+                    'ext': 'mp4',
+                    'duration': 1602.67,
+                    'title': 'irelandthemakingofarepublicreel2.mov',
+                    'thumbnail': 'https://archive.org/download/irelandthemakingofarepublic/irelandthemakingofarepublic.thumbs/irelandthemakingofarepublicreel2_001554.jpg',
+                    'display_id': 'irelandthemakingofarepublicreel2.mov',
+                },
+            }
+        ]
     }]
 
     @staticmethod
@@ -216,17 +293,25 @@ class ArchiveOrgIE(InfoExtractor):
                     'filesize': int_or_none(f.get('size'))})
 
             extension = (f['name'].rsplit('.', 1) + [None])[1]
-            if extension in KNOWN_EXTENSIONS:
+
+            # We don't want to skip private formats if the user has access to them,
+            # however without access to an account with such privileges we can't implement/test this.
+            # For now to be safe, we will only skip them if there is no user logged in.
+            is_logged_in = bool(self._get_cookies('https://archive.org').get('logged-in-sig'))
+            if extension in KNOWN_EXTENSIONS and (not f.get('private') or is_logged_in):
                 entry['formats'].append({
                     'url': 'https://archive.org/download/' + identifier + '/' + f['name'],
                     'format': f.get('format'),
                     'width': int_or_none(f.get('width')),
                     'height': int_or_none(f.get('height')),
                     'filesize': int_or_none(f.get('size')),
-                    'protocol': 'https'})
+                    'protocol': 'https',
+                    'source_preference': 0 if f.get('source') == 'original' else -1,
+                    'format_note': f.get('source')
+                })
 
         for entry in entries.values():
-            self._sort_formats(entry['formats'])
+            self._sort_formats(entry['formats'], ('source', ))
 
         if len(entries) == 1:
             # If there's only one item, use it as the main info dict

yt_dlp/extractor/arcpublishing.py

@@ -70,8 +70,8 @@ class ArcPublishingIE(InfoExtractor):
         ], 'video-api-cdn.%s.arcpublishing.com/api'),
     ]
 
-    @staticmethod
+    @classmethod
-    def _extract_urls(webpage):
+    def _extract_embed_urls(cls, url, webpage):
         entries = []
         # https://arcpublishing.atlassian.net/wiki/spaces/POWA/overview
         for powa_el in re.findall(r'(<div[^>]+class="[^"]*\bpowa\b[^"]*"[^>]+data-uuid="%s"[^>]*>)' % ArcPublishingIE._UUID_REGEX, webpage):

yt_dlp/extractor/arkena.py

@@ -1,5 +1,3 @@
-import re
-
 from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
@@ -19,6 +17,8 @@ class ArkenaIE(InfoExtractor):
                                 play\.arkena\.com/(?:config|embed)/avp/v\d/player/media/(?P<id>[^/]+)/[^/]+/(?P<account_id>\d+)
                             )
                         '''
+    # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
+    _EMBED_REGEX = [r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1']
     _TESTS = [{
         'url': 'https://video.qbrick.com/play2/embed/player?accountId=1034090&mediaId=d8ab4607-00090107-aab86310',
         'md5': '97f117754e5f3c020f5f26da4a44ebaf',
@@ -50,15 +50,6 @@ class ArkenaIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_url(webpage):
-        # See https://support.arkena.com/display/PLAY/Ways+to+embed+your+video
-        mobj = re.search(
-            r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//play\.arkena\.com/embed/avp/.+?)\1',
-            webpage)
-        if mobj:
-            return mobj.group('url')
-
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')

yt_dlp/extractor/arte.py

@@ -1,190 +1,210 @@
 import re
 
 from .common import InfoExtractor
-from ..compat import (
-    compat_str,
-)
 from ..utils import (
     ExtractorError,
+    GeoRestrictedError,
     int_or_none,
+    parse_iso8601,
     parse_qs,
-    qualities,
     strip_or_none,
-    try_get,
+    traverse_obj,
-    unified_strdate,
     url_or_none,
 )
 
 
 class ArteTVBaseIE(InfoExtractor):
     _ARTE_LANGUAGES = 'fr|de|en|es|it|pl'
-    _API_BASE = 'https://api.arte.tv/api/player/v1'
+    _API_BASE = 'https://api.arte.tv/api/player/v2'
 
 
 class ArteTVIE(ArteTVBaseIE):
     _VALID_URL = r'''(?x)
-                    https?://
+                    (?:https?://
                         (?:
                             (?:www\.)?arte\.tv/(?P<lang>%(langs)s)/videos|
                             api\.arte\.tv/api/player/v\d+/config/(?P<lang_2>%(langs)s)
                         )
-                        /(?P<id>\d{6}-\d{3}-[AF])
+                    |arte://program)
+                        /(?P<id>\d{6}-\d{3}-[AF]|LIVE)
                     ''' % {'langs': ArteTVBaseIE._ARTE_LANGUAGES}
     _TESTS = [{
         'url': 'https://www.arte.tv/en/videos/088501-000-A/mexico-stealing-petrol-to-survive/',
-        'info_dict': {
+        'only_matching': True,
-            'id': '088501-000-A',
-            'ext': 'mp4',
-            'title': 'Mexico: Stealing Petrol to Survive',
-            'upload_date': '20190628',
-        },
     }, {
         'url': 'https://www.arte.tv/pl/videos/100103-000-A/usa-dyskryminacja-na-porodowce/',
-        'only_matching': True,
+        'info_dict': {
+            'id': '100103-000-A',
+            'title': 'USA: Dyskryminacja na porodówce',
+            'description': 'md5:242017b7cce59ffae340a54baefcafb1',
+            'alt_title': 'ARTE Reportage',
+            'upload_date': '20201103',
+            'duration': 554,
+            'thumbnail': r're:https://api-cdn\.arte\.tv/.+940x530',
+            'timestamp': 1604417980,
+            'ext': 'mp4',
+        },
+        'params': {'skip_download': 'm3u8'}
+    }, {
+        'note': 'No alt_title',
+        'url': 'https://www.arte.tv/fr/videos/110371-000-A/la-chaleur-supplice-des-arbres-de-rue/',
+        'info_dict': {
+            'id': '110371-000-A',
+            'ext': 'mp4',
+            'upload_date': '20220718',
+            'duration': 154,
+            'timestamp': 1658162460,
+            'description': 'md5:5890f36fe7dccfadb8b7c0891de54786',
+            'title': 'La chaleur, supplice des arbres de rue',
+            'thumbnail': 'https://api-cdn.arte.tv/img/v2/image/CPE2sQDtD8GLQgt8DuYHLf/940x530',
+        },
+        'params': {'skip_download': 'm3u8'}
     }, {
         'url': 'https://api.arte.tv/api/player/v2/config/de/100605-013-A',
         'only_matching': True,
+    }, {
+        'url': 'https://api.arte.tv/api/player/v2/config/de/LIVE',
+        'only_matching': True,
     }]
 
+    _GEO_BYPASS = True
+
+    _LANG_MAP = {  # ISO639 -> French abbreviations
+        'fr': 'F',
+        'de': 'A',
+        'en': 'E[ANG]',
+        'es': 'E[ESP]',
+        'it': 'E[ITA]',
+        'pl': 'E[POL]',
+        # XXX: probably means mixed; <https://www.arte.tv/en/videos/107710-029-A/dispatches-from-ukraine-local-journalists-report/>
+        # uses this code for audio that happens to be in Ukrainian, but the manifest uses the ISO code 'mul' (mixed)
+        'mul': 'EU',
+    }
+
+    _VERSION_CODE_RE = re.compile(r'''(?x)
+        V
+        (?P<original_voice>O?)
+        (?P<vlang>[FA]|E\[[A-Z]+\]|EU)?
+        (?P<audio_desc>AUD|)
+        (?:
+            (?P<has_sub>-ST)
+            (?P<sdh_sub>M?)
+            (?P<sub_lang>[FA]|E\[[A-Z]+\]|EU)
+        )?
+    ''')
+
+    # all obtained by exhaustive testing
+    _COUNTRIES_MAP = {
+        'DE_FR': {
+            'BL', 'DE', 'FR', 'GF', 'GP', 'MF', 'MQ', 'NC',
+            'PF', 'PM', 'RE', 'WF', 'YT',
+        },
+        # with both of the below 'BE' sometimes works, sometimes doesn't
+        'EUR_DE_FR': {
+            'AT', 'BL', 'CH', 'DE', 'FR', 'GF', 'GP', 'LI',
+            'MC', 'MF', 'MQ', 'NC', 'PF', 'PM', 'RE', 'WF',
+            'YT',
+        },
+        'SAT': {
+            'AD', 'AT', 'AX', 'BG', 'BL', 'CH', 'CY', 'CZ',
+            'DE', 'DK', 'EE', 'ES', 'FI', 'FR', 'GB', 'GF',
+            'GR', 'HR', 'HU', 'IE', 'IS', 'IT', 'KN', 'LI',
+            'LT', 'LU', 'LV', 'MC', 'MF', 'MQ', 'MT', 'NC',
+            'NL', 'NO', 'PF', 'PL', 'PM', 'PT', 'RE', 'RO',
+            'SE', 'SI', 'SK', 'SM', 'VA', 'WF', 'YT',
+        },
+    }
+
     def _real_extract(self, url):
         mobj = self._match_valid_url(url)
         video_id = mobj.group('id')
         lang = mobj.group('lang') or mobj.group('lang_2')
+        langauge_code = self._LANG_MAP.get(lang)
 
-        info = self._download_json(
+        config = self._download_json(f'{self._API_BASE}/config/{lang}/{video_id}', video_id)
-            '%s/config/%s/%s' % (self._API_BASE, lang, video_id), video_id)
-        player_info = info['videoJsonPlayer']
 
-        vsr = try_get(player_info, lambda x: x['VSR'], dict)
+        geoblocking = traverse_obj(config, ('data', 'attributes', 'restriction', 'geoblocking')) or {}
-        if not vsr:
+        if geoblocking.get('restrictedArea'):
-            error = None
+            raise GeoRestrictedError(f'Video restricted to {geoblocking["code"]!r}',
-            if try_get(player_info, lambda x: x['custom_msg']['type']) == 'error':
+                                     countries=self._COUNTRIES_MAP.get(geoblocking['code'], ('DE', 'FR')))
-                error = try_get(
-                    player_info, lambda x: x['custom_msg']['msg'], compat_str)
-            if not error:
-                error = 'Video %s is not available' % player_info.get('VID') or video_id
-            raise ExtractorError(error, expected=True)
 
-        upload_date_str = player_info.get('shootingDate')
+        if not traverse_obj(config, ('data', 'attributes', 'rights')):
-        if not upload_date_str:
+            # Eg: https://www.arte.tv/de/videos/097407-215-A/28-minuten
-            upload_date_str = (player_info.get('VRA') or player_info.get('VDA') or '').split(' ')[0]
+            # Eg: https://www.arte.tv/es/videos/104351-002-A/serviteur-du-peuple-1-23
+            raise ExtractorError(
+                'Video is not available in this language edition of Arte or broadcast rights expired', expected=True)
 
-        title = (player_info.get('VTI') or player_info['VID']).strip()
+        formats, subtitles = [], {}
-        subtitle = player_info.get('VSU', '').strip()
+        for stream in config['data']['attributes']['streams']:
-        if subtitle:
+            # official player contains code like `e.get("versions")[0].eStat.ml5`
-            title += ' - %s' % subtitle
+            stream_version = stream['versions'][0]
+            stream_version_code = stream_version['eStat']['ml5']
 
-        qfunc = qualities(['MQ', 'HQ', 'EQ', 'SQ'])
+            lang_pref = -1
+            m = self._VERSION_CODE_RE.match(stream_version_code)
+            if m:
+                lang_pref = int(''.join('01'[x] for x in (
+                    m.group('vlang') == langauge_code,      # we prefer voice in the requested language
+                    not m.group('audio_desc'),              # and not the audio description version
+                    bool(m.group('original_voice')),        # but if voice is not in the requested language, at least choose the original voice
+                    m.group('sub_lang') == langauge_code,   # if subtitles are present, we prefer them in the requested language
+                    not m.group('has_sub'),                 # but we prefer no subtitles otherwise
+                    not m.group('sdh_sub'),                 # and we prefer not the hard-of-hearing subtitles if there are subtitles
+                )))
 
-        LANGS = {
+            if stream['protocol'].startswith('HLS'):
-            'fr': 'F',
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(
-            'de': 'A',
+                    stream['url'], video_id=video_id, ext='mp4', m3u8_id=stream_version_code, fatal=False)
-            'en': 'E[ANG]',
+                for fmt in fmts:
-            'es': 'E[ESP]',
+                    fmt.update({
-            'it': 'E[ITA]',
+                        'format_note': f'{stream_version.get("label", "unknown")} [{stream_version.get("shortLabel", "?")}]',
-            'pl': 'E[POL]',
-        }
-
-        langcode = LANGS.get(lang, lang)
-
-        formats = []
-        for format_id, format_dict in vsr.items():
-            f = dict(format_dict)
-            format_url = url_or_none(f.get('url'))
-            streamer = f.get('streamer')
-            if not format_url and not streamer:
-                continue
-            versionCode = f.get('versionCode')
-            l = re.escape(langcode)
-
-            # Language preference from most to least priority
-            # Reference: section 6.8 of
-            # https://www.arte.tv/sites/en/corporate/files/complete-technical-guidelines-arte-geie-v1-07-1.pdf
-            PREFERENCES = (
-                # original version in requested language, without subtitles
-                r'VO{0}$'.format(l),
-                # original version in requested language, with partial subtitles in requested language
-                r'VO{0}-ST{0}$'.format(l),
-                # original version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
-                r'VO{0}-STM{0}$'.format(l),
-                # non-original (dubbed) version in requested language, without subtitles
-                r'V{0}$'.format(l),
-                # non-original (dubbed) version in requested language, with subtitles partial subtitles in requested language
-                r'V{0}-ST{0}$'.format(l),
-                # non-original (dubbed) version in requested language, with subtitles for the deaf and hard-of-hearing in requested language
-                r'V{0}-STM{0}$'.format(l),
-                # original version in requested language, with partial subtitles in different language
-                r'VO{0}-ST(?!{0}).+?$'.format(l),
-                # original version in requested language, with subtitles for the deaf and hard-of-hearing in different language
-                r'VO{0}-STM(?!{0}).+?$'.format(l),
-                # original version in different language, with partial subtitles in requested language
-                r'VO(?:(?!{0}).+?)?-ST{0}$'.format(l),
-                # original version in different language, with subtitles for the deaf and hard-of-hearing in requested language
-                r'VO(?:(?!{0}).+?)?-STM{0}$'.format(l),
-                # original version in different language, without subtitles
-                r'VO(?:(?!{0}))?$'.format(l),
-                # original version in different language, with partial subtitles in different language
-                r'VO(?:(?!{0}).+?)?-ST(?!{0}).+?$'.format(l),
-                # original version in different language, with subtitles for the deaf and hard-of-hearing in different language
-                r'VO(?:(?!{0}).+?)?-STM(?!{0}).+?$'.format(l),
-            )
-
-            for pref, p in enumerate(PREFERENCES):
-                if re.match(p, versionCode):
-                    lang_pref = len(PREFERENCES) - pref
-                    break
-            else:
-                lang_pref = -1
-            format_note = '%s, %s' % (f.get('versionCode'), f.get('versionLibelle'))
-
-            media_type = f.get('mediaType')
-            if media_type == 'hls':
-                m3u8_formats = self._extract_m3u8_formats(
-                    format_url, video_id, 'mp4', entry_protocol='m3u8_native',
-                    m3u8_id=format_id, fatal=False)
-                for m3u8_format in m3u8_formats:
-                    m3u8_format.update({
                         'language_preference': lang_pref,
-                        'format_note': format_note,
                     })
-                formats.extend(m3u8_formats)
+                formats.extend(fmts)
-                continue
+                self._merge_subtitles(subs, target=subtitles)
 
-            format = {
+            elif stream['protocol'] in ('HTTPS', 'RTMP'):
-                'format_id': format_id,
+                formats.append({
-                'language_preference': lang_pref,
+                    'format_id': f'{stream["protocol"]}-{stream_version_code}',
-                'format_note': format_note,
+                    'url': stream['url'],
-                'width': int_or_none(f.get('width')),
+                    'format_note': f'{stream_version.get("label", "unknown")} [{stream_version.get("shortLabel", "?")}]',
-                'height': int_or_none(f.get('height')),
+                    'language_preference': lang_pref,
-                'tbr': int_or_none(f.get('bitrate')),
+                    # 'ext': 'mp4',  # XXX: may or may not be necessary, at least for HTTPS
-                'quality': qfunc(f.get('quality')),
+                })
-            }
 
-            if media_type == 'rtmp':
-                format['url'] = f['streamer']
-                format['play_path'] = 'mp4:' + f['url']
-                format['ext'] = 'flv'
             else:
-                format['url'] = f['url']
+                self.report_warning(f'Skipping stream with unknown protocol {stream["protocol"]}')
 
-            formats.append(format)
+            # TODO: chapters from stream['segments']?
+            # The JS also looks for chapters in config['data']['attributes']['chapters'],
+            # but I am yet to find a video having those
 
-        # For this extractor, quality only represents the relative quality
+        self._sort_formats(formats)
-        # with respect to other formats with the same resolution
+
-        self._sort_formats(formats, ('res', 'quality'))
+        metadata = config['data']['attributes']['metadata']
 
         return {
-            'id': player_info.get('VID') or video_id,
+            'id': metadata['providerId'],
-            'title': title,
+            'webpage_url': traverse_obj(metadata, ('link', 'url')),
-            'description': player_info.get('VDE') or player_info.get('V7T'),
+            'title': traverse_obj(metadata, 'subtitle', 'title'),
-            'upload_date': unified_strdate(upload_date_str),
+            'alt_title': metadata.get('subtitle') and metadata.get('title'),
-            'thumbnail': player_info.get('programImage') or player_info.get('VTU', {}).get('IUR'),
+            'description': metadata.get('description'),
+            'duration': traverse_obj(metadata, ('duration', 'seconds')),
+            'language': metadata.get('language'),
+            'timestamp': traverse_obj(config, ('data', 'attributes', 'rights', 'begin'), expected_type=parse_iso8601),
+            'is_live': config['data']['attributes'].get('live', False),
             'formats': formats,
+            'subtitles': subtitles,
+            'thumbnails': [
+                {'url': image['url'], 'id': image.get('caption')}
+                for image in metadata.get('images') or [] if url_or_none(image.get('url'))
+            ],
         }
 
 
 class ArteTVEmbedIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+'
+    _EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1']
     _TESTS = [{
         'url': 'https://www.arte.tv/player/v5/index.php?json_url=https%3A%2F%2Fapi.arte.tv%2Fapi%2Fplayer%2Fv2%2Fconfig%2Fde%2F100605-013-A&lang=de&autoplay=true&mute=0100605-013-A',
         'info_dict': {
@@ -194,17 +214,12 @@ class ArteTVEmbedIE(InfoExtractor):
             'description': 'md5:be40b667f45189632b78c1425c7c2ce1',
             'upload_date': '20201116',
         },
+        'skip': 'No video available'
     }, {
         'url': 'https://www.arte.tv/player/v3/index.php?json_url=https://api.arte.tv/api/player/v2/config/de/100605-013-A',
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [url for _, url in re.findall(
-            r'<(?:iframe|script)[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?arte\.tv/player/v\d+/index\.php\?.*?\bjson_url=.+?)\1',
-            webpage)]
-
     def _real_extract(self, url):
         qs = parse_qs(url)
         json_url = qs['json_url'][0]
@@ -217,44 +232,36 @@ class ArteTVPlaylistIE(ArteTVBaseIE):
     _VALID_URL = r'https?://(?:www\.)?arte\.tv/(?P<lang>%s)/videos/(?P<id>RC-\d{6})' % ArteTVBaseIE._ARTE_LANGUAGES
     _TESTS = [{
         'url': 'https://www.arte.tv/en/videos/RC-016954/earn-a-living/',
-        'info_dict': {
+        'only_matching': True,
-            'id': 'RC-016954',
-            'title': 'Earn a Living',
-            'description': 'md5:d322c55011514b3a7241f7fb80d494c2',
-        },
-        'playlist_mincount': 6,
     }, {
         'url': 'https://www.arte.tv/pl/videos/RC-014123/arte-reportage/',
-        'only_matching': True,
+        'playlist_mincount': 100,
+        'info_dict': {
+            'description': 'md5:84e7bf1feda248bc325ebfac818c476e',
+            'id': 'RC-014123',
+            'title': 'ARTE Reportage - najlepsze reportaże',
+        },
     }]
 
     def _real_extract(self, url):
-        lang, playlist_id = self._match_valid_url(url).groups()
+        lang, playlist_id = self._match_valid_url(url).group('lang', 'id')
-        collection = self._download_json(
+        playlist = self._download_json(
-            '%s/collectionData/%s/%s?source=videos'
+            f'{self._API_BASE}/playlist/{lang}/{playlist_id}', playlist_id)['data']['attributes']
-            % (self._API_BASE, lang, playlist_id), playlist_id)
+
-        entries = []
+        entries = [{
-        for video in collection['videos']:
+            '_type': 'url_transparent',
-            if not isinstance(video, dict):
+            'url': video['config']['url'],
-                continue
+            'ie_key': ArteTVIE.ie_key(),
-            video_url = url_or_none(video.get('url')) or url_or_none(video.get('jsonUrl'))
+            'id': video.get('providerId'),
-            if not video_url:
+            'title': video.get('title'),
-                continue
+            'alt_title': video.get('subtitle'),
-            video_id = video.get('programId')
+            'thumbnail': url_or_none(traverse_obj(video, ('mainImage', 'url'))),
-            entries.append({
+            'duration': int_or_none(traverse_obj(video, ('duration', 'seconds'))),
-                '_type': 'url_transparent',
+        } for video in traverse_obj(playlist, ('items', lambda _, v: v['config']['url']))]
-                'url': video_url,
+
-                'id': video_id,
+        return self.playlist_result(entries, playlist_id,
-                'title': video.get('title'),
+                                    traverse_obj(playlist, ('metadata', 'title')),
-                'alt_title': video.get('subtitle'),
+                                    traverse_obj(playlist, ('metadata', 'description')))
-                'thumbnail': url_or_none(try_get(video, lambda x: x['mainImage']['url'], compat_str)),
-                'duration': int_or_none(video.get('durationSeconds')),
-                'view_count': int_or_none(video.get('views')),
-                'ie_key': ArteTVIE.ie_key(),
-            })
-        title = collection.get('title')
-        description = collection.get('shortDescription') or collection.get('teaserText')
-        return self.playlist_result(entries, playlist_id, title, description)
 
 
 class ArteTVCategoryIE(ArteTVBaseIE):
@@ -267,14 +274,13 @@ class ArteTVCategoryIE(ArteTVBaseIE):
             'description': 'Investigative documentary series, geopolitical analysis, and international commentary',
         },
         'playlist_mincount': 13,
-    },
+    }]
-    ]
 
     @classmethod
     def suitable(cls, url):
         return (
             not any(ie.suitable(url) for ie in (ArteTVIE, ArteTVPlaylistIE, ))
-            and super(ArteTVCategoryIE, cls).suitable(url))
+            and super().suitable(url))
 
     def _real_extract(self, url):
         lang, playlist_id = self._match_valid_url(url).groups()

yt_dlp/extractor/audiodraft.py

@@ -0,0 +1,93 @@
+from .common import InfoExtractor
+from ..utils import int_or_none
+
+
+class AudiodraftBaseIE(InfoExtractor):
+    def _audiodraft_extract_from_id(self, player_entry_id):
+        data_json = self._download_json(
+            'https://www.audiodraft.com/scripts/general/player/getPlayerInfoNew.php', player_entry_id,
+            headers={
+                'Content-type': 'application/x-www-form-urlencoded; charset=UTF-8',
+                'X-Requested-With': 'XMLHttpRequest',
+            }, data=f'id={player_entry_id}'.encode('utf-8'))
+
+        return {
+            'id': str(data_json['entry_id']),
+            'title': data_json.get('entry_title'),
+            'url': data_json['path'],
+            'vcodec': 'none',
+            'ext': 'mp3',
+            'uploader': data_json.get('designer_name'),
+            'uploader_id': data_json.get('designer_id'),
+            'webpage_url': data_json.get('entry_url'),
+            'like_count': int_or_none(data_json.get('entry_likes')),
+            'average_rating': int_or_none(data_json.get('entry_rating')),
+        }
+
+
+class AudiodraftCustomIE(AudiodraftBaseIE):
+    IE_NAME = 'Audiodraft:custom'
+    _VALID_URL = r'https?://(?:[-\w]+)\.audiodraft\.com/entry/(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'http://nokiatune.audiodraft.com/entry/5874',
+        'info_dict': {
+            'id': '9485',
+            'ext': 'mp3',
+            'title': 'Hula Hula Calls',
+            'uploader': 'unclemaki',
+            'uploader_id': '13512',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }, {
+        'url': 'http://vikinggrace.audiodraft.com/entry/501',
+        'info_dict': {
+            'id': '22241',
+            'ext': 'mp3',
+            'title': 'MVG Happy',
+            'uploader': 'frog',
+            'uploader_id': '19142',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }, {
+        'url': 'http://timferriss.audiodraft.com/entry/765',
+        'info_dict': {
+            'id': '19710',
+            'ext': 'mp3',
+            'title': 'ferris03',
+            'uploader': 'malex',
+            'uploader_id': '17335',
+            'average_rating': 5,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        webpage = self._download_webpage(url, id)
+        player_entry_id = self._search_regex(r'playAudio\(\'(player_entry_\d+)\'\);', webpage, id, 'play entry id')
+        return self._audiodraft_extract_from_id(player_entry_id)
+
+
+class AudiodraftGenericIE(AudiodraftBaseIE):
+    IE_NAME = 'Audiodraft:generic'
+    _VALID_URL = r'https?://www\.audiodraft\.com/contests/[^/#]+#entries&eid=(?P<id>\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.audiodraft.com/contests/570-Score-A-Video-Surprise-Us#entries&eid=30138',
+        'info_dict': {
+            'id': '30138',
+            'ext': 'mp3',
+            'title': 'DROP in sound_V2',
+            'uploader': 'TiagoSilva',
+            'uploader_id': '19452',
+            'average_rating': 4,
+            'like_count': int,
+        },
+    }]
+
+    def _real_extract(self, url):
+        id = self._match_id(url)
+        return self._audiodraft_extract_from_id(f'player_entry_{id}')

yt_dlp/extractor/bandcamp.py

@@ -22,6 +22,7 @@ from ..utils import (
 
 class BandcampIE(InfoExtractor):
     _VALID_URL = r'https?://[^/]+\.bandcamp\.com/track/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [r'<meta property="og:url"[^>]*?content="(?P<url>.*?bandcamp\.com.*?)"']
     _TESTS = [{
         'url': 'http://youtube-dl.bandcamp.com/track/youtube-dl-test-song',
         'md5': 'c557841d5e50261777a6585648adf439',

yt_dlp/extractor/bbc.py

@@ -46,6 +46,7 @@ class BBCCoUkIE(InfoExtractor):
                         )
                         (?P<id>%s)(?!/(?:episodes|broadcasts|clips))
                     ''' % _ID_REGEX
+    _EMBED_REGEX = [r'setPlaylist\("(?P<url>https?://www\.bbc\.co\.uk/iplayer/[^/]+/[\da-z]{8})"\)']
 
     _LOGIN_URL = 'https://account.bbc.com/signin'
     _NETRC_MACHINE = 'bbc'
@@ -1231,7 +1232,7 @@ class BBCIE(BBCCoUkIE):
                                           (lambda x: x['data']['blocks'],
                                            lambda x: x['data']['content']['model']['blocks'],),
                                           list) or []):
-                        if block.get('type') != 'media':
+                        if block.get('type') not in ['media', 'video']:
                             continue
                         parse_media(block.get('model'))
             return self.playlist_result(

yt_dlp/extractor/bigo.py

@@ -28,7 +28,7 @@ class BigoIE(InfoExtractor):
         user_id = self._match_id(url)
 
         info_raw = self._download_json(
-            'https://bigo.tv/studio/getInternalStudioInfo',
+            'https://ta.bigo.tv/official_website/studio/getInternalStudioInfo',
             user_id, data=urlencode_postdata({'siteId': user_id}))
 
         if not isinstance(info_raw, dict):
@@ -41,14 +41,14 @@ class BigoIE(InfoExtractor):
         if not info.get('alive'):
             raise ExtractorError('This user is offline.', expected=True)
 
+        formats, subs = self._extract_m3u8_formats_and_subtitles(
+            info.get('hls_src'), user_id, 'mp4', 'm3u8')
+
         return {
             'id': info.get('roomId') or user_id,
             'title': info.get('roomTopic') or info.get('nick_name') or user_id,
-            'formats': [{
+            'formats': formats,
-                'url': info.get('hls_src'),
+            'subtitles': subs,
-                'ext': 'mp4',
-                'protocol': 'm3u8',
-            }],
             'thumbnail': info.get('snapshot'),
             'uploader': info.get('nick_name'),
             'uploader_id': user_id,

yt_dlp/extractor/bilibili.py

@@ -795,12 +795,14 @@ class BiliIntlBaseIE(InfoExtractor):
 
     def _get_subtitles(self, *, ep_id=None, aid=None):
         sub_json = self._call_api(
-            '/web/v2/subtitle', ep_id or aid, note='Downloading subtitles list',
+            '/web/v2/subtitle', ep_id or aid, fatal=False,
-            errnote='Unable to download subtitles list', query=filter_dict({
+            note='Downloading subtitles list', errnote='Unable to download subtitles list',
+            query=filter_dict({
                 'platform': 'web',
+                's_locale': 'en_US',
                 'episode_id': ep_id,
                 'aid': aid,
-            }))
+            })) or {}
         subtitles = {}
         for sub in sub_json.get('subtitles') or []:
             sub_url = sub.get('url')

yt_dlp/extractor/bitchute.py

@@ -13,6 +13,7 @@ from ..utils import (
 
 class BitChuteIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
         'md5': '7e427d7ed7af5a75b5855705ec750e2b',
@@ -33,14 +34,6 @@ class BitChuteIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>%s)' % BitChuteIE._VALID_URL,
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

yt_dlp/extractor/blogger.py

@@ -1,5 +1,3 @@
-import re
-
 from ..utils import (
     mimetype2ext,
     parse_duration,
@@ -13,7 +11,7 @@ from .common import InfoExtractor
 class BloggerIE(InfoExtractor):
     IE_NAME = 'blogger.com'
     _VALID_URL = r'https?://(?:www\.)?blogger\.com/video\.g\?token=(?P<id>.+)'
-    _VALID_EMBED = r'''<iframe[^>]+src=["']((?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']'''
+    _EMBED_REGEX = [r'''<iframe[^>]+src=["'](?P<url>(?:https?:)?//(?:www\.)?blogger\.com/video\.g\?token=[^"']+)["']''']
     _TESTS = [{
         'url': 'https://www.blogger.com/video.g?token=AD6v5dzEe9hfcARr5Hlq1WTkYy6t-fXH3BBahVhGvVHe5szdEUBEloSEDSTA8-b111089KbfWuBvTN7fnbxMtymsHhXAXwVvyzHH4Qch2cfLQdGxKQrrEuFpC1amSl_9GuLWODjPgw',
         'md5': 'f1bc19b6ea1b0fd1d81e84ca9ec467ac',
@@ -26,10 +24,6 @@ class BloggerIE(InfoExtractor):
         }
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(BloggerIE._VALID_EMBED, webpage)
-
     def _real_extract(self, url):
         token_id = self._match_id(url)
         webpage = self._download_webpage(url, token_id)

yt_dlp/extractor/brightcove.py

@@ -402,11 +402,11 @@ class BrightcoveNewIE(AdobePassIE):
 
     @staticmethod
     def _extract_url(ie, webpage):
-        urls = BrightcoveNewIE._extract_urls(ie, webpage)
+        urls = BrightcoveNewIE._extract_brightcove_urls(ie, webpage)
         return urls[0] if urls else None
 
     @staticmethod
-    def _extract_urls(ie, webpage):
+    def _extract_brightcove_urls(ie, webpage):
         # Reference:
         # 1. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#setvideoiniframe
         # 2. http://docs.brightcove.com/en/video-cloud/brightcove-player/guides/publish-video.html#tag

yt_dlp/extractor/buzzfeed.py

@@ -81,7 +81,7 @@ class BuzzFeedIE(InfoExtractor):
                 continue
             entries.append(self.url_result(video['url']))
 
-        facebook_urls = FacebookIE._extract_urls(webpage)
+        facebook_urls = FacebookIE._extract_embed_urls(url, webpage)
         entries.extend([
             self.url_result(facebook_url)
             for facebook_url in facebook_urls])

yt_dlp/extractor/camtasia.py

@@ -0,0 +1,71 @@
+import os
+import urllib.parse
+
+from .common import InfoExtractor
+from ..utils import float_or_none
+
+
+class CamtasiaEmbedIE(InfoExtractor):
+    _VALID_URL = False
+    _WEBPAGE_TESTS = [
+        {
+            'url': 'http://www.ll.mit.edu/workshops/education/videocourses/antennas/lecture1/video/',
+            'playlist': [{
+                'md5': '0c5e352edabf715d762b0ad4e6d9ee67',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - video1',
+                    'ext': 'flv',
+                    'duration': 2235.90,
+                }
+            }, {
+                'md5': '10e4bb3aaca9fd630e273ff92d9f3c63',
+                'info_dict': {
+                    'id': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final_PIP',
+                    'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final - pip',
+                    'ext': 'flv',
+                    'duration': 2235.93,
+                }
+            }],
+            'info_dict': {
+                'title': 'Fenn-AA_PA_Radar_Course_Lecture_1c_Final',
+            },
+            'skip': 'webpage dead'
+        },
+
+    ]
+
+    def _extract_from_webpage(self, url, webpage):
+        camtasia_cfg = self._search_regex(
+            r'fo\.addVariable\(\s*"csConfigFile",\s*"([^"]+)"\s*\);',
+            webpage, 'camtasia configuration file', default=None)
+        if camtasia_cfg is None:
+            return None
+
+        title = self._html_search_meta('DC.title', webpage, fatal=True)
+
+        camtasia_url = urllib.parse.urljoin(url, camtasia_cfg)
+        camtasia_cfg = self._download_xml(
+            camtasia_url, self._generic_id(url),
+            note='Downloading camtasia configuration',
+            errnote='Failed to download camtasia configuration')
+        fileset_node = camtasia_cfg.find('./playlist/array/fileset')
+
+        entries = []
+        for n in fileset_node.getchildren():
+            url_n = n.find('./uri')
+            if url_n is None:
+                continue
+
+            entries.append({
+                'id': os.path.splitext(url_n.text.rpartition('/')[2])[0],
+                'title': f'{title} - {n.tag}',
+                'url': urllib.parse.urljoin(url, url_n.text),
+                'duration': float_or_none(n.find('./duration').text),
+            })
+
+        return {
+            '_type': 'playlist',
+            'entries': entries,
+            'title': title,
+        }

yt_dlp/extractor/cellebrite.py

@@ -0,0 +1,64 @@
+from .common import InfoExtractor
+from ..utils import traverse_obj
+
+
+class CellebriteIE(InfoExtractor):
+    _VALID_URL = r'https?://cellebrite\.com/(?:\w+)?/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://cellebrite.com/en/collect-data-from-android-devices-with-cellebrite-ufed/',
+        'info_dict': {
+            'id': '16025876',
+            'ext': 'mp4',
+            'description': 'md5:174571cb97083fd1d457d75c684f4e2b',
+            'thumbnail': 'https://cellebrite.com/wp-content/uploads/2021/05/Chat-Capture-1024x559.png',
+            'title': 'Ask the Expert: Chat Capture - Collect Data from Android Devices in Cellebrite UFED',
+            'duration': 455,
+            'tags': [],
+        }
+    }, {
+        'url': 'https://cellebrite.com/en/how-to-lawfully-collect-the-maximum-amount-of-data-from-android-devices/',
+        'info_dict': {
+            'id': '29018255',
+            'ext': 'mp4',
+            'duration': 134,
+            'tags': [],
+            'description': 'md5:e9a3d124c7287b0b07bad2547061cacf',
+            'thumbnail': 'https://cellebrite.com/wp-content/uploads/2022/07/How-to-Lawfully-Collect-the-Maximum-Amount-of-Data-From-Android-Devices.png',
+            'title': 'Android Extractions Explained',
+        }
+    }]
+
+    def _get_formats_and_subtitles(self, json_data, display_id):
+        formats = [{'url': url} for url in traverse_obj(json_data, ('mp4', ..., 'url')) or []]
+        subtitles = {}
+
+        for url in traverse_obj(json_data, ('hls', ..., 'url')) or []:
+            fmt, sub = self._extract_m3u8_formats_and_subtitles(
+                url, display_id, ext='mp4', headers={'Referer': 'https://play.vidyard.com/'})
+            formats.extend(fmt)
+            self._merge_subtitles(sub, target=subtitles)
+
+        return formats, subtitles
+
+    def _real_extract(self, url):
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+
+        player_uuid = self._search_regex(
+            r'<img\s[^>]*\bdata-uuid\s*=\s*"([^"\?]+)', webpage, 'player UUID')
+        json_data = self._download_json(
+            f'https://play.vidyard.com/player/{player_uuid}.json', display_id)['payload']['chapters'][0]
+
+        formats, subtitles = self._get_formats_and_subtitles(json_data['sources'], display_id)
+        self._sort_formats(formats)
+        return {
+            'id': str(json_data['videoId']),
+            'title': json_data.get('name') or self._og_search_title(webpage),
+            'formats': formats,
+            'subtitles': subtitles,
+            'description': json_data.get('description') or self._og_search_description(webpage),
+            'duration': json_data.get('seconds'),
+            'tags': json_data.get('tags'),
+            'thumbnail': self._og_search_thumbnail(webpage),
+            'http_headers': {'Referer': 'https://play.vidyard.com/'},
+        }

yt_dlp/extractor/channel9.py

@@ -14,6 +14,7 @@ class Channel9IE(InfoExtractor):
     IE_DESC = 'Channel 9'
     IE_NAME = 'channel9'
     _VALID_URL = r'https?://(?:www\.)?(?:channel9\.msdn\.com|s\.ch9\.ms)/(?P<contentpath>.+?)(?P<rss>/RSS)?/?(?:[?#&]|$)'
+    _EMBED_REGEX = [r'<iframe[^>]+src=["\'](?P<url>https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b']
 
     _TESTS = [{
         'url': 'http://channel9.msdn.com/Events/TechEd/Australia/2013/KOS002',
@@ -78,12 +79,6 @@ class Channel9IE(InfoExtractor):
 
     _RSS_URL = 'http://channel9.msdn.com/%s/RSS'
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return re.findall(
-            r'<iframe[^>]+src=["\'](https?://channel9\.msdn\.com/(?:[^/]+/)+)player\b',
-            webpage)
-
     def _extract_list(self, video_id, rss_url=None):
         if not rss_url:
             rss_url = self._RSS_URL % video_id

yt_dlp/extractor/cinchcast.py

@@ -7,6 +7,8 @@ from ..utils import (
 
 class CinchcastIE(InfoExtractor):
     _VALID_URL = r'https?://player\.cinchcast\.com/.*?(?:assetId|show_id)=(?P<id>[0-9]+)'
+    _EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>https?://player\.cinchcast\.com/.+?)\1']
+
     _TESTS = [{
         'url': 'http://player.cinchcast.com/?show_id=5258197&platformId=1&assetType=single',
         'info_dict': {

yt_dlp/extractor/cloudflarestream.py

@@ -1,5 +1,4 @@
 import base64
-import re
 
 from .common import InfoExtractor
 
@@ -16,6 +15,7 @@ class CloudflareStreamIE(InfoExtractor):
                         )
                         (?P<id>%s)
                     ''' % (_DOMAIN_RE, _EMBED_RE, _ID_RE)
+    _EMBED_REGEX = [fr'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//{_EMBED_RE}(?:{_ID_RE}).*?)\1']
     _TESTS = [{
         'url': 'https://embed.cloudflarestream.com/embed/we4g.fla9.latest.js?video=31c9291ab41fac05471db4e73aa11717',
         'info_dict': {
@@ -37,21 +37,13 @@ class CloudflareStreamIE(InfoExtractor):
         'only_matching': True,
     }]
 
-    @staticmethod
-    def _extract_urls(webpage):
-        return [
-            mobj.group('url')
-            for mobj in re.finditer(
-                r'<script[^>]+\bsrc=(["\'])(?P<url>(?:https?:)?//%s(?:%s).*?)\1' % (CloudflareStreamIE._EMBED_RE, CloudflareStreamIE._ID_RE),
-                webpage)]
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         domain = 'bytehighway.net' if 'bytehighway.net/' in url else 'videodelivery.net'
         base_url = 'https://%s/%s/' % (domain, video_id)
         if '.' in video_id:
             video_id = self._parse_json(base64.urlsafe_b64decode(
-                video_id.split('.')[1]), video_id)['sub']
+                video_id.split('.')[1] + '==='), video_id)['sub']
         manifest_base_url = base_url + 'manifest/video.'
 
         formats = self._extract_m3u8_formats(

yt_dlp/extractor/common.py

@@ -11,17 +11,20 @@ import math
 import netrc
 import os
 import random
+import re
 import sys
 import time
+import types
 import urllib.parse
 import urllib.request
 import xml.etree.ElementTree
 
-from ..compat import functools, re  # isort: split
+from ..compat import functools  # isort: split
 from ..compat import compat_etree_fromstring, compat_expanduser, compat_os_name
 from ..downloader import FileDownloader
 from ..downloader.f4m import get_base_url, remove_encrypted_media
 from ..utils import (
+    IDENTITY,
     JSON_LD_RE,
     NO_DEFAULT,
     ExtractorError,
@@ -29,6 +32,7 @@ from ..utils import (
     GeoUtils,
     LenientJSONDecoder,
     RegexNotFoundError,
+    RetryManager,
     UnsupportedError,
     age_restricted,
     base_url,
@@ -58,6 +62,7 @@ from ..utils import (
     parse_m3u8_attributes,
     parse_resolution,
     sanitize_filename,
+    sanitize_url,
     sanitized_Request,
     str_or_none,
     str_to_int,
@@ -149,6 +154,7 @@ class InfoExtractor:
                     * abr        Average audio bitrate in KBit/s
                     * acodec     Name of the audio codec in use
                     * asr        Audio sampling rate in Hertz
+                    * audio_channels  Number of audio channels
                     * vbr        Average video bitrate in KBit/s
                     * fps        Frame rate
                     * vcodec     Name of the video codec in use
@@ -311,7 +317,8 @@ class InfoExtractor:
                     live stream that goes on instead of a fixed-length video.
     was_live:       True, False, or None (=unknown). Whether this video was
                     originally a live stream.
-    live_status:    'is_live', 'is_upcoming', 'was_live', 'not_live' or None (=unknown)
+    live_status:    None (=unknown), 'is_live', 'is_upcoming', 'was_live', 'not_live',
+                    or 'post_live' (was live, but VOD is not yet processed)
                     If absent, automatically set from is_live, was_live
     start_time:     Time in seconds where the reproduction should start, as
                     specified in the URL.
@@ -324,11 +331,12 @@ class InfoExtractor:
     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; e.g. '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
+    _old_archive_ids: A list of old archive ids needed for backward compatibility
     __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.
@@ -383,6 +391,10 @@ class InfoExtractor:
     section_start:  Start time of the section in seconds
     section_end:    End time of the section in seconds
 
+    The following fields should only be set for storyboards:
+    rows:           Number of rows in each storyboard fragment, as an integer
+    columns:        Number of columns in each storyboard fragment, as an integer
+
     Unless mentioned otherwise, the fields should be Unicode strings.
 
     Unless mentioned otherwise, None is equivalent to absence of information.
@@ -425,14 +437,26 @@ class InfoExtractor:
     title, description etc.
 
 
-    Subclasses of this should define a _VALID_URL regexp and, re-define the
+    Subclasses of this should also be added to the list of extractors and
-    _real_extract() and (optionally) _real_initialize() methods.
+    should define a _VALID_URL regexp and, re-define the _real_extract() and
-    Probably, they should also be added to the list of extractors.
+    (optionally) _real_initialize() methods.
 
     Subclasses may also override suitable() if necessary, but ensure the function
     signature is preserved and that this function imports everything it needs
     (except other extractors), so that lazy_extractors works correctly.
 
+    Subclasses can define a list of _EMBED_REGEX, which will be searched for in
+    the HTML of Generic webpages. It may also override _extract_embed_urls
+    or _extract_from_webpage as necessary. While these are normally classmethods,
+    _extract_from_webpage is allowed to be an instance method.
+
+    _extract_from_webpage may raise self.StopExtraction() to stop further
+    processing of the webpage and obtain exclusive rights to it. This is useful
+    when the extractor cannot reliably be matched using just the URL,
+    e.g. invidious/peertube instances
+
+    Embed-only extractors can be defined by setting _VALID_URL = False.
+
     To support username + password (or netrc) login, the extractor must define a
     _NETRC_MACHINE and re-define _perform_login(username, password) and
     (optionally) _initialize_pre_login() methods. The _perform_login method will
@@ -470,6 +494,8 @@ class InfoExtractor:
     _NETRC_MACHINE = None
     IE_DESC = None
     SEARCH_KEY = None
+    _VALID_URL = None
+    _EMBED_REGEX = []
 
     def _login_hint(self, method=NO_DEFAULT, netrc=None):
         password_hint = f'--username and --password, or --netrc ({netrc or self._NETRC_MACHINE}) to provide account credentials'
@@ -493,12 +519,12 @@ class InfoExtractor:
 
     @classmethod
     def _match_valid_url(cls, url):
+        if cls._VALID_URL is False:
+            return None
         # This does not use has/getattr intentionally - we want to know whether
         # we have cached the regexp for *this* class, whereas getattr would also
         # match the superclass
         if '_VALID_URL_RE' not in cls.__dict__:
-            if '_VALID_URL' not in cls.__dict__:
-                cls._VALID_URL = cls._make_valid_url()
             cls._VALID_URL_RE = re.compile(cls._VALID_URL)
         return cls._VALID_URL_RE.match(url)
 
@@ -642,10 +668,10 @@ class InfoExtractor:
                         return None
                     if self._x_forwarded_for_ip:
                         ie_result['__x_forwarded_for_ip'] = self._x_forwarded_for_ip
-                    subtitles = ie_result.get('subtitles')
+                    subtitles = ie_result.get('subtitles') or {}
-                    if (subtitles and 'live_chat' in subtitles
+                    if 'no-live-chat' in self.get_param('compat_opts'):
-                            and 'no-live-chat' in self.get_param('compat_opts', [])):
+                        for lang in ('live_chat', 'comments', 'danmaku'):
-                        del subtitles['live_chat']
+                            subtitles.pop(lang, None)
                     return ie_result
                 except GeoRestrictedError as e:
                     if self.__maybe_fake_ip_and_retry(e.countries):
@@ -925,39 +951,37 @@ class InfoExtractor:
 
         return content
 
-    def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True):
+    def __print_error(self, errnote, fatal, video_id, err):
+        if fatal:
+            raise ExtractorError(f'{video_id}: {errnote}', cause=err)
+        elif errnote:
+            self.report_warning(f'{video_id}: {errnote}: {err}')
+
+    def _parse_xml(self, xml_string, video_id, transform_source=None, fatal=True, errnote=None):
         if transform_source:
             xml_string = transform_source(xml_string)
         try:
             return compat_etree_fromstring(xml_string.encode('utf-8'))
         except xml.etree.ElementTree.ParseError as ve:
-            errmsg = '%s: Failed to parse XML ' % video_id
+            self.__print_error('Failed to parse XML' if errnote is None else errnote, fatal, video_id, ve)
-            if fatal:
-                raise ExtractorError(errmsg, cause=ve)
-            else:
-                self.report_warning(errmsg + str(ve))
 
-    def _parse_json(self, json_string, video_id, transform_source=None, fatal=True, **parser_kwargs):
+    def _parse_json(self, json_string, video_id, transform_source=None, fatal=True, errnote=None, **parser_kwargs):
         try:
             return json.loads(
                 json_string, cls=LenientJSONDecoder, strict=False, transform_source=transform_source, **parser_kwargs)
         except ValueError as ve:
-            errmsg = f'{video_id}: Failed to parse JSON'
+            self.__print_error('Failed to parse JSON' if errnote is None else errnote, fatal, video_id, ve)
-            if fatal:
-                raise ExtractorError(errmsg, cause=ve)
-            else:
-                self.report_warning(f'{errmsg}: {ve}')
 
-    def _parse_socket_response_as_json(self, data, video_id, transform_source=None, fatal=True):
+    def _parse_socket_response_as_json(self, data, *args, **kwargs):
-        return self._parse_json(
+        return self._parse_json(data[data.find('{'):data.rfind('}') + 1], *args, **kwargs)
-            data[data.find('{'):data.rfind('}') + 1],
-            video_id, transform_source, fatal)
 
     def __create_download_methods(name, parser, note, errnote, return_value):
 
-        def parse(ie, content, *args, **kwargs):
+        def parse(ie, content, *args, errnote=errnote, **kwargs):
             if parser is None:
                 return content
+            if errnote is False:
+                kwargs['errnote'] = errnote
             # parser is fetched by name so subclasses can override it
             return getattr(ie, parser)(content, *args, **kwargs)
 
@@ -969,7 +993,7 @@ class InfoExtractor:
             if res is False:
                 return res
             content, urlh = res
-            return parse(self, content, video_id, transform_source=transform_source, fatal=fatal), urlh
+            return parse(self, content, video_id, transform_source=transform_source, fatal=fatal, errnote=errnote), urlh
 
         def download_content(self, url_or_request, video_id, note=note, errnote=errnote, transform_source=None,
                              fatal=True, encoding=None, data=None, headers={}, query={}, expected_status=None):
@@ -984,7 +1008,7 @@ class InfoExtractor:
                     self.report_warning(f'Unable to load request from disk: {e}')
                 else:
                     content = self.__decode_webpage(webpage_bytes, encoding, url_or_request.headers)
-                    return parse(self, content, video_id, transform_source, fatal)
+                    return parse(self, content, video_id, transform_source=transform_source, fatal=fatal, errnote=errnote)
             kwargs = {
                 'note': note,
                 'errnote': errnote,
@@ -1139,10 +1163,12 @@ class InfoExtractor:
             'url': url,
         }
 
-    def playlist_from_matches(self, matches, playlist_id=None, playlist_title=None, getter=None, ie=None, video_kwargs=None, **kwargs):
+    @classmethod
-        urls = (self.url_result(self._proto_relative_url(m), ie, **(video_kwargs or {}))
+    def playlist_from_matches(cls, matches, playlist_id=None, playlist_title=None,
-                for m in orderedSet(map(getter, matches) if getter else matches))
+                              getter=IDENTITY, ie=None, video_kwargs=None, **kwargs):
-        return self.playlist_result(urls, playlist_id, playlist_title, **kwargs)
+        return cls.playlist_result(
+            (cls.url_result(m, ie, **(video_kwargs or {})) for m in orderedSet(map(getter, matches), lazy=True)),
+            playlist_id, playlist_title, **kwargs)
 
     @staticmethod
     def playlist_result(entries, playlist_id=None, playlist_title=None, playlist_description=None, *, multi_video=False, **kwargs):
@@ -1349,12 +1375,20 @@ class InfoExtractor:
     def _dc_search_uploader(self, html):
         return self._html_search_meta('dc.creator', html, 'uploader')
 
-    def _rta_search(self, html):
+    @staticmethod
+    def _rta_search(html):
         # See http://www.rtalabel.org/index.php?content=howtofaq#single
         if re.search(r'(?ix)<meta\s+name="rating"\s+'
                      r'     content="RTA-5042-1996-1400-1577-RTA"',
                      html):
             return 18
+
+        # And then there are the jokers who advertise that they use RTA, but actually don't.
+        AGE_LIMIT_MARKERS = [
+            r'Proudly Labeled <a href="http://www\.rtalabel\.org/" title="Restricted to Adults">RTA</a>',
+        ]
+        if any(re.search(marker, html) for marker in AGE_LIMIT_MARKERS):
+            return 18
         return 0
 
     def _media_rating_search(self, html):
@@ -1502,7 +1536,7 @@ class InfoExtractor:
                 'url': url_or_none(e.get('contentUrl')),
                 'title': unescapeHTML(e.get('name')),
                 'description': unescapeHTML(e.get('description')),
-                'thumbnails': [{'url': url}
+                'thumbnails': [{'url': unescapeHTML(url)}
                                for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL'))
                                if url_or_none(url)],
                 'duration': parse_duration(e.get('duration')),
@@ -1635,8 +1669,8 @@ class InfoExtractor:
         regex = r' *((?P<reverse>\+)?(?P<field>[a-zA-Z0-9_]+)((?P<separator>[~:])(?P<limit>.*?))?)? *$'
 
         default = ('hidden', 'aud_or_vid', 'hasvid', 'ie_pref', 'lang', 'quality',
-                   'res', 'fps', 'hdr:12', 'codec:vp9.2', 'size', 'br', 'asr',
+                   'res', 'fps', 'hdr:12', 'vcodec:vp9.2', 'channels', 'acodec',
-                   'proto', 'ext', 'hasaud', 'source', 'id')  # These must not be aliases
+                   'size', 'br', 'asr', 'proto', 'ext', 'hasaud', 'source', 'id')  # These must not be aliases
         ytdl_default = ('hasaud', 'lang', 'quality', 'tbr', 'filesize', 'vbr',
                         'height', 'width', 'proto', 'vext', 'abr', 'aext',
                         'fps', 'fs_approx', 'source', 'id')
@@ -1671,6 +1705,7 @@ class InfoExtractor:
             'height': {'convert': 'float_none'},
             'width': {'convert': 'float_none'},
             'fps': {'convert': 'float_none'},
+            'channels': {'convert': 'float_none', 'field': 'audio_channels'},
             'tbr': {'convert': 'float_none'},
             'vbr': {'convert': 'float_none'},
             'abr': {'convert': 'float_none'},
@@ -1684,13 +1719,14 @@ class InfoExtractor:
             'res': {'type': 'multiple', 'field': ('height', 'width'),
                     'function': lambda it: (lambda l: min(l) if l else 0)(tuple(filter(None, it)))},
 
-            # For compatibility with youtube-dl
+            # Actual field names
             'format_id': {'type': 'alias', 'field': 'id'},
             'preference': {'type': 'alias', 'field': 'ie_pref'},
             'language_preference': {'type': 'alias', 'field': 'lang'},
             'source_preference': {'type': 'alias', 'field': 'source'},
             'protocol': {'type': 'alias', 'field': 'proto'},
             'filesize_approx': {'type': 'alias', 'field': 'fs_approx'},
+            'audio_channels': {'type': 'alias', 'field': 'channels'},
 
             # Deprecated
             'dimension': {'type': 'alias', 'field': 'res', 'deprecated': True},
@@ -1961,14 +1997,9 @@ class InfoExtractor:
             else 'https:')
 
     def _proto_relative_url(self, url, scheme=None):
-        if url is None:
+        scheme = scheme or self.http_scheme()
-            return url
+        assert scheme.endswith(':')
-        if url.startswith('//'):
+        return sanitize_url(url, scheme=scheme[:-1])
-            if scheme is None:
-                scheme = self.http_scheme()
-            return scheme + url
-        else:
-            return url
 
     def _sleep(self, timeout, video_id, msg_template=None):
         if msg_template is None:
@@ -2336,7 +2367,7 @@ class InfoExtractor:
                     audio_group_id = last_stream_inf.get('AUDIO')
                     # As per [1, 4.3.4.1.1] any EXT-X-STREAM-INF tag which
                     # references a rendition group MUST have a CODECS attribute.
-                    # However, this is not always respected, for example, [2]
+                    # However, this is not always respected. E.g. [2]
                     # contains EXT-X-STREAM-INF tag which references AUDIO
                     # rendition group but does not have CODECS and despite
                     # referencing an audio group it represents a complete
@@ -2972,8 +3003,8 @@ class InfoExtractor:
                                     segment_number += 1
                                 segment_time += segment_d
                     elif 'segment_urls' in representation_ms_info and 's' in representation_ms_info:
-                        # No media template
+                        # No media template,
-                        # Example: https://www.youtube.com/watch?v=iXZV5uAYMJI
+                        # e.g. https://www.youtube.com/watch?v=iXZV5uAYMJI
                         # or any YouTube dashsegments video
                         fragments = []
                         segment_index = 0
@@ -2990,7 +3021,7 @@ class InfoExtractor:
                         representation_ms_info['fragments'] = fragments
                     elif 'segment_urls' in representation_ms_info:
                         # Segment URLs with no SegmentTimeline
-                        # Example: https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
+                        # E.g. https://www.seznam.cz/zpravy/clanek/cesko-zasahne-vitr-o-sile-vichrice-muze-byt-i-zivotu-nebezpecny-39091
                         # https://github.com/ytdl-org/youtube-dl/pull/14844
                         fragments = []
                         segment_duration = float_or_none(
@@ -3218,8 +3249,8 @@ class InfoExtractor:
         media_tags.extend(re.findall(
             # We only allow video|audio followed by a whitespace or '>'.
             # Allowing more characters may end up in significant slow down (see
-            # https://github.com/ytdl-org/youtube-dl/issues/11979, example URL:
+            # https://github.com/ytdl-org/youtube-dl/issues/11979,
-            # http://www.porntrex.com/maps/videositemap.xml).
+            # e.g. http://www.porntrex.com/maps/videositemap.xml).
             r'(?s)(<(?P<tag>%s)(?:\s+[^>]*)?>)(.*?)</(?P=tag)>' % _MEDIA_TAG_NAME_RE, webpage))
         for media_tag, _, media_type, media_content in media_tags:
             media_info = {
@@ -3639,11 +3670,18 @@ class InfoExtractor:
             t['name'] = cls.ie_key()
             yield t
 
+    @classmethod
+    def get_webpage_testcases(cls):
+        tests = getattr(cls, '_WEBPAGE_TESTS', [])
+        for t in tests:
+            t['name'] = cls.ie_key()
+        return tests
+
     @classproperty
     def age_limit(cls):
         """Get age limit from the testcases"""
         return max(traverse_obj(
-            tuple(cls.get_testcases(include_onlymatching=False)),
+            (*cls.get_testcases(include_onlymatching=False), *cls.get_webpage_testcases()),
             (..., (('playlist', 0), None), 'info_dict', 'age_limit')) or [0])
 
     @classmethod
@@ -3668,7 +3706,7 @@ class InfoExtractor:
             desc += f'; "{cls.SEARCH_KEY}:" prefix'
             if search_examples:
                 _COUNTS = ('', '5', '10', 'all')
-                desc += f' (Example: "{cls.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(search_examples)}")'
+                desc += f' (e.g. "{cls.SEARCH_KEY}{random.choice(_COUNTS)}:{random.choice(search_examples)}")'
         if not cls.working():
             desc += ' (**Currently broken**)' if markdown else ' (Currently broken)'
 
@@ -3763,10 +3801,12 @@ class InfoExtractor:
             headers['Ytdl-request-proxy'] = geo_verification_proxy
         return headers
 
-    def _generic_id(self, url):
+    @staticmethod
+    def _generic_id(url):
         return urllib.parse.unquote(os.path.splitext(url.rstrip('/').split('/')[-1])[0])
 
-    def _generic_title(self, url):
+    @staticmethod
+    def _generic_title(url):
         return urllib.parse.unquote(os.path.splitext(url_basename(url))[0])
 
     @staticmethod
@@ -3812,6 +3852,52 @@ class InfoExtractor:
         self.to_screen(f'Downloading {playlist_label}{playlist_id} - add --no-playlist to download just the {video_label}{video_id}')
         return True
 
+    def _error_or_warning(self, err, _count=None, _retries=0, *, fatal=True):
+        RetryManager.report_retry(err, _count or int(fatal), _retries, info=self.to_screen, warn=self.report_warning,
+                                  sleep_func=self.get_param('retry_sleep_functions', {}).get('extractor'))
+
+    def RetryManager(self, **kwargs):
+        return RetryManager(self.get_param('extractor_retries', 3), self._error_or_warning, **kwargs)
+
+    @classmethod
+    def extract_from_webpage(cls, ydl, url, webpage):
+        ie = (cls if isinstance(cls._extract_from_webpage, types.MethodType)
+              else ydl.get_info_extractor(cls.ie_key()))
+        for info in ie._extract_from_webpage(url, webpage) or []:
+            # url = None since we do not want to set (webpage/original)_url
+            ydl.add_default_extra_info(info, ie, None)
+            yield info
+
+    @classmethod
+    def _extract_from_webpage(cls, url, webpage):
+        for embed_url in orderedSet(
+                cls._extract_embed_urls(url, webpage) or [], lazy=True):
+            yield cls.url_result(embed_url, cls)
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        """@returns all the embed urls on the webpage"""
+        if '_EMBED_URL_RE' not in cls.__dict__:
+            assert isinstance(cls._EMBED_REGEX, (list, tuple))
+            for idx, regex in enumerate(cls._EMBED_REGEX):
+                assert regex.count('(?P<url>') == 1, \
+                    f'{cls.__name__}._EMBED_REGEX[{idx}] must have exactly 1 url group\n\t{regex}'
+            cls._EMBED_URL_RE = tuple(map(re.compile, cls._EMBED_REGEX))
+
+        for regex in cls._EMBED_URL_RE:
+            for mobj in regex.finditer(webpage):
+                embed_url = urllib.parse.urljoin(url, unescapeHTML(mobj.group('url')))
+                if cls._VALID_URL is False or cls.suitable(embed_url):
+                    yield embed_url
+
+    class StopExtraction(Exception):
+        pass
+
+    @classmethod
+    def _extract_url(cls, webpage):  # TODO: Remove
+        """Only for compatibility with some older extractors"""
+        return next(iter(cls._extract_embed_urls(None, webpage) or []), None)
+
 
 class SearchInfoExtractor(InfoExtractor):
     """
@@ -3822,8 +3908,8 @@ class SearchInfoExtractor(InfoExtractor):
 
     _MAX_RESULTS = float('inf')
 
-    @classmethod
+    @classproperty
-    def _make_valid_url(cls):
+    def _VALID_URL(cls):
         return r'%s(?P<prefix>|[1-9][0-9]*|all):(?P<query>[\s\S]+)' % cls._SEARCH_KEY
 
     def _real_extract(self, query):

yt_dlp/extractor/commonmistakes.py

@@ -4,9 +4,7 @@ from ..utils import ExtractorError
 
 class CommonMistakesIE(InfoExtractor):
     IE_DESC = False  # Do not list
-    _VALID_URL = r'''(?x)
+    _VALID_URL = r'(?:url|URL|yt-dlp)$'
-        (?:url|URL)$
-    '''
 
     _TESTS = [{
         'url': 'url',

yt_dlp/extractor/condenast.py

@@ -58,7 +58,10 @@ class CondeNastIE(InfoExtractor):
         )''' % '|'.join(_SITES.keys())
     IE_DESC = 'Condé Nast media group: %s' % ', '.join(sorted(_SITES.values()))
 
-    EMBED_URL = r'(?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?' % '|'.join(_SITES.keys())
+    _EMBED_REGEX = [r'''(?x)
+        <(?:iframe|script)[^>]+?src=(["\'])(?P<url>
+            (?:https?:)?//player(?:-backend)?\.(?:%s)\.com/(?:embed(?:js)?|(?:script|inline)/video)/.+?
+        )\1''' % '|'.join(_SITES.keys())]
 
     _TESTS = [{
         'url': 'http://video.wired.com/watch/3d-printed-speakers-lit-with-led',

yt_dlp/extractor/crooksandliars.py

@@ -7,6 +7,8 @@ from ..utils import (
 
 class CrooksAndLiarsIE(InfoExtractor):
     _VALID_URL = r'https?://embed\.crooksandliars\.com/(?:embed|v)/(?P<id>[A-Za-z0-9]+)'
+    _EMBED_REGEX = [r'<(?:iframe[^>]+src|param[^>]+value)=(["\'])(?P<url>(?:https?:)?//embed\.crooksandliars\.com/(?:embed|v)/.+?)\1']
+
     _TESTS = [{
         'url': 'https://embed.crooksandliars.com/embed/8RUoRhRi',
         'info_dict': {