Release 2025.05.22

Created by: bashonly

:ci skip all

.github/workflows/build.yml

@@ -192,7 +192,7 @@ jobs:
         with:
           path: ./repo
       - name: Virtualized Install, Prepare & Build
-        uses: yt-dlp/run-on-arch-action@v2
+        uses: yt-dlp/run-on-arch-action@v3
         with:
           # Ref: https://github.com/uraimo/run-on-arch-action/issues/55
           env: |
@@ -411,7 +411,7 @@ jobs:
         run: | # Custom pyinstaller built with https://github.com/yt-dlp/pyinstaller-builds
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py --include curl-cffi
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.11.1-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/x86_64/pyinstaller-6.13.0-py3-none-any.whl"
 
       - name: Prepare
         run: |
@@ -460,7 +460,7 @@ jobs:
         run: |
           python devscripts/install_deps.py -o --include build
           python devscripts/install_deps.py
-          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.11.1-py3-none-any.whl"
+          python -m pip install -U "https://yt-dlp.github.io/Pyinstaller-Builds/i686/pyinstaller-6.13.0-py3-none-any.whl"
 
       - name: Prepare
         run: |

CONTRIBUTORS

@@ -770,3 +770,8 @@ NeonMan
 pj47x
 troex
 WouterGordts
+baierjan
+GeoffreyFrogeye
+Pawka
+v3DJG6GL
+yozel

Changelog.md

@@ -4,6 +4,52 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2025.05.22
+
+#### Core changes
+- **cookies**: [Fix Linux desktop environment detection](https://github.com/yt-dlp/yt-dlp/commit/e491fd4d090db3af52a82863fb0553dd5e17fb85) ([#13197](https://github.com/yt-dlp/yt-dlp/issues/13197)) by [mbway](https://github.com/mbway)
+- **jsinterp**: [Fix increment/decrement evaluation](https://github.com/yt-dlp/yt-dlp/commit/167d7a9f0ffd1b4fe600193441bdb7358db2740b) ([#13238](https://github.com/yt-dlp/yt-dlp/issues/13238)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **1tv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/41c0a1fb89628696f8bb88e2b9f3a68f355b8c26) ([#13168](https://github.com/yt-dlp/yt-dlp/issues/13168)) by [bashonly](https://github.com/bashonly)
+- **amcnetworks**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/464c84fedf78eef822a431361155f108b5df96d7) ([#13147](https://github.com/yt-dlp/yt-dlp/issues/13147)) by [bashonly](https://github.com/bashonly)
+- **bitchute**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/1d0f6539c47e5d5c68c3c47cdb7075339e2885ac) ([#13081](https://github.com/yt-dlp/yt-dlp/issues/13081)) by [bashonly](https://github.com/bashonly)
+- **cartoonnetwork**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/7dbb47f84f0ee1266a3a01f58c9bc4c76d76794a) ([#13148](https://github.com/yt-dlp/yt-dlp/issues/13148)) by [bashonly](https://github.com/bashonly)
+- **iprima**: [Fix login support](https://github.com/yt-dlp/yt-dlp/commit/a7d9a5eb79ceeecb851389f3f2c88597871ca3f2) ([#12937](https://github.com/yt-dlp/yt-dlp/issues/12937)) by [baierjan](https://github.com/baierjan)
+- **jiosaavn**
+    - artist: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/586b557b124f954d3f625360ebe970989022ad97) ([#12803](https://github.com/yt-dlp/yt-dlp/issues/12803)) by [subrat-lima](https://github.com/subrat-lima)
+    - playlist, show: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/317f4b8006c2c0f0f64f095b1485163ad97c9053) ([#12803](https://github.com/yt-dlp/yt-dlp/issues/12803)) by [subrat-lima](https://github.com/subrat-lima)
+    - show: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/6839276496d8814cf16f58b637e45663467928e6) ([#12803](https://github.com/yt-dlp/yt-dlp/issues/12803)) by [subrat-lima](https://github.com/subrat-lima)
+- **lrtradio**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/abf58dcd6a09e14eec4ea82ae12f79a0337cb383) ([#13200](https://github.com/yt-dlp/yt-dlp/issues/13200)) by [Pawka](https://github.com/Pawka)
+- **nebula**: [Support `--mark-watched`](https://github.com/yt-dlp/yt-dlp/commit/20f288bdc2173c7cc58d709d25ca193c1f6001e7) ([#13120](https://github.com/yt-dlp/yt-dlp/issues/13120)) by [GeoffreyFrogeye](https://github.com/GeoffreyFrogeye)
+- **niconico**
+    - [Fix error handling](https://github.com/yt-dlp/yt-dlp/commit/f569be4602c2a857087e495d5d7ed6060cd97abe) ([#13236](https://github.com/yt-dlp/yt-dlp/issues/13236)) by [bashonly](https://github.com/bashonly)
+    - live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7a7b85c9014d96421e18aa7ea5f4c1bee5ceece0) ([#13045](https://github.com/yt-dlp/yt-dlp/issues/13045)) by [doe1080](https://github.com/doe1080)
+- **nytimesarticle**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/b26bc32579c00ef579d75a835807ccc87d20ee0a) ([#13104](https://github.com/yt-dlp/yt-dlp/issues/13104)) by [bashonly](https://github.com/bashonly)
+- **once**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/f475e8b529d18efdad603ffda02a56e707fe0e2c) ([#13164](https://github.com/yt-dlp/yt-dlp/issues/13164)) by [bashonly](https://github.com/bashonly)
+- **picarto**: vod: [Support `/profile/` video URLs](https://github.com/yt-dlp/yt-dlp/commit/31e090cb787f3504ec25485adff9a2a51d056734) ([#13227](https://github.com/yt-dlp/yt-dlp/issues/13227)) by [subrat-lima](https://github.com/subrat-lima)
+- **playsuisse**: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/d880e060803ae8ed5a047e578cca01e1f0e630ce) ([#12466](https://github.com/yt-dlp/yt-dlp/issues/12466)) by [v3DJG6GL](https://github.com/v3DJG6GL)
+- **sprout**: [Remove extractor](https://github.com/yt-dlp/yt-dlp/commit/cbcfe6378dde33a650e3852ab17ad4503b8e008d) ([#13149](https://github.com/yt-dlp/yt-dlp/issues/13149)) by [bashonly](https://github.com/bashonly)
+- **svtpage**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/ea8498ed534642dd7e925961b97b934987142fd3) ([#12957](https://github.com/yt-dlp/yt-dlp/issues/12957)) by [diman8](https://github.com/diman8)
+- **twitch**: [Support `--live-from-start`](https://github.com/yt-dlp/yt-dlp/commit/00b1bec55249cf2ad6271d36492c51b34b6459d1) ([#13202](https://github.com/yt-dlp/yt-dlp/issues/13202)) by [bashonly](https://github.com/bashonly)
+- **vimeo**: event: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/545c1a5b6f2fe88722b41aef0e7485bf3be3f3f9) ([#13216](https://github.com/yt-dlp/yt-dlp/issues/13216)) by [bashonly](https://github.com/bashonly)
+- **wat.tv**: [Improve error handling](https://github.com/yt-dlp/yt-dlp/commit/f123cc83b3aea45053f5fa1d9141048b01fc2774) ([#13111](https://github.com/yt-dlp/yt-dlp/issues/13111)) by [bashonly](https://github.com/bashonly)
+- **weverse**: [Fix live extraction](https://github.com/yt-dlp/yt-dlp/commit/5328eda8820cc5f21dcf917684d23fbdca41831d) ([#13084](https://github.com/yt-dlp/yt-dlp/issues/13084)) by [bashonly](https://github.com/bashonly)
+- **xinpianchang**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/83fabf352489d52843f67e6e9cc752db86d27e6e) ([#13245](https://github.com/yt-dlp/yt-dlp/issues/13245)) by [garret1317](https://github.com/garret1317)
+- **youtube**
+    - [Add PO token support for subtitles](https://github.com/yt-dlp/yt-dlp/commit/32ed5f107c6c641958d1cd2752e130de4db55a13) ([#13234](https://github.com/yt-dlp/yt-dlp/issues/13234)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz)
+    - [Add `web_embedded` client for age-restricted videos](https://github.com/yt-dlp/yt-dlp/commit/0feec6dc131f488428bf881519e7c69766fbb9ae) ([#13089](https://github.com/yt-dlp/yt-dlp/issues/13089)) by [bashonly](https://github.com/bashonly)
+    - [Add a PO Token Provider Framework](https://github.com/yt-dlp/yt-dlp/commit/2685654a37141cca63eda3a92da0e2706e23ccfd) ([#12840](https://github.com/yt-dlp/yt-dlp/issues/12840)) by [coletdjnz](https://github.com/coletdjnz)
+    - [Extract `media_type` for all videos](https://github.com/yt-dlp/yt-dlp/commit/ded11ebc9afba6ba33923375103e9be2d7c804e7) ([#13136](https://github.com/yt-dlp/yt-dlp/issues/13136)) by [bashonly](https://github.com/bashonly)
+    - [Fix `--live-from-start` support for premieres](https://github.com/yt-dlp/yt-dlp/commit/8f303afb43395be360cafd7ad4ce2b6e2eedfb8a) ([#13079](https://github.com/yt-dlp/yt-dlp/issues/13079)) by [arabcoders](https://github.com/arabcoders)
+    - [Fix geo-restriction error handling](https://github.com/yt-dlp/yt-dlp/commit/c7e575e31608c19c5b26c10a4229db89db5fc9a8) ([#13217](https://github.com/yt-dlp/yt-dlp/issues/13217)) by [yozel](https://github.com/yozel)
+
+#### Misc. changes
+- **build**
+    - [Bump PyInstaller to v6.13.0](https://github.com/yt-dlp/yt-dlp/commit/17cf9088d0d535e4a7feffbf02bd49cd9dae5ab9) ([#13082](https://github.com/yt-dlp/yt-dlp/issues/13082)) by [bashonly](https://github.com/bashonly)
+    - [Bump run-on-arch-action to v3](https://github.com/yt-dlp/yt-dlp/commit/9064d2482d1fe722bbb4a49731fe0711c410d1c8) ([#13088](https://github.com/yt-dlp/yt-dlp/issues/13088)) by [bashonly](https://github.com/bashonly)
+- **cleanup**: Miscellaneous: [7977b32](https://github.com/yt-dlp/yt-dlp/commit/7977b329ed97b216e37bd402f4935f28c00eac9e) by [bashonly](https://github.com/bashonly)
+
 ### 2025.04.30
 
 #### Important changes

README.md

@@ -44,6 +44,7 @@ yt-dlp is a feature-rich command-line audio/video downloader with support for [t
     * [Post-processing Options](#post-processing-options)
     * [SponsorBlock Options](#sponsorblock-options)
     * [Extractor Options](#extractor-options)
+    * [Preset Aliases](#preset-aliases)
 * [CONFIGURATION](#configuration)
     * [Configuration file encoding](#configuration-file-encoding)
     * [Authentication with netrc](#authentication-with-netrc)
@@ -348,8 +349,8 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
     --no-flat-playlist              Fully extract the videos of a playlist
                                     (default)
     --live-from-start               Download livestreams from the start.
-                                    Currently only supported for YouTube
-                                    (Experimental)
+                                    Currently experimental and only supported
+                                    for YouTube and Twitch
     --no-live-from-start            Download livestreams from the current time
                                     (default)
     --wait-for-video MIN[-MAX]      Wait for scheduled streams to become
@@ -375,12 +376,12 @@ If you fork the project on GitHub, you can run your fork's [build workflow](.git
                                     an alias starts with a dash "-", it is
                                     prefixed with "--". Arguments are parsed
                                     according to the Python string formatting
-                                    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
-                                    "-S=aext:ARG0,abr -x --audio-format ARG0".
-                                    All defined aliases are listed in the --help
+                                    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 "-S
+                                    aext:ARG0,abr -x --audio-format ARG0". All
+                                    defined aliases are listed in the --help
                                     output. Alias options can trigger more
                                     aliases; so be careful to avoid defining
                                     recursive options. As a safety measure, each
@@ -1105,6 +1106,10 @@ Make chapter entries for, or remove various segments (sponsor,
                                     arguments for different extractors
 
 ## Preset Aliases:
+Predefined aliases for convenience and ease of use. Note that future
+    versions of yt-dlp may add or adjust presets, but the existing preset
+    names will not be changed or removed
+
     -t mp3                          -f 'ba[acodec^=mp3]/ba/b' -x --audio-format
                                     mp3
 
@@ -1792,9 +1797,10 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `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 currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
+* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
 * `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), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
+* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`
 * `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
@@ -1804,8 +1810,12 @@ The following extractors use this feature:
 * `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
 * `data_sync_id`: Overrides the account Data Sync ID used in Innertube API requests. This may be needed if you are using an account with `youtube:player_skip=webpage,configs` or `youtubetab:skip=webpage`
 * `visitor_data`: Overrides the Visitor Data used in Innertube API requests. This should be used with `player_skip=webpage,configs` and without cookies. Note: this may have adverse effects if used improperly. If a session from a browser is wanted, you should pass cookies instead (which contain the Visitor ID)
-* `po_token`:  Proof of Origin (PO) Token(s) to use. Comma seperated list of PO Tokens in the format `CLIENT.CONTEXT+PO_TOKEN`, e.g. `youtube:po_token=web.gvs+XXX,web.player=XXX,web_safari.gvs+YYY`. Context can be either `gvs` (Google Video Server URLs) or `player` (Innertube player request)
-* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`
+* `po_token`:  Proof of Origin (PO) Token(s) to use. Comma seperated list of PO Tokens in the format `CLIENT.CONTEXT+PO_TOKEN`, e.g. `youtube:po_token=web.gvs+XXX,web.player=XXX,web_safari.gvs+YYY`. Context can be any of `gvs` (Google Video Server URLs), `player` (Innertube player request) or `subs` (Subtitles)
+* `pot_trace`: Enable debug logging for PO Token fetching. Either `true` or `false` (default)
+* `fetch_pot`: Policy to use for fetching a PO Token from providers. One of `always` (always try fetch a PO Token regardless if the client requires one for the given context), `never` (never fetch a PO Token), or `auto` (default; only fetch a PO Token if the client requires one for the given context)
+
+#### youtubepot-webpo
+* `bind_to_visitor_id`: Whether to use the Visitor ID instead of Visitor Data for caching WebPO tokens. Either `true` (default) or `false`
 
 #### youtubetab (YouTube playlists, channels, feeds, etc.)
 * `skip`: One or more of `webpage` (skip initial webpage download), `authcheck` (allow the download of playlists requiring authentication when no initial webpage is downloaded. This may cause unwanted behavior, see [#1122](https://github.com/yt-dlp/yt-dlp/pull/1122) for more details)

pyproject.toml

@@ -82,7 +82,7 @@ test = [
     "pytest-rerunfailures~=14.0",
 ]
 pyinstaller = [
-    "pyinstaller>=6.11.1",  # Windows temp cleanup fixed in 6.11.1
+    "pyinstaller>=6.13.0",  # Windows temp cleanup fixed in 6.13.0
 ]
 
 [project.urls]

supportedsites.md

@@ -246,7 +246,6 @@ The only reliable way to check if a site is supported is to try it.
  - **Canalplus**: mycanal.fr and piwiplus.fr
  - **Canalsurmas**
  - **CaracolTvPlay**: [*caracoltv-play*](## "netrc machine")
- - **CartoonNetwork**
  - **cbc.ca**
  - **cbc.ca:player**
  - **cbc.ca:​player:playlist**
@@ -649,7 +648,10 @@ The only reliable way to check if a site is supported is to try it.
  - **jiocinema**: [*jiocinema*](## "netrc machine")
  - **jiocinema:series**: [*jiocinema*](## "netrc machine")
  - **jiosaavn:album**
+ - **jiosaavn:artist**
  - **jiosaavn:playlist**
+ - **jiosaavn:show**
+ - **jiosaavn:​show:playlist**
  - **jiosaavn:song**
  - **Joj**
  - **JoqrAg**: 超!A&G+ 文化放送 (f.k.a. AGQR) Nippon Cultural Broadcasting, Inc. (JOQR)
@@ -1081,8 +1083,8 @@ The only reliable way to check if a site is supported is to try it.
  - **Photobucket**
  - **PiaLive**
  - **Piapro**: [*piapro*](## "netrc machine")
- - **Picarto**
- - **PicartoVod**
+ - **picarto**
+ - **picarto:vod**
  - **Piksel**
  - **Pinkbike**
  - **Pinterest**
@@ -1390,7 +1392,6 @@ The only reliable way to check if a site is supported is to try it.
  - **Spreaker**
  - **SpreakerShow**
  - **SpringboardPlatform**
- - **Sprout**
  - **SproutVideo**
  - **sr:mediathek**: Saarländischer Rundfunk (**Currently broken**)
  - **SRGSSR**
@@ -1656,6 +1657,7 @@ The only reliable way to check if a site is supported is to try it.
  - **vimeo**: [*vimeo*](## "netrc machine")
  - **vimeo:album**: [*vimeo*](## "netrc machine")
  - **vimeo:channel**: [*vimeo*](## "netrc machine")
+ - **vimeo:event**: [*vimeo*](## "netrc machine")
  - **vimeo:group**: [*vimeo*](## "netrc machine")
  - **vimeo:likes**: [*vimeo*](## "netrc machine") Vimeo user likes
  - **vimeo:ondemand**: [*vimeo*](## "netrc machine")

test/test_YoutubeDL.py

@@ -1435,6 +1435,27 @@ class TestYoutubeDL(unittest.TestCase):
         FakeYDL().close()
         assert all_plugins_loaded.value
 
+    def test_close_hooks(self):
+        # Should call all registered close hooks on close
+        close_hook_called = False
+        close_hook_two_called = False
+
+        def close_hook():
+            nonlocal close_hook_called
+            close_hook_called = True
+
+        def close_hook_two():
+            nonlocal close_hook_two_called
+            close_hook_two_called = True
+
+        ydl = FakeYDL()
+        ydl.add_close_hook(close_hook)
+        ydl.add_close_hook(close_hook_two)
+
+        ydl.close()
+        self.assertTrue(close_hook_called, 'Close hook was not called')
+        self.assertTrue(close_hook_two_called, 'Close hook two was not called')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_cookies.py

@@ -58,6 +58,14 @@ class TestCookies(unittest.TestCase):
             ({'DESKTOP_SESSION': 'kde'}, _LinuxDesktopEnvironment.KDE3),
             ({'DESKTOP_SESSION': 'xfce'}, _LinuxDesktopEnvironment.XFCE),
 
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'gnome'}, _LinuxDesktopEnvironment.GNOME),
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'mate'}, _LinuxDesktopEnvironment.GNOME),
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'kde4'}, _LinuxDesktopEnvironment.KDE4),
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'kde'}, _LinuxDesktopEnvironment.KDE3),
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'xfce'}, _LinuxDesktopEnvironment.XFCE),
+
+            ({'XDG_CURRENT_DESKTOP': 'my_custom_de', 'DESKTOP_SESSION': 'my_custom_de', 'GNOME_DESKTOP_SESSION_ID': 1}, _LinuxDesktopEnvironment.GNOME),
+
             ({'GNOME_DESKTOP_SESSION_ID': 1}, _LinuxDesktopEnvironment.GNOME),
             ({'KDE_FULL_SESSION': 1}, _LinuxDesktopEnvironment.KDE3),
             ({'KDE_FULL_SESSION': 1, 'DESKTOP_SESSION': 'kde4'}, _LinuxDesktopEnvironment.KDE4),

test/test_jsinterp.py

@@ -478,6 +478,14 @@ class TestJSInterpreter(unittest.TestCase):
         func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
         self.assertEqual(func([1]), 1111)
 
+    def test_increment_decrement(self):
+        self._test('function f() { var x = 1; return ++x; }', 2)
+        self._test('function f() { var x = 1; return x++; }', 1)
+        self._test('function f() { var x = 1; x--; return x }', 0)
+        self._test('function f() { var y; var x = 1; x++, --x, x--, x--, y="z", "abc", x++; return --x }', -1)
+        self._test('function f() { var a = "test--"; return a; }', 'test--')
+        self._test('function f() { var b = 1; var a = "b--"; return a; }', 'b--')
+
 
 if __name__ == '__main__':
     unittest.main()

test/test_networking_utils.py

@@ -20,7 +20,6 @@ from yt_dlp.networking._helper import (
     add_accept_encoding_header,
     get_redirect_method,
     make_socks_proxy_opts,
-    select_proxy,
     ssl_load_certs,
 )
 from yt_dlp.networking.exceptions import (
@@ -28,7 +27,7 @@ from yt_dlp.networking.exceptions import (
     IncompleteRead,
 )
 from yt_dlp.socks import ProxyType
-from yt_dlp.utils.networking import HTTPHeaderDict
+from yt_dlp.utils.networking import HTTPHeaderDict, select_proxy
 
 TEST_DIR = os.path.dirname(os.path.abspath(__file__))
 

test/test_pot/conftest.py

@@ -0,0 +1,71 @@
+import collections
+
+import pytest
+
+from yt_dlp import YoutubeDL
+from yt_dlp.cookies import YoutubeDLCookieJar
+from yt_dlp.extractor.common import InfoExtractor
+from yt_dlp.extractor.youtube.pot._provider import IEContentProviderLogger
+from yt_dlp.extractor.youtube.pot.provider import PoTokenRequest, PoTokenContext
+from yt_dlp.utils.networking import HTTPHeaderDict
+
+
+class MockLogger(IEContentProviderLogger):
+
+    log_level = IEContentProviderLogger.LogLevel.TRACE
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        self.messages = collections.defaultdict(list)
+
+    def trace(self, message: str):
+        self.messages['trace'].append(message)
+
+    def debug(self, message: str):
+        self.messages['debug'].append(message)
+
+    def info(self, message: str):
+        self.messages['info'].append(message)
+
+    def warning(self, message: str, *, once=False):
+        self.messages['warning'].append(message)
+
+    def error(self, message: str):
+        self.messages['error'].append(message)
+
+
+@pytest.fixture
+def ie() -> InfoExtractor:
+    ydl = YoutubeDL()
+    return ydl.get_info_extractor('Youtube')
+
+
+@pytest.fixture
+def logger() -> MockLogger:
+    return MockLogger()
+
+
+@pytest.fixture()
+def pot_request() -> PoTokenRequest:
+    return PoTokenRequest(
+        context=PoTokenContext.GVS,
+        innertube_context={'client': {'clientName': 'WEB'}},
+        innertube_host='youtube.com',
+        session_index=None,
+        player_url=None,
+        is_authenticated=False,
+        video_webpage=None,
+
+        visitor_data='example-visitor-data',
+        data_sync_id='example-data-sync-id',
+        video_id='example-video-id',
+
+        request_cookiejar=YoutubeDLCookieJar(),
+        request_proxy=None,
+        request_headers=HTTPHeaderDict(),
+        request_timeout=None,
+        request_source_address=None,
+        request_verify_tls=True,
+
+        bypass_cache=False,
+    )

test/test_pot/test_pot_builtin_memorycache.py

@@ -0,0 +1,117 @@
+import threading
+import time
+from collections import OrderedDict
+import pytest
+from yt_dlp.extractor.youtube.pot._provider import IEContentProvider, BuiltinIEContentProvider
+from yt_dlp.utils import bug_reports_message
+from yt_dlp.extractor.youtube.pot._builtin.memory_cache import MemoryLRUPCP, memorylru_preference, initialize_global_cache
+from yt_dlp.version import __version__
+from yt_dlp.extractor.youtube.pot._registry import _pot_cache_providers, _pot_memory_cache
+
+
+class TestMemoryLRUPCS:
+
+    def test_base_type(self):
+        assert issubclass(MemoryLRUPCP, IEContentProvider)
+        assert issubclass(MemoryLRUPCP, BuiltinIEContentProvider)
+
+    @pytest.fixture
+    def pcp(self, ie, logger) -> MemoryLRUPCP:
+        return MemoryLRUPCP(ie, logger, {}, initialize_cache=lambda max_size: (OrderedDict(), threading.Lock(), max_size))
+
+    def test_is_registered(self):
+        assert _pot_cache_providers.value.get('MemoryLRU') == MemoryLRUPCP
+
+    def test_initialization(self, pcp):
+        assert pcp.PROVIDER_NAME == 'memory'
+        assert pcp.PROVIDER_VERSION == __version__
+        assert pcp.BUG_REPORT_MESSAGE == bug_reports_message(before='')
+        assert pcp.is_available()
+
+    def test_store_and_get(self, pcp):
+        pcp.store('key1', 'value1', int(time.time()) + 60)
+        assert pcp.get('key1') == 'value1'
+        assert len(pcp.cache) == 1
+
+    def test_store_ignore_expired(self, pcp):
+        pcp.store('key1', 'value1', int(time.time()) - 1)
+        assert len(pcp.cache) == 0
+        assert pcp.get('key1') is None
+        assert len(pcp.cache) == 0
+
+    def test_store_override_existing_key(self, ie, logger):
+        MAX_SIZE = 2
+        pcp = MemoryLRUPCP(ie, logger, {}, initialize_cache=lambda max_size: (OrderedDict(), threading.Lock(), MAX_SIZE))
+        pcp.store('key1', 'value1', int(time.time()) + 60)
+        pcp.store('key2', 'value2', int(time.time()) + 60)
+        assert len(pcp.cache) == 2
+        pcp.store('key1', 'value2', int(time.time()) + 60)
+        # Ensure that the override key gets added to the end of the cache instead of in the same position
+        pcp.store('key3', 'value3', int(time.time()) + 60)
+        assert pcp.get('key1') == 'value2'
+
+    def test_store_ignore_expired_existing_key(self, pcp):
+        pcp.store('key1', 'value2', int(time.time()) + 60)
+        pcp.store('key1', 'value1', int(time.time()) - 1)
+        assert len(pcp.cache) == 1
+        assert pcp.get('key1') == 'value2'
+        assert len(pcp.cache) == 1
+
+    def test_get_key_expired(self, pcp):
+        pcp.store('key1', 'value1', int(time.time()) + 60)
+        assert pcp.get('key1') == 'value1'
+        assert len(pcp.cache) == 1
+        pcp.cache['key1'] = ('value1', int(time.time()) - 1)
+        assert pcp.get('key1') is None
+        assert len(pcp.cache) == 0
+
+    def test_lru_eviction(self, ie, logger):
+        MAX_SIZE = 2
+        provider = MemoryLRUPCP(ie, logger, {}, initialize_cache=lambda max_size: (OrderedDict(), threading.Lock(), MAX_SIZE))
+        provider.store('key1', 'value1', int(time.time()) + 5)
+        provider.store('key2', 'value2', int(time.time()) + 5)
+        assert len(provider.cache) == 2
+
+        assert provider.get('key1') == 'value1'
+
+        provider.store('key3', 'value3', int(time.time()) + 5)
+        assert len(provider.cache) == 2
+
+        assert provider.get('key2') is None
+
+        provider.store('key4', 'value4', int(time.time()) + 5)
+        assert len(provider.cache) == 2
+
+        assert provider.get('key1') is None
+        assert provider.get('key3') == 'value3'
+        assert provider.get('key4') == 'value4'
+
+    def test_delete(self, pcp):
+        pcp.store('key1', 'value1', int(time.time()) + 5)
+        assert len(pcp.cache) == 1
+        assert pcp.get('key1') == 'value1'
+        pcp.delete('key1')
+        assert len(pcp.cache) == 0
+        assert pcp.get('key1') is None
+
+    def test_use_global_cache_default(self, ie, logger):
+        pcp = MemoryLRUPCP(ie, logger, {})
+        assert pcp.max_size == _pot_memory_cache.value['max_size'] == 25
+        assert pcp.cache is _pot_memory_cache.value['cache']
+        assert pcp.lock is _pot_memory_cache.value['lock']
+
+        pcp2 = MemoryLRUPCP(ie, logger, {})
+        assert pcp.max_size == pcp2.max_size == _pot_memory_cache.value['max_size'] == 25
+        assert pcp.cache is pcp2.cache is _pot_memory_cache.value['cache']
+        assert pcp.lock is pcp2.lock is _pot_memory_cache.value['lock']
+
+    def test_fail_max_size_change_global(self, ie, logger):
+        pcp = MemoryLRUPCP(ie, logger, {})
+        assert pcp.max_size == _pot_memory_cache.value['max_size'] == 25
+        with pytest.raises(ValueError, match='Cannot change max_size of initialized global memory cache'):
+            initialize_global_cache(50)
+
+        assert pcp.max_size == _pot_memory_cache.value['max_size'] == 25
+
+    def test_memory_lru_preference(self, pcp, ie, pot_request):
+        assert memorylru_preference(pcp, pot_request) == 10000

test/test_pot/test_pot_builtin_utils.py

@@ -0,0 +1,47 @@
+import pytest
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenContext,
+
+)
+
+from yt_dlp.extractor.youtube.pot.utils import get_webpo_content_binding, ContentBindingType
+
+
+class TestGetWebPoContentBinding:
+
+    @pytest.mark.parametrize('client_name, context, is_authenticated, expected', [
+        *[(client, context, is_authenticated, expected) for client in [
+            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
+          for context, is_authenticated, expected in [
+            (PoTokenContext.GVS, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
+            (PoTokenContext.PLAYER, False, ('example-video-id', ContentBindingType.VIDEO_ID)),
+            (PoTokenContext.SUBS, False, ('example-video-id', ContentBindingType.VIDEO_ID)),
+            (PoTokenContext.GVS, True, ('example-data-sync-id', ContentBindingType.DATASYNC_ID)),
+        ]],
+        ('WEB_REMIX', PoTokenContext.GVS, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
+        ('WEB_REMIX', PoTokenContext.PLAYER, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
+        ('ANDROID', PoTokenContext.GVS, False, (None, None)),
+        ('IOS', PoTokenContext.GVS, False, (None, None)),
+    ])
+    def test_get_webpo_content_binding(self, pot_request, client_name, context, is_authenticated, expected):
+        pot_request.innertube_context['client']['clientName'] = client_name
+        pot_request.context = context
+        pot_request.is_authenticated = is_authenticated
+        assert get_webpo_content_binding(pot_request) == expected
+
+    def test_extract_visitor_id(self, pot_request):
+        pot_request.visitor_data = 'CgsxMjNhYmNYWVpfLSiA4s%2DqBg%3D%3D'
+        assert get_webpo_content_binding(pot_request, bind_to_visitor_id=True) == ('123abcXYZ_-', ContentBindingType.VISITOR_ID)
+
+    def test_invalid_visitor_id(self, pot_request):
+        # visitor id not alphanumeric (i.e. protobuf extraction failed)
+        pot_request.visitor_data = 'CggxMjM0NTY3OCiA4s-qBg%3D%3D'
+        assert get_webpo_content_binding(pot_request, bind_to_visitor_id=True) == (pot_request.visitor_data, ContentBindingType.VISITOR_DATA)
+
+    def test_no_visitor_id(self, pot_request):
+        pot_request.visitor_data = 'KIDiz6oG'
+        assert get_webpo_content_binding(pot_request, bind_to_visitor_id=True) == (pot_request.visitor_data, ContentBindingType.VISITOR_DATA)
+
+    def test_invalid_base64(self, pot_request):
+        pot_request.visitor_data = 'invalid-base64'
+        assert get_webpo_content_binding(pot_request, bind_to_visitor_id=True) == (pot_request.visitor_data, ContentBindingType.VISITOR_DATA)

test/test_pot/test_pot_builtin_webpospec.py

@@ -0,0 +1,92 @@
+import pytest
+
+from yt_dlp.extractor.youtube.pot._provider import IEContentProvider, BuiltinIEContentProvider
+from yt_dlp.extractor.youtube.pot.cache import CacheProviderWritePolicy
+from yt_dlp.utils import bug_reports_message
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenRequest,
+    PoTokenContext,
+
+)
+from yt_dlp.version import __version__
+
+from yt_dlp.extractor.youtube.pot._builtin.webpo_cachespec import WebPoPCSP
+from yt_dlp.extractor.youtube.pot._registry import _pot_pcs_providers
+
+
+@pytest.fixture()
+def pot_request(pot_request) -> PoTokenRequest:
+    pot_request.visitor_data = 'CgsxMjNhYmNYWVpfLSiA4s%2DqBg%3D%3D'  # visitor_id=123abcXYZ_-
+    return pot_request
+
+
+class TestWebPoPCSP:
+    def test_base_type(self):
+        assert issubclass(WebPoPCSP, IEContentProvider)
+        assert issubclass(WebPoPCSP, BuiltinIEContentProvider)
+
+    def test_init(self, ie, logger):
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={})
+        assert pcs.PROVIDER_NAME == 'webpo'
+        assert pcs.PROVIDER_VERSION == __version__
+        assert pcs.BUG_REPORT_MESSAGE == bug_reports_message(before='')
+        assert pcs.is_available()
+
+    def test_is_registered(self):
+        assert _pot_pcs_providers.value.get('WebPo') == WebPoPCSP
+
+    @pytest.mark.parametrize('client_name, context, is_authenticated', [
+        ('ANDROID', PoTokenContext.GVS, False),
+        ('IOS', PoTokenContext.GVS, False),
+        ('IOS', PoTokenContext.PLAYER, False),
+    ])
+    def test_not_supports(self, ie, logger, pot_request, client_name, context, is_authenticated):
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={})
+        pot_request.innertube_context['client']['clientName'] = client_name
+        pot_request.context = context
+        pot_request.is_authenticated = is_authenticated
+        assert pcs.generate_cache_spec(pot_request) is None
+
+    @pytest.mark.parametrize('client_name, context, is_authenticated, remote_host, source_address, request_proxy, expected', [
+        *[(client, context, is_authenticated, remote_host, source_address, request_proxy, expected) for client in [
+            'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
+          for context, is_authenticated, remote_host, source_address, request_proxy, expected in [
+            (PoTokenContext.GVS, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id'}),
+            (PoTokenContext.PLAYER, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'video_id'}),
+            (PoTokenContext.GVS, True, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': 'example-data-sync-id', 'cbt': 'datasync_id'}),
+        ]],
+        ('WEB_REMIX', PoTokenContext.PLAYER, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id'}),
+        ('WEB', PoTokenContext.GVS, False, None, None, None, {'t': 'webpo', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id', 'ip': None, 'sa': None, 'px': None}),
+        ('TVHTML5', PoTokenContext.PLAYER, False, None, None, 'http://example.com', {'t': 'webpo', 'cb': '123abcXYZ_-', 'cbt': 'video_id', 'ip': None, 'sa': None, 'px': 'http://example.com'}),
+
+    ])
+    def test_generate_key_bindings(self, ie, logger, pot_request, client_name, context, is_authenticated, remote_host, source_address, request_proxy, expected):
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={})
+        pot_request.innertube_context['client']['clientName'] = client_name
+        pot_request.context = context
+        pot_request.is_authenticated = is_authenticated
+        pot_request.innertube_context['client']['remoteHost'] = remote_host
+        pot_request.request_source_address = source_address
+        pot_request.request_proxy = request_proxy
+        pot_request.video_id = '123abcXYZ_-'  # same as visitor id to test type
+
+        assert pcs.generate_cache_spec(pot_request).key_bindings == expected
+
+    def test_no_bind_visitor_id(self, ie, logger, pot_request):
+        # Should not bind to visitor id if setting is set to False
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={'bind_to_visitor_id': ['false']})
+        pot_request.innertube_context['client']['clientName'] = 'WEB'
+        pot_request.context = PoTokenContext.GVS
+        pot_request.is_authenticated = False
+        assert pcs.generate_cache_spec(pot_request).key_bindings == {'t': 'webpo', 'ip': None, 'sa': None, 'px': None, 'cb': 'CgsxMjNhYmNYWVpfLSiA4s%2DqBg%3D%3D', 'cbt': 'visitor_data'}
+
+    def test_default_ttl(self, ie, logger, pot_request):
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={})
+        assert pcs.generate_cache_spec(pot_request).default_ttl == 6 * 60 * 60  # should default to 6 hours
+
+    def test_write_policy(self, ie, logger, pot_request):
+        pcs = WebPoPCSP(ie=ie, logger=logger, settings={})
+        pot_request.context = PoTokenContext.GVS
+        assert pcs.generate_cache_spec(pot_request).write_policy == CacheProviderWritePolicy.WRITE_ALL
+        pot_request.context = PoTokenContext.PLAYER
+        assert pcs.generate_cache_spec(pot_request).write_policy == CacheProviderWritePolicy.WRITE_FIRST

test/test_pot/test_pot_framework.py

@@ -0,0 +1,629 @@
+import pytest
+
+from yt_dlp.extractor.youtube.pot._provider import IEContentProvider
+from yt_dlp.cookies import YoutubeDLCookieJar
+from yt_dlp.utils.networking import HTTPHeaderDict
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenRequest,
+    PoTokenContext,
+    ExternalRequestFeature,
+
+)
+
+from yt_dlp.extractor.youtube.pot.cache import (
+    PoTokenCacheProvider,
+    PoTokenCacheSpec,
+    PoTokenCacheSpecProvider,
+    CacheProviderWritePolicy,
+)
+
+import yt_dlp.extractor.youtube.pot.cache as cache
+
+from yt_dlp.networking import Request
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenResponse,
+    PoTokenProvider,
+    PoTokenProviderRejectedRequest,
+    provider_bug_report_message,
+    register_provider,
+    register_preference,
+)
+
+from yt_dlp.extractor.youtube.pot._registry import _pot_providers, _ptp_preferences, _pot_pcs_providers, _pot_cache_providers, _pot_cache_provider_preferences
+
+
+class ExamplePTP(PoTokenProvider):
+    PROVIDER_NAME = 'example'
+    PROVIDER_VERSION = '0.0.1'
+    BUG_REPORT_LOCATION = 'https://example.com/issues'
+
+    _SUPPORTED_CLIENTS = ('WEB',)
+    _SUPPORTED_CONTEXTS = (PoTokenContext.GVS, )
+
+    _SUPPORTED_EXTERNAL_REQUEST_FEATURES = (
+        ExternalRequestFeature.PROXY_SCHEME_HTTP,
+        ExternalRequestFeature.PROXY_SCHEME_SOCKS5H,
+    )
+
+    def is_available(self) -> bool:
+        return True
+
+    def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+        return PoTokenResponse('example-token', expires_at=123)
+
+
+class ExampleCacheProviderPCP(PoTokenCacheProvider):
+
+    PROVIDER_NAME = 'example'
+    PROVIDER_VERSION = '0.0.1'
+    BUG_REPORT_LOCATION = 'https://example.com/issues'
+
+    def is_available(self) -> bool:
+        return True
+
+    def get(self, key: str):
+        return 'example-cache'
+
+    def store(self, key: str, value: str, expires_at: int):
+        pass
+
+    def delete(self, key: str):
+        pass
+
+
+class ExampleCacheSpecProviderPCSP(PoTokenCacheSpecProvider):
+
+    PROVIDER_NAME = 'example'
+    PROVIDER_VERSION = '0.0.1'
+    BUG_REPORT_LOCATION = 'https://example.com/issues'
+
+    def generate_cache_spec(self, request: PoTokenRequest):
+        return PoTokenCacheSpec(
+            key_bindings={'field': 'example-key'},
+            default_ttl=60,
+            write_policy=CacheProviderWritePolicy.WRITE_FIRST,
+        )
+
+
+class TestPoTokenProvider:
+
+    def test_base_type(self):
+        assert issubclass(PoTokenProvider, IEContentProvider)
+
+    def test_create_provider_missing_fetch_method(self, ie, logger):
+        class MissingMethodsPTP(PoTokenProvider):
+            def is_available(self) -> bool:
+                return True
+
+        with pytest.raises(TypeError):
+            MissingMethodsPTP(ie=ie, logger=logger, settings={})
+
+    def test_create_provider_missing_available_method(self, ie, logger):
+        class MissingMethodsPTP(PoTokenProvider):
+            def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+                raise PoTokenProviderRejectedRequest('Not implemented')
+
+        with pytest.raises(TypeError):
+            MissingMethodsPTP(ie=ie, logger=logger, settings={})
+
+    def test_barebones_provider(self, ie, logger):
+        class BarebonesProviderPTP(PoTokenProvider):
+            def is_available(self) -> bool:
+                return True
+
+            def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+                raise PoTokenProviderRejectedRequest('Not implemented')
+
+        provider = BarebonesProviderPTP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'BarebonesProvider'
+        assert provider.PROVIDER_KEY == 'BarebonesProvider'
+        assert provider.PROVIDER_VERSION == '0.0.0'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  (developer has not provided a bug report location)  .'
+
+    def test_example_provider_success(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'example'
+        assert provider.PROVIDER_KEY == 'Example'
+        assert provider.PROVIDER_VERSION == '0.0.1'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  https://example.com/issues  .'
+        assert provider.is_available()
+
+        response = provider.request_pot(pot_request)
+
+        assert response.po_token == 'example-token'
+        assert response.expires_at == 123
+
+    def test_provider_unsupported_context(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+        pot_request.context = PoTokenContext.PLAYER
+
+        with pytest.raises(PoTokenProviderRejectedRequest):
+            provider.request_pot(pot_request)
+
+    def test_provider_unsupported_client(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+        pot_request.innertube_context['client']['clientName'] = 'ANDROID'
+
+        with pytest.raises(PoTokenProviderRejectedRequest):
+            provider.request_pot(pot_request)
+
+    def test_provider_unsupported_proxy_scheme(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+        pot_request.request_proxy = 'socks4://example.com'
+
+        with pytest.raises(
+            PoTokenProviderRejectedRequest,
+            match='External requests by "example" provider do not support proxy scheme "socks4". Supported proxy '
+            'schemes: http, socks5h',
+        ):
+            provider.request_pot(pot_request)
+
+        pot_request.request_proxy = 'http://example.com'
+
+        assert provider.request_pot(pot_request)
+
+    def test_provider_ignore_external_request_features(self, ie, logger, pot_request):
+        class InternalPTP(ExamplePTP):
+            _SUPPORTED_EXTERNAL_REQUEST_FEATURES = None
+
+        provider = InternalPTP(ie=ie, logger=logger, settings={})
+
+        pot_request.request_proxy = 'socks5://example.com'
+        assert provider.request_pot(pot_request)
+        pot_request.request_source_address = '0.0.0.0'
+        assert provider.request_pot(pot_request)
+
+    def test_provider_unsupported_external_request_source_address(self, ie, logger, pot_request):
+        class InternalPTP(ExamplePTP):
+            _SUPPORTED_EXTERNAL_REQUEST_FEATURES = tuple()
+
+        provider = InternalPTP(ie=ie, logger=logger, settings={})
+
+        pot_request.request_source_address = None
+        assert provider.request_pot(pot_request)
+
+        pot_request.request_source_address = '0.0.0.0'
+        with pytest.raises(
+            PoTokenProviderRejectedRequest,
+            match='External requests by "example" provider do not support setting source address',
+        ):
+            provider.request_pot(pot_request)
+
+    def test_provider_supported_external_request_source_address(self, ie, logger, pot_request):
+        class InternalPTP(ExamplePTP):
+            _SUPPORTED_EXTERNAL_REQUEST_FEATURES = (
+                ExternalRequestFeature.SOURCE_ADDRESS,
+            )
+
+        provider = InternalPTP(ie=ie, logger=logger, settings={})
+
+        pot_request.request_source_address = None
+        assert provider.request_pot(pot_request)
+
+        pot_request.request_source_address = '0.0.0.0'
+        assert provider.request_pot(pot_request)
+
+    def test_provider_unsupported_external_request_tls_verification(self, ie, logger, pot_request):
+        class InternalPTP(ExamplePTP):
+            _SUPPORTED_EXTERNAL_REQUEST_FEATURES = tuple()
+
+        provider = InternalPTP(ie=ie, logger=logger, settings={})
+
+        pot_request.request_verify_tls = True
+        assert provider.request_pot(pot_request)
+
+        pot_request.request_verify_tls = False
+        with pytest.raises(
+            PoTokenProviderRejectedRequest,
+            match='External requests by "example" provider do not support ignoring TLS certificate failures',
+        ):
+            provider.request_pot(pot_request)
+
+    def test_provider_supported_external_request_tls_verification(self, ie, logger, pot_request):
+        class InternalPTP(ExamplePTP):
+            _SUPPORTED_EXTERNAL_REQUEST_FEATURES = (
+                ExternalRequestFeature.DISABLE_TLS_VERIFICATION,
+            )
+
+        provider = InternalPTP(ie=ie, logger=logger, settings={})
+
+        pot_request.request_verify_tls = True
+        assert provider.request_pot(pot_request)
+
+        pot_request.request_verify_tls = False
+        assert provider.request_pot(pot_request)
+
+    def test_provider_request_webpage(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+
+        cookiejar = YoutubeDLCookieJar()
+        pot_request.request_headers = HTTPHeaderDict({'User-Agent': 'example-user-agent'})
+        pot_request.request_proxy = 'socks5://example-proxy.com'
+        pot_request.request_cookiejar = cookiejar
+
+        def mock_urlopen(request):
+            return request
+
+        ie._downloader.urlopen = mock_urlopen
+
+        sent_request = provider._request_webpage(Request(
+            'https://example.com',
+        ), pot_request=pot_request)
+
+        assert sent_request.url == 'https://example.com'
+        assert sent_request.headers['User-Agent'] == 'example-user-agent'
+        assert sent_request.proxies == {'all': 'socks5://example-proxy.com'}
+        assert sent_request.extensions['cookiejar'] is cookiejar
+        assert 'Requesting webpage' in logger.messages['info']
+
+    def test_provider_request_webpage_override(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+
+        cookiejar_request = YoutubeDLCookieJar()
+        pot_request.request_headers = HTTPHeaderDict({'User-Agent': 'example-user-agent'})
+        pot_request.request_proxy = 'socks5://example-proxy.com'
+        pot_request.request_cookiejar = cookiejar_request
+
+        def mock_urlopen(request):
+            return request
+
+        ie._downloader.urlopen = mock_urlopen
+
+        sent_request = provider._request_webpage(Request(
+            'https://example.com',
+            headers={'User-Agent': 'override-user-agent-override'},
+            proxies={'http': 'http://example-proxy-override.com'},
+            extensions={'cookiejar': YoutubeDLCookieJar()},
+        ), pot_request=pot_request, note='Custom requesting webpage')
+
+        assert sent_request.url == 'https://example.com'
+        assert sent_request.headers['User-Agent'] == 'override-user-agent-override'
+        assert sent_request.proxies == {'http': 'http://example-proxy-override.com'}
+        assert sent_request.extensions['cookiejar'] is not cookiejar_request
+        assert 'Custom requesting webpage' in logger.messages['info']
+
+    def test_provider_request_webpage_no_log(self, ie, logger, pot_request):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+
+        def mock_urlopen(request):
+            return request
+
+        ie._downloader.urlopen = mock_urlopen
+
+        sent_request = provider._request_webpage(Request(
+            'https://example.com',
+        ), note=False)
+
+        assert sent_request.url == 'https://example.com'
+        assert 'info' not in logger.messages
+
+    def test_provider_request_webpage_no_pot_request(self, ie, logger):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={})
+
+        def mock_urlopen(request):
+            return request
+
+        ie._downloader.urlopen = mock_urlopen
+
+        sent_request = provider._request_webpage(Request(
+            'https://example.com',
+        ), pot_request=None)
+
+        assert sent_request.url == 'https://example.com'
+
+    def test_get_config_arg(self, ie, logger):
+        provider = ExamplePTP(ie=ie, logger=logger, settings={'abc': ['123D'], 'xyz': ['456a', '789B']})
+
+        assert provider._configuration_arg('abc') == ['123d']
+        assert provider._configuration_arg('abc', default=['default']) == ['123d']
+        assert provider._configuration_arg('ABC', default=['default']) == ['default']
+        assert provider._configuration_arg('abc', casesense=True) == ['123D']
+        assert provider._configuration_arg('xyz', casesense=False) == ['456a', '789b']
+
+    def test_require_class_end_with_suffix(self, ie, logger):
+        class InvalidSuffix(PoTokenProvider):
+            PROVIDER_NAME = 'invalid-suffix'
+
+            def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+                raise PoTokenProviderRejectedRequest('Not implemented')
+
+            def is_available(self) -> bool:
+                return True
+
+        provider = InvalidSuffix(ie=ie, logger=logger, settings={})
+
+        with pytest.raises(AssertionError):
+            provider.PROVIDER_KEY  # noqa: B018
+
+
+class TestPoTokenCacheProvider:
+
+    def test_base_type(self):
+        assert issubclass(PoTokenCacheProvider, IEContentProvider)
+
+    def test_create_provider_missing_get_method(self, ie, logger):
+        class MissingMethodsPCP(PoTokenCacheProvider):
+            def store(self, key: str, value: str, expires_at: int):
+                pass
+
+            def delete(self, key: str):
+                pass
+
+                def is_available(self) -> bool:
+                    return True
+
+        with pytest.raises(TypeError):
+            MissingMethodsPCP(ie=ie, logger=logger, settings={})
+
+    def test_create_provider_missing_store_method(self, ie, logger):
+        class MissingMethodsPCP(PoTokenCacheProvider):
+            def get(self, key: str):
+                pass
+
+            def delete(self, key: str):
+                pass
+
+            def is_available(self) -> bool:
+                return True
+
+        with pytest.raises(TypeError):
+            MissingMethodsPCP(ie=ie, logger=logger, settings={})
+
+    def test_create_provider_missing_delete_method(self, ie, logger):
+        class MissingMethodsPCP(PoTokenCacheProvider):
+            def get(self, key: str):
+                pass
+
+            def store(self, key: str, value: str, expires_at: int):
+                pass
+
+            def is_available(self) -> bool:
+                return True
+
+        with pytest.raises(TypeError):
+            MissingMethodsPCP(ie=ie, logger=logger, settings={})
+
+    def test_create_provider_missing_is_available_method(self, ie, logger):
+        class MissingMethodsPCP(PoTokenCacheProvider):
+            def get(self, key: str):
+                pass
+
+            def store(self, key: str, value: str, expires_at: int):
+                pass
+
+            def delete(self, key: str):
+                pass
+
+        with pytest.raises(TypeError):
+            MissingMethodsPCP(ie=ie, logger=logger, settings={})
+
+    def test_barebones_provider(self, ie, logger):
+        class BarebonesProviderPCP(PoTokenCacheProvider):
+
+            def is_available(self) -> bool:
+                return True
+
+            def get(self, key: str):
+                return 'example-cache'
+
+            def store(self, key: str, value: str, expires_at: int):
+                pass
+
+            def delete(self, key: str):
+                pass
+
+        provider = BarebonesProviderPCP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'BarebonesProvider'
+        assert provider.PROVIDER_KEY == 'BarebonesProvider'
+        assert provider.PROVIDER_VERSION == '0.0.0'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  (developer has not provided a bug report location)  .'
+
+    def test_create_provider_example(self, ie, logger):
+        provider = ExampleCacheProviderPCP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'example'
+        assert provider.PROVIDER_KEY == 'ExampleCacheProvider'
+        assert provider.PROVIDER_VERSION == '0.0.1'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  https://example.com/issues  .'
+        assert provider.is_available()
+
+    def test_get_config_arg(self, ie, logger):
+        provider = ExampleCacheProviderPCP(ie=ie, logger=logger, settings={'abc': ['123D'], 'xyz': ['456a', '789B']})
+        assert provider._configuration_arg('abc') == ['123d']
+        assert provider._configuration_arg('abc', default=['default']) == ['123d']
+        assert provider._configuration_arg('ABC', default=['default']) == ['default']
+        assert provider._configuration_arg('abc', casesense=True) == ['123D']
+        assert provider._configuration_arg('xyz', casesense=False) == ['456a', '789b']
+
+    def test_require_class_end_with_suffix(self, ie, logger):
+        class InvalidSuffix(PoTokenCacheProvider):
+            def get(self, key: str):
+                return 'example-cache'
+
+            def store(self, key: str, value: str, expires_at: int):
+                pass
+
+            def delete(self, key: str):
+                pass
+
+            def is_available(self) -> bool:
+                return True
+
+        provider = InvalidSuffix(ie=ie, logger=logger, settings={})
+
+        with pytest.raises(AssertionError):
+            provider.PROVIDER_KEY  # noqa: B018
+
+
+class TestPoTokenCacheSpecProvider:
+
+    def test_base_type(self):
+        assert issubclass(PoTokenCacheSpecProvider, IEContentProvider)
+
+    def test_create_provider_missing_supports_method(self, ie, logger):
+        class MissingMethodsPCS(PoTokenCacheSpecProvider):
+            pass
+
+        with pytest.raises(TypeError):
+            MissingMethodsPCS(ie=ie, logger=logger, settings={})
+
+    def test_create_provider_barebones(self, ie, pot_request, logger):
+        class BarebonesProviderPCSP(PoTokenCacheSpecProvider):
+            def generate_cache_spec(self, request: PoTokenRequest):
+                return PoTokenCacheSpec(
+                    default_ttl=100,
+                    key_bindings={},
+                )
+
+        provider = BarebonesProviderPCSP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'BarebonesProvider'
+        assert provider.PROVIDER_KEY == 'BarebonesProvider'
+        assert provider.PROVIDER_VERSION == '0.0.0'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  (developer has not provided a bug report location)  .'
+        assert provider.is_available()
+        assert provider.generate_cache_spec(request=pot_request).default_ttl == 100
+        assert provider.generate_cache_spec(request=pot_request).key_bindings == {}
+        assert provider.generate_cache_spec(request=pot_request).write_policy == CacheProviderWritePolicy.WRITE_ALL
+
+    def test_create_provider_example(self, ie, pot_request, logger):
+        provider = ExampleCacheSpecProviderPCSP(ie=ie, logger=logger, settings={})
+        assert provider.PROVIDER_NAME == 'example'
+        assert provider.PROVIDER_KEY == 'ExampleCacheSpecProvider'
+        assert provider.PROVIDER_VERSION == '0.0.1'
+        assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  https://example.com/issues  .'
+        assert provider.is_available()
+        assert provider.generate_cache_spec(pot_request)
+        assert provider.generate_cache_spec(pot_request).key_bindings == {'field': 'example-key'}
+        assert provider.generate_cache_spec(pot_request).default_ttl == 60
+        assert provider.generate_cache_spec(pot_request).write_policy == CacheProviderWritePolicy.WRITE_FIRST
+
+    def test_get_config_arg(self, ie, logger):
+        provider = ExampleCacheSpecProviderPCSP(ie=ie, logger=logger, settings={'abc': ['123D'], 'xyz': ['456a', '789B']})
+
+        assert provider._configuration_arg('abc') == ['123d']
+        assert provider._configuration_arg('abc', default=['default']) == ['123d']
+        assert provider._configuration_arg('ABC', default=['default']) == ['default']
+        assert provider._configuration_arg('abc', casesense=True) == ['123D']
+        assert provider._configuration_arg('xyz', casesense=False) == ['456a', '789b']
+
+    def test_require_class_end_with_suffix(self, ie, logger):
+        class InvalidSuffix(PoTokenCacheSpecProvider):
+            def generate_cache_spec(self, request: PoTokenRequest):
+                return None
+
+        provider = InvalidSuffix(ie=ie, logger=logger, settings={})
+
+        with pytest.raises(AssertionError):
+            provider.PROVIDER_KEY  # noqa: B018
+
+
+class TestPoTokenRequest:
+    def test_copy_request(self, pot_request):
+        copied_request = pot_request.copy()
+
+        assert copied_request is not pot_request
+        assert copied_request.context == pot_request.context
+        assert copied_request.innertube_context == pot_request.innertube_context
+        assert copied_request.innertube_context is not pot_request.innertube_context
+        copied_request.innertube_context['client']['clientName'] = 'ANDROID'
+        assert pot_request.innertube_context['client']['clientName'] != 'ANDROID'
+        assert copied_request.innertube_host == pot_request.innertube_host
+        assert copied_request.session_index == pot_request.session_index
+        assert copied_request.player_url == pot_request.player_url
+        assert copied_request.is_authenticated == pot_request.is_authenticated
+        assert copied_request.visitor_data == pot_request.visitor_data
+        assert copied_request.data_sync_id == pot_request.data_sync_id
+        assert copied_request.video_id == pot_request.video_id
+        assert copied_request.request_cookiejar is pot_request.request_cookiejar
+        assert copied_request.request_proxy == pot_request.request_proxy
+        assert copied_request.request_headers == pot_request.request_headers
+        assert copied_request.request_headers is not pot_request.request_headers
+        assert copied_request.request_timeout == pot_request.request_timeout
+        assert copied_request.request_source_address == pot_request.request_source_address
+        assert copied_request.request_verify_tls == pot_request.request_verify_tls
+        assert copied_request.bypass_cache == pot_request.bypass_cache
+
+
+def test_provider_bug_report_message(ie, logger):
+    provider = ExamplePTP(ie=ie, logger=logger, settings={})
+    assert provider.BUG_REPORT_MESSAGE == 'please report this issue to the provider developer at  https://example.com/issues  .'
+
+    message = provider_bug_report_message(provider)
+    assert message == '; please report this issue to the provider developer at  https://example.com/issues  .'
+
+    message_before = provider_bug_report_message(provider, before='custom message!')
+    assert message_before == 'custom message! Please report this issue to the provider developer at  https://example.com/issues  .'
+
+
+def test_register_provider(ie):
+
+    @register_provider
+    class UnavailableProviderPTP(PoTokenProvider):
+        def is_available(self) -> bool:
+            return False
+
+        def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+            raise PoTokenProviderRejectedRequest('Not implemented')
+
+    assert _pot_providers.value.get('UnavailableProvider') == UnavailableProviderPTP
+    _pot_providers.value.pop('UnavailableProvider')
+
+
+def test_register_pot_preference(ie):
+    before = len(_ptp_preferences.value)
+
+    @register_preference(ExamplePTP)
+    def unavailable_preference(provider: PoTokenProvider, request: PoTokenRequest):
+        return 1
+
+    assert len(_ptp_preferences.value) == before + 1
+
+
+def test_register_cache_provider(ie):
+
+    @cache.register_provider
+    class UnavailableCacheProviderPCP(PoTokenCacheProvider):
+        def is_available(self) -> bool:
+            return False
+
+        def get(self, key: str):
+            return 'example-cache'
+
+        def store(self, key: str, value: str, expires_at: int):
+            pass
+
+        def delete(self, key: str):
+            pass
+
+    assert _pot_cache_providers.value.get('UnavailableCacheProvider') == UnavailableCacheProviderPCP
+    _pot_cache_providers.value.pop('UnavailableCacheProvider')
+
+
+def test_register_cache_provider_spec(ie):
+
+    @cache.register_spec
+    class UnavailableCacheProviderPCSP(PoTokenCacheSpecProvider):
+        def is_available(self) -> bool:
+            return False
+
+        def generate_cache_spec(self, request: PoTokenRequest):
+            return None
+
+    assert _pot_pcs_providers.value.get('UnavailableCacheProvider') == UnavailableCacheProviderPCSP
+    _pot_pcs_providers.value.pop('UnavailableCacheProvider')
+
+
+def test_register_cache_provider_preference(ie):
+    before = len(_pot_cache_provider_preferences.value)
+
+    @cache.register_preference(ExampleCacheProviderPCP)
+    def unavailable_preference(provider: PoTokenCacheProvider, request: PoTokenRequest):
+        return 1
+
+    assert len(_pot_cache_provider_preferences.value) == before + 1
+
+
+def test_logger_log_level(logger):
+    assert logger.LogLevel('INFO') == logger.LogLevel.INFO
+    assert logger.LogLevel('debuG') == logger.LogLevel.DEBUG
+    assert logger.LogLevel(10) == logger.LogLevel.DEBUG
+    assert logger.LogLevel('UNKNOWN') == logger.LogLevel.INFO

test/test_youtube_signature.py

@@ -316,6 +316,10 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
         'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
     ),
+    (
+        'https://www.youtube.com/s/player/59b252b9/player_ias.vflset/en_US/base.js',
+        'D3XWVpYgwhLLKNK4AGX', 'aZrQ1qWJ5yv5h',
+    ),
 ]
 
 

yt_dlp/YoutubeDL.py

@@ -640,6 +640,7 @@ class YoutubeDL:
         self._printed_messages = set()
         self._first_webpage_request = True
         self._post_hooks = []
+        self._close_hooks = []
         self._progress_hooks = []
         self._postprocessor_hooks = []
         self._download_retcode = 0
@@ -908,6 +909,11 @@ class YoutubeDL:
         """Add the post hook"""
         self._post_hooks.append(ph)
 
+    def add_close_hook(self, ch):
+        """Add a close hook, called when YoutubeDL.close() is called"""
+        assert callable(ch), 'Close hook must be callable'
+        self._close_hooks.append(ch)
+
     def add_progress_hook(self, ph):
         """Add the download progress hook"""
         self._progress_hooks.append(ph)
@@ -1016,6 +1022,9 @@ class YoutubeDL:
             self._request_director.close()
             del self._request_director
 
+        for close_hook in self._close_hooks:
+            close_hook()
+
     def trouble(self, message=None, tb=None, is_error=True):
         """Determine action to take when a download problem appears.
 

yt_dlp/cookies.py

@@ -764,11 +764,11 @@ def _get_linux_desktop_environment(env, logger):
     GetDesktopEnvironment
     """
     xdg_current_desktop = env.get('XDG_CURRENT_DESKTOP', None)
-    desktop_session = env.get('DESKTOP_SESSION', None)
+    desktop_session = env.get('DESKTOP_SESSION', '')
     if xdg_current_desktop is not None:
         for part in map(str.strip, xdg_current_desktop.split(':')):
             if part == 'Unity':
-                if desktop_session is not None and 'gnome-fallback' in desktop_session:
+                if 'gnome-fallback' in desktop_session:
                     return _LinuxDesktopEnvironment.GNOME
                 else:
                     return _LinuxDesktopEnvironment.UNITY
@@ -797,35 +797,34 @@ def _get_linux_desktop_environment(env, logger):
                 return _LinuxDesktopEnvironment.UKUI
             elif part == 'LXQt':
                 return _LinuxDesktopEnvironment.LXQT
-        logger.info(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
+        logger.debug(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
 
-    elif desktop_session is not None:
-        if desktop_session == 'deepin':
-            return _LinuxDesktopEnvironment.DEEPIN
-        elif desktop_session in ('mate', 'gnome'):
-            return _LinuxDesktopEnvironment.GNOME
-        elif desktop_session in ('kde4', 'kde-plasma'):
+    if desktop_session == 'deepin':
+        return _LinuxDesktopEnvironment.DEEPIN
+    elif desktop_session in ('mate', 'gnome'):
+        return _LinuxDesktopEnvironment.GNOME
+    elif desktop_session in ('kde4', 'kde-plasma'):
+        return _LinuxDesktopEnvironment.KDE4
+    elif desktop_session == 'kde':
+        if 'KDE_SESSION_VERSION' in env:
             return _LinuxDesktopEnvironment.KDE4
-        elif desktop_session == 'kde':
-            if 'KDE_SESSION_VERSION' in env:
-                return _LinuxDesktopEnvironment.KDE4
-            else:
-                return _LinuxDesktopEnvironment.KDE3
-        elif 'xfce' in desktop_session or desktop_session == 'xubuntu':
-            return _LinuxDesktopEnvironment.XFCE
-        elif desktop_session == 'ukui':
-            return _LinuxDesktopEnvironment.UKUI
         else:
-            logger.info(f'DESKTOP_SESSION is set to an unknown value: "{desktop_session}"')
-
+            return _LinuxDesktopEnvironment.KDE3
+    elif 'xfce' in desktop_session or desktop_session == 'xubuntu':
+        return _LinuxDesktopEnvironment.XFCE
+    elif desktop_session == 'ukui':
+        return _LinuxDesktopEnvironment.UKUI
     else:
-        if 'GNOME_DESKTOP_SESSION_ID' in env:
-            return _LinuxDesktopEnvironment.GNOME
-        elif 'KDE_FULL_SESSION' in env:
-            if 'KDE_SESSION_VERSION' in env:
-                return _LinuxDesktopEnvironment.KDE4
-            else:
-                return _LinuxDesktopEnvironment.KDE3
+        logger.debug(f'DESKTOP_SESSION is set to an unknown value: "{desktop_session}"')
+
+    if 'GNOME_DESKTOP_SESSION_ID' in env:
+        return _LinuxDesktopEnvironment.GNOME
+    elif 'KDE_FULL_SESSION' in env:
+        if 'KDE_SESSION_VERSION' in env:
+            return _LinuxDesktopEnvironment.KDE4
+        else:
+            return _LinuxDesktopEnvironment.KDE3
+
     return _LinuxDesktopEnvironment.OTHER
 
 

yt_dlp/extractor/_extractors.py

@@ -338,7 +338,6 @@ from .canalc2 import Canalc2IE
 from .canalplus import CanalplusIE
 from .canalsurmas import CanalsurmasIE
 from .caracoltv import CaracolTvPlayIE
-from .cartoonnetwork import CartoonNetworkIE
 from .cbc import (
     CBCIE,
     CBCGemIE,
@@ -929,7 +928,10 @@ from .jiocinema import (
 )
 from .jiosaavn import (
     JioSaavnAlbumIE,
+    JioSaavnArtistIE,
     JioSaavnPlaylistIE,
+    JioSaavnShowIE,
+    JioSaavnShowPlaylistIE,
     JioSaavnSongIE,
 )
 from .joj import JojIE
@@ -1964,7 +1966,6 @@ from .spreaker import (
     SpreakerShowIE,
 )
 from .springboardplatform import SpringboardPlatformIE
-from .sprout import SproutIE
 from .sproutvideo import (
     SproutVideoIE,
     VidsIoIE,
@@ -2368,6 +2369,7 @@ from .vimeo import (
     VHXEmbedIE,
     VimeoAlbumIE,
     VimeoChannelIE,
+    VimeoEventIE,
     VimeoGroupsIE,
     VimeoIE,
     VimeoLikesIE,

yt_dlp/extractor/amcnetworks.py

@@ -1,32 +1,24 @@
-import re
-
-from .theplatform import ThePlatformIE
-from ..utils import (
-    int_or_none,
-    parse_age_limit,
-    try_get,
-    update_url_query,
-)
+from .brightcove import BrightcoveNewIE
+from .common import InfoExtractor
+from ..utils.traversal import traverse_obj
 
 
-class AMCNetworksIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
-    _VALID_URL = r'https?://(?:www\.)?(?P<site>amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/]+)+)/[^/?#&]+)'
+class AMCNetworksIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?(?:amc|bbcamerica|ifc|(?:we|sundance)tv)\.com/(?P<id>(?:movies|shows(?:/[^/?#]+)+)/[^/?#&]+)'
     _TESTS = [{
-        'url': 'https://www.bbcamerica.com/shows/the-graham-norton-show/videos/tina-feys-adorable-airline-themed-family-dinner--51631',
+        'url': 'https://www.amc.com/shows/dark-winds/videos/dark-winds-a-look-at-season-3--1072027',
         'info_dict': {
-            'id': '4Lq1dzOnZGt0',
+            'id': '6369261343112',
             'ext': 'mp4',
-            'title': "The Graham Norton Show - Season 28 - Tina Fey's Adorable Airline-Themed Family Dinner",
-            'description': "It turns out child stewardesses are very generous with the wine! All-new episodes of 'The Graham Norton Show' premiere Fridays at 11/10c on BBC America.",
-            'upload_date': '20201120',
-            'timestamp': 1605904350,
-            'uploader': 'AMCN',
+            'title': 'Dark Winds: A Look at Season 3',
+            'uploader_id': '6240731308001',
+            'duration': 176.427,
+            'thumbnail': r're:https://[^/]+\.boltdns\.net/.+/image\.jpg',
+            'tags': [],
+            'timestamp': 1740414792,
+            'upload_date': '20250224',
         },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-        'skip': '404 Not Found',
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://www.bbcamerica.com/shows/the-hunt/full-episodes/season-1/episode-01-the-hardest-challenge',
         'only_matching': True,
@@ -52,96 +44,18 @@ class AMCNetworksIE(ThePlatformIE):  # XXX: Do not subclass from concrete IE
         'url': 'https://www.sundancetv.com/shows/riviera/full-episodes/season-1/episode-01-episode-1',
         'only_matching': True,
     }]
-    _REQUESTOR_ID_MAP = {
-        'amc': 'AMC',
-        'bbcamerica': 'BBCA',
-        'ifc': 'IFC',
-        'sundancetv': 'SUNDANCE',
-        'wetv': 'WETV',
-    }
 
     def _real_extract(self, url):
-        site, display_id = self._match_valid_url(url).groups()
-        requestor_id = self._REQUESTOR_ID_MAP[site]
-        page_data = self._download_json(
-            f'https://content-delivery-gw.svc.ds.amcn.com/api/v2/content/amcn/{requestor_id.lower()}/url/{display_id}',
-            display_id)['data']
-        properties = page_data.get('properties') or {}
-        query = {
-            'mbr': 'true',
-            'manifest': 'm3u',
-        }
+        display_id = self._match_id(url)
+        webpage = self._download_webpage(url, display_id)
+        initial_data = self._search_json(
+            r'window\.initialData\s*=\s*JSON\.parse\(String\.raw`', webpage, 'initial data', display_id)
+        video_id = traverse_obj(initial_data, ('initialData', 'properties', 'videoId', {str}))
+        if not video_id:  # All locked videos are now DRM-protected
+            self.report_drm(display_id)
+        account_id = initial_data['config']['brightcove']['accountId']
+        player_id = initial_data['config']['brightcove']['playerId']
 
-        video_player_count = 0
-        try:
-            for v in page_data['children']:
-                if v.get('type') == 'video-player':
-                    release_pid = v['properties']['currentVideo']['meta']['releasePid']
-                    tp_path = 'M_UwQC/' + release_pid
-                    media_url = 'https://link.theplatform.com/s/' + tp_path
-                    video_player_count += 1
-        except KeyError:
-            pass
-        if video_player_count > 1:
-            self.report_warning(
-                f'The JSON data has {video_player_count} video players. Only one will be extracted')
-
-        # Fall back to videoPid if releasePid not found.
-        # TODO: Fall back to videoPid if releasePid manifest uses DRM.
-        if not video_player_count:
-            tp_path = 'M_UwQC/media/' + properties['videoPid']
-            media_url = 'https://link.theplatform.com/s/' + tp_path
-
-        theplatform_metadata = self._download_theplatform_metadata(tp_path, display_id)
-        info = self._parse_theplatform_metadata(theplatform_metadata)
-        video_id = theplatform_metadata['pid']
-        title = theplatform_metadata['title']
-        rating = try_get(
-            theplatform_metadata, lambda x: x['ratings'][0]['rating'])
-        video_category = properties.get('videoCategory')
-        if video_category and video_category.endswith('-Auth'):
-            resource = self._get_mvpd_resource(
-                requestor_id, title, video_id, rating)
-            query['auth'] = self._extract_mvpd_auth(
-                url, video_id, requestor_id, resource)
-        media_url = update_url_query(media_url, query)
-        formats, subtitles = self._extract_theplatform_smil(
-            media_url, video_id)
-
-        thumbnails = []
-        thumbnail_urls = [properties.get('imageDesktop')]
-        if 'thumbnail' in info:
-            thumbnail_urls.append(info.pop('thumbnail'))
-        for thumbnail_url in thumbnail_urls:
-            if not thumbnail_url:
-                continue
-            mobj = re.search(r'(\d+)x(\d+)', thumbnail_url)
-            thumbnails.append({
-                'url': thumbnail_url,
-                'width': int(mobj.group(1)) if mobj else None,
-                'height': int(mobj.group(2)) if mobj else None,
-            })
-
-        info.update({
-            'age_limit': parse_age_limit(rating),
-            'formats': formats,
-            'id': video_id,
-            'subtitles': subtitles,
-            'thumbnails': thumbnails,
-        })
-        ns_keys = theplatform_metadata.get('$xmlns', {}).keys()
-        if ns_keys:
-            ns = next(iter(ns_keys))
-            episode = theplatform_metadata.get(ns + '$episodeTitle') or None
-            episode_number = int_or_none(
-                theplatform_metadata.get(ns + '$episode'))
-            season_number = int_or_none(
-                theplatform_metadata.get(ns + '$season'))
-            series = theplatform_metadata.get(ns + '$show') or None
-            info.update({
-                'episode': episode,
-                'episode_number': episode_number,
-                'season_number': season_number,
-                'series': series,
-            })
-        return info
+        return self.url_result(
+            f'https://players.brightcove.net/{account_id}/{player_id}_default/index.html?videoId={video_id}',
+            BrightcoveNewIE, video_id)

yt_dlp/extractor/bitchute.py

@@ -1,30 +1,32 @@
 import functools
+import json
 import re
 
 from .common import InfoExtractor
 from ..networking import HEADRequest
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
     clean_html,
-    extract_attributes,
+    determine_ext,
+    format_field,
     get_element_by_class,
-    get_element_by_id,
-    get_element_html_by_class,
     get_elements_html_by_class,
     int_or_none,
     orderedSet,
     parse_count,
     parse_duration,
-    traverse_obj,
-    unified_strdate,
+    parse_iso8601,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BitChuteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|old)\.)?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/',
@@ -34,12 +36,17 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'This is the first video on #BitChute !',
             'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20170103',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 16.0,
+            'timestamp': 1483425443,
         },
     }, {
         # test case: video with different channel and uploader
@@ -49,13 +56,18 @@ class BitChuteIE(InfoExtractor):
             'id': 'Yti_j9A-UZ4',
             'ext': 'mp4',
             'title': 'Israel at War | Full Measure',
-            'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:e60198b89971966d6030d22b3268f08f',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'sharylattkisson',
             'upload_date': '20231106',
             'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
             'channel': 'Full Measure with Sharyl Attkisson',
             'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
+            'uploader_id': '9K0kUWA9zmd9',
+            'channel_id': 'NpdxoCRv3ZLb',
+            'view_count': int,
+            'duration': 554.0,
+            'timestamp': 1699296106,
         },
     }, {
         # video not downloadable in browser, but we can recover it
@@ -66,25 +78,21 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'filesize': 71537926,
             'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
-            'description': 'md5:228ee93bd840a24938f536aeac9cf749',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:2029c7c212ccd4b040f52bb2d036ef4e',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20181113',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 1701.0,
+            'tags': ['bitchute'],
+            'timestamp': 1542130287,
         },
         'params': {'check_formats': None},
-    }, {
-        # restricted video
-        'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
-        'info_dict': {
-            'id': 'WEnQU7XGcTdl',
-            'ext': 'mp4',
-            'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
-        },
-        'params': {'skip_download': True},
-        'skip': 'Georestricted in DE',
     }, {
         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
         'only_matching': True,
@@ -96,11 +104,8 @@ class BitChuteIE(InfoExtractor):
         'only_matching': True,
     }]
     _GEO_BYPASS = False
-
-    _HEADERS = {
-        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
-        'Referer': 'https://www.bitchute.com/',
-    }
+    _UPLOADER_URL_TMPL = 'https://www.bitchute.com/profile/%s/'
+    _CHANNEL_URL_TMPL = 'https://www.bitchute.com/channel/%s/'
 
     def _check_format(self, video_url, video_id):
         urls = orderedSet(
@@ -112,7 +117,7 @@ class BitChuteIE(InfoExtractor):
         for url in urls:
             try:
                 response = self._request_webpage(
-                    HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
+                    HEADRequest(url), video_id=video_id, note=f'Checking {url}')
             except ExtractorError as e:
                 self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
                 continue
@@ -121,54 +126,79 @@ class BitChuteIE(InfoExtractor):
                 'filesize': int_or_none(response.headers.get('Content-Length')),
             }
 
-    def _raise_if_restricted(self, webpage):
-        page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
-        if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
-            reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
-            self.raise_geo_restricted(reason)
-
-    @staticmethod
-    def _make_url(html):
-        path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
-        return urljoin('https://www.bitchute.com', path)
+    def _call_api(self, endpoint, data, display_id, fatal=True):
+        note = endpoint.rpartition('/')[2]
+        try:
+            return self._download_json(
+                f'https://api.bitchute.com/api/beta/{endpoint}', display_id,
+                f'Downloading {note} API JSON', f'Unable to download {note} API JSON',
+                data=json.dumps(data).encode(),
+                headers={
+                    'Accept': 'application/json',
+                    'Content-Type': 'application/json',
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                errors = '. '.join(traverse_obj(e.cause.response.read().decode(), (
+                    {json.loads}, 'errors', lambda _, v: v['context'] == 'reason', 'message', {str})))
+                if errors and 'location' in errors:
+                    # Can always be fatal since the video/media call will reach this code first
+                    self.raise_geo_restricted(errors)
+            if fatal:
+                raise
+            self.report_warning(e.msg)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
-
-        self._raise_if_restricted(webpage)
-        publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        data = {'video_id': video_id}
+        media_url = self._call_api('video/media', data, video_id)['media_url']
 
         formats = []
-        for format_ in traverse_obj(entries, (0, 'formats', ...)):
+        if determine_ext(media_url) == 'm3u8':
+            formats.extend(
+                self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls', live=True))
+        else:
             if self.get_param('check_formats') is not False:
-                format_.update(self._check_format(format_.pop('url'), video_id) or {})
-                if 'url' not in format_:
-                    continue
-            formats.append(format_)
+                if fmt := self._check_format(media_url, video_id):
+                    formats.append(fmt)
+            else:
+                formats.append({'url': media_url})
 
         if not formats:
             self.raise_no_formats(
                 'Video is unavailable. Please make sure this video is playable in the browser '
                 'before reporting this issue.', expected=True, video_id=video_id)
 
-        details = get_element_by_class('details', webpage) or ''
-        uploader_html = get_element_html_by_class('creator', details) or ''
-        channel_html = get_element_html_by_class('name', details) or ''
+        video = self._call_api('video', data, video_id, fatal=False)
+        channel = None
+        if channel_id := traverse_obj(video, ('channel', 'channel_id', {str})):
+            channel = self._call_api('channel', {'channel_id': channel_id}, video_id, fatal=False)
 
         return {
+            **traverse_obj(video, {
+                'title': ('video_name', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'channel': ('channel', 'channel_name', {str}),
+                'channel_id': ('channel', 'channel_id', {str}),
+                'channel_url': ('channel', 'channel_url', {urljoin('https://www.bitchute.com/')}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+                'timestamp': ('date_published', {parse_iso8601}),
+                'duration': ('duration', {parse_duration}),
+                'tags': ('hashtags', ..., {str}, filter, all, filter),
+                'view_count': ('view_count', {int_or_none}),
+                'is_live': ('state_id', {lambda x: x == 'live'}),
+            }),
+            **traverse_obj(channel, {
+                'channel': ('channel_name', {str}),
+                'channel_id': ('channel_id', {str}),
+                'channel_url': ('url_slug', {format_field(template=self._CHANNEL_URL_TMPL)}, filter),
+                'uploader': ('profile_name', {str}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+            }),
             'id': video_id,
-            'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
-            'description': self._og_search_description(webpage, default=None),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': clean_html(uploader_html),
-            'uploader_url': self._make_url(uploader_html),
-            'channel': clean_html(channel_html),
-            'channel_url': self._make_url(channel_html),
-            'upload_date': unified_strdate(self._search_regex(
-                r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
             'formats': formats,
         }
 
@@ -190,7 +220,7 @@ class BitChuteChannelIE(InfoExtractor):
                     'ext': 'mp4',
                     'title': 'This is the first video on #BitChute !',
                     'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-                    'thumbnail': r're:^https?://.*\.jpg$',
+                    'thumbnail': r're:https?://.+/.+\.jpg$',
                     'uploader': 'BitChute',
                     'upload_date': '20170103',
                     'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
@@ -198,6 +228,9 @@ class BitChuteChannelIE(InfoExtractor):
                     'channel_url': 'https://www.bitchute.com/channel/bitchute/',
                     'duration': 16,
                     'view_count': int,
+                    'uploader_id': 'I5NgtHZn9vPj',
+                    'channel_id': '1VBwRfyNcKdX',
+                    'timestamp': 1483425443,
                 },
             },
         ],
@@ -213,6 +246,7 @@ class BitChuteChannelIE(InfoExtractor):
             'title': 'Bruce MacDonald and "The Light of Darkness"',
             'description': 'md5:747724ef404eebdfc04277714f81863e',
         },
+        'skip': '404 Not Found',
     }, {
         'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
         'only_matching': True,

yt_dlp/extractor/cartoonnetwork.py

@@ -1,59 +0,0 @@
-from .turner import TurnerBaseIE
-from ..utils import int_or_none
-
-
-class CartoonNetworkIE(TurnerBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?cartoonnetwork\.com/video/(?:[^/]+/)+(?P<id>[^/?#]+)-(?:clip|episode)\.html'
-    _TEST = {
-        'url': 'https://www.cartoonnetwork.com/video/ben-10/how-to-draw-upgrade-episode.html',
-        'info_dict': {
-            'id': '6e3375097f63874ebccec7ef677c1c3845fa850e',
-            'ext': 'mp4',
-            'title': 'How to Draw Upgrade',
-            'description': 'md5:2061d83776db7e8be4879684eefe8c0f',
-        },
-        'params': {
-            # m3u8 download
-            'skip_download': True,
-        },
-    }
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        webpage = self._download_webpage(url, display_id)
-
-        def find_field(global_re, name, content_re=None, value_re='[^"]+', fatal=False):
-            metadata_re = ''
-            if content_re:
-                metadata_re = r'|video_metadata\.content_' + content_re
-            return self._search_regex(
-                rf'(?:_cnglobal\.currentVideo\.{global_re}{metadata_re})\s*=\s*"({value_re})";',
-                webpage, name, fatal=fatal)
-
-        media_id = find_field('mediaId', 'media id', 'id', '[0-9a-f]{40}', True)
-        title = find_field('episodeTitle', 'title', '(?:episodeName|name)', fatal=True)
-
-        info = self._extract_ngtv_info(
-            media_id, {'networkId': 'cartoonnetwork'}, {
-                'url': url,
-                'site_name': 'CartoonNetwork',
-                'auth_required': find_field('authType', 'auth type') != 'unauth',
-            })
-
-        series = find_field(
-            'propertyName', 'series', 'showName') or self._html_search_meta('partOfSeries', webpage)
-        info.update({
-            'id': media_id,
-            'display_id': display_id,
-            'title': title,
-            'description': self._html_search_meta('description', webpage),
-            'series': series,
-            'episode': title,
-        })
-
-        for field in ('season', 'episode'):
-            field_name = field + 'Number'
-            info[field + '_number'] = int_or_none(find_field(
-                field_name, field + ' number', value_re=r'\d+') or self._html_search_meta(field_name, webpage))
-
-        return info

yt_dlp/extractor/espn.py

@@ -5,7 +5,6 @@ import urllib.parse
 
 from .adobepass import AdobePassIE
 from .common import InfoExtractor
-from .once import OnceIE
 from ..utils import (
     determine_ext,
     dict_get,
@@ -16,7 +15,7 @@ from ..utils import (
 )
 
 
-class ESPNIE(OnceIE):
+class ESPNIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
@@ -131,9 +130,7 @@ class ESPNIE(OnceIE):
                 return
             format_urls.add(source_url)
             ext = determine_ext(source_url)
-            if OnceIE.suitable(source_url):
-                formats.extend(self._extract_once_formats(source_url))
-            elif ext == 'smil':
+            if ext == 'smil':
                 formats.extend(self._extract_smil_formats(
                     source_url, video_id, fatal=False))
             elif ext == 'f4m':

yt_dlp/extractor/firsttv.py

@@ -2,11 +2,15 @@ import urllib.parse
 
 from .common import InfoExtractor
 from ..utils import (
+    determine_ext,
     int_or_none,
-    qualities,
+    join_nonempty,
+    mimetype2ext,
+    parse_qs,
     unified_strdate,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class FirstTVIE(InfoExtractor):
@@ -15,40 +19,51 @@ class FirstTVIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?(?:sport)?1tv\.ru/(?:[^/?#]+/)+(?P<id>[^/?#]+)'
 
     _TESTS = [{
-        # single format
-        'url': 'http://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
-        'md5': 'a1b6b60d530ebcf8daacf4565762bbaf',
+        # single format; has item.id
+        'url': 'https://www.1tv.ru/shows/naedine-so-vsemi/vypuski/gost-lyudmila-senchina-naedine-so-vsemi-vypusk-ot-12-02-2015',
+        'md5': '8011ae8e88ff4150107ab9c5a8f5b659',
         'info_dict': {
             'id': '40049',
             'ext': 'mp4',
             'title': 'Гость Людмила Сенчина. Наедине со всеми. Выпуск от 12.02.2015',
-            'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'upload_date': '20150212',
             'duration': 2694,
         },
+        'params': {'skip_download': 'm3u8'},
     }, {
-        # multiple formats
-        'url': 'http://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
+        # multiple formats; has item.id
+        'url': 'https://www.1tv.ru/shows/dobroe-utro/pro-zdorove/vesennyaya-allergiya-dobroe-utro-fragment-vypuska-ot-07042016',
         'info_dict': {
             'id': '364746',
             'ext': 'mp4',
             'title': 'Весенняя аллергия. Доброе утро. Фрагмент выпуска от 07.04.2016',
-            'thumbnail': r're:^https?://.*\.(?:jpg|JPG)$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'upload_date': '20160407',
             'duration': 179,
             'formats': 'mincount:3',
         },
-        'params': {
-            'skip_download': True,
-        },
+        'params': {'skip_download': 'm3u8'},
     }, {
-        'url': 'http://www.1tv.ru/news/issue/2016-12-01/14:00',
+        'url': 'https://www.1tv.ru/news/issue/2016-12-01/14:00',
         'info_dict': {
             'id': '14:00',
-            'title': 'Выпуск новостей в 14:00   1 декабря 2016 года. Новости. Первый канал',
-            'description': 'md5:2e921b948f8c1ff93901da78ebdb1dfd',
+            'title': 'Выпуск программы «Время» в 20:00   1 декабря 2016 года. Новости. Первый канал',
+            'thumbnail': 'https://static.1tv.ru/uploads/photo/image/8/big/338448_big_8fc7eb236f.jpg',
         },
         'playlist_count': 13,
+    }, {
+        # has timestamp; has item.uid but not item.id
+        'url': 'https://www.1tv.ru/shows/segodnya-vecherom/vypuski/avtory-odnogo-hita-segodnya-vecherom-vypusk-ot-03-05-2025',
+        'info_dict': {
+            'id': '270411',
+            'ext': 'mp4',
+            'title': 'Авторы одного хита. Сегодня вечером. Выпуск от 03.05.2025',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'timestamp': 1746286020,
+            'upload_date': '20250503',
+        },
+        'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'http://www.1tv.ru/shows/tochvtoch-supersezon/vystupleniya/evgeniy-dyatlov-vladimir-vysockiy-koni-priveredlivye-toch-v-toch-supersezon-fragment-vypuska-ot-06-11-2016',
         'only_matching': True,
@@ -57,96 +72,60 @@ class FirstTVIE(InfoExtractor):
         'only_matching': True,
     }]
 
+    def _entries(self, items):
+        for item in items:
+            video_id = str(item.get('id') or item['uid'])
+
+            formats, subtitles = [], {}
+            for f in traverse_obj(item, ('sources', lambda _, v: url_or_none(v['src']))):
+                src = f['src']
+                ext = mimetype2ext(f.get('type'), default=determine_ext(src))
+                if ext == 'm3u8':
+                    fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                        src, video_id, 'mp4', m3u8_id='hls', fatal=False)
+                elif ext == 'mpd':
+                    fmts, subs = self._extract_mpd_formats_and_subtitles(
+                        src, video_id, mpd_id='dash', fatal=False)
+                else:
+                    tbr = self._search_regex(fr'_(\d{{3,}})\.{ext}', src, 'tbr', default=None)
+                    formats.append({
+                        'url': src,
+                        'ext': ext,
+                        'format_id': join_nonempty('http', ext, tbr),
+                        'tbr': int_or_none(tbr),
+                        # quality metadata of http formats may be incorrect
+                        'quality': -10,
+                    })
+                    continue
+                formats.extend(fmts)
+                self._merge_subtitles(subs, target=subtitles)
+
+            yield {
+                **traverse_obj(item, {
+                    'title': ('title', {str}),
+                    'thumbnail': ('poster', {url_or_none}),
+                    'timestamp': ('dvr_begin_at', {int_or_none}),
+                    'upload_date': ('date_air', {unified_strdate}),
+                    'duration': ('duration', {int_or_none}),
+                }),
+                'id': video_id,
+                'formats': formats,
+                'subtitles': subtitles,
+            }
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
 
         webpage = self._download_webpage(url, display_id)
-        playlist_url = urllib.parse.urljoin(url, self._search_regex(
+        playlist_url = urllib.parse.urljoin(url, self._html_search_regex(
             r'data-playlist-url=(["\'])(?P<url>(?:(?!\1).)+)\1',
             webpage, 'playlist url', group='url'))
 
-        parsed_url = urllib.parse.urlparse(playlist_url)
-        qs = urllib.parse.parse_qs(parsed_url.query)
-        item_ids = qs.get('videos_ids[]') or qs.get('news_ids[]')
+        item_ids = traverse_obj(parse_qs(playlist_url), 'video_id', 'videos_ids[]', 'news_ids[]')
+        items = traverse_obj(
+            self._download_json(playlist_url, display_id),
+            lambda _, v: v['uid'] and (str(v['uid']) in item_ids if item_ids else True))
 
-        items = self._download_json(playlist_url, display_id)
-
-        if item_ids:
-            items = [
-                item for item in items
-                if item.get('uid') and str(item['uid']) in item_ids]
-        else:
-            items = [items[0]]
-
-        entries = []
-        QUALITIES = ('ld', 'sd', 'hd')
-
-        for item in items:
-            title = item['title']
-            quality = qualities(QUALITIES)
-            formats = []
-            path = None
-            for f in item.get('mbr', []):
-                src = url_or_none(f.get('src'))
-                if not src:
-                    continue
-                tbr = int_or_none(self._search_regex(
-                    r'_(\d{3,})\.mp4', src, 'tbr', default=None))
-                if not path:
-                    path = self._search_regex(
-                        r'//[^/]+/(.+?)_\d+\.mp4', src,
-                        'm3u8 path', default=None)
-                formats.append({
-                    'url': src,
-                    'format_id': f.get('name'),
-                    'tbr': tbr,
-                    'source_preference': quality(f.get('name')),
-                    # quality metadata of http formats may be incorrect
-                    'preference': -10,
-                })
-            # m3u8 URL format is reverse engineered from [1] (search for
-            # master.m3u8). dashEdges (that is currently balancer-vod.1tv.ru)
-            # is taken from [2].
-            # 1. http://static.1tv.ru/player/eump1tv-current/eump-1tv.all.min.js?rnd=9097422834:formatted
-            # 2. http://static.1tv.ru/player/eump1tv-config/config-main.js?rnd=9097422834
-            if not path and len(formats) == 1:
-                path = self._search_regex(
-                    r'//[^/]+/(.+?$)', formats[0]['url'],
-                    'm3u8 path', default=None)
-            if path:
-                if len(formats) == 1:
-                    m3u8_path = ','
-                else:
-                    tbrs = [str(t) for t in sorted(f['tbr'] for f in formats)]
-                    m3u8_path = '_,{},{}'.format(','.join(tbrs), '.mp4')
-                formats.extend(self._extract_m3u8_formats(
-                    f'http://balancer-vod.1tv.ru/{path}{m3u8_path}.urlset/master.m3u8',
-                    display_id, 'mp4',
-                    entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
-
-            thumbnail = item.get('poster') or self._og_search_thumbnail(webpage)
-            duration = int_or_none(item.get('duration') or self._html_search_meta(
-                'video:duration', webpage, 'video duration', fatal=False))
-            upload_date = unified_strdate(self._html_search_meta(
-                'ya:ovs:upload_date', webpage, 'upload date', default=None))
-
-            entries.append({
-                'id': str(item.get('id') or item['uid']),
-                'thumbnail': thumbnail,
-                'title': title,
-                'upload_date': upload_date,
-                'duration': int_or_none(duration),
-                'formats': formats,
-            })
-
-        title = self._html_search_regex(
-            (r'<div class="tv_translation">\s*<h1><a href="[^"]+">([^<]*)</a>',
-             r"'title'\s*:\s*'([^']+)'"),
-            webpage, 'title', default=None) or self._og_search_title(
-            webpage, default=None)
-        description = self._html_search_regex(
-            r'<div class="descr">\s*<div>&nbsp;</div>\s*<p>([^<]*)</p></div>',
-            webpage, 'description', default=None) or self._html_search_meta(
-            'description', webpage, 'description', default=None)
-
-        return self.playlist_result(entries, display_id, title, description)
+        return self.playlist_result(
+            self._entries(items), display_id, self._og_search_title(webpage, default=None),
+            thumbnail=self._og_search_thumbnail(webpage, default=None))

yt_dlp/extractor/gamespot.py

@@ -1,9 +1,9 @@
 import urllib.parse
 
-from .once import OnceIE
+from .common import InfoExtractor
 
 
-class GameSpotIE(OnceIE):
+class GameSpotIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?gamespot\.com/(?:video|article|review)s/(?:[^/]+/\d+-|embed/)(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',

yt_dlp/extractor/iprima.py

@@ -1,3 +1,4 @@
+import json
 import re
 import time
 
@@ -6,9 +7,7 @@ from ..utils import (
     ExtractorError,
     determine_ext,
     js_to_json,
-    parse_qs,
     traverse_obj,
-    urlencode_postdata,
 )
 
 
@@ -16,7 +15,6 @@ class IPrimaIE(InfoExtractor):
     _VALID_URL = r'https?://(?!cnn)(?:[^/]+)\.iprima\.cz/(?:[^/]+/)*(?P<id>[^/?#&]+)'
     _GEO_BYPASS = False
     _NETRC_MACHINE = 'iprima'
-    _AUTH_ROOT = 'https://auth.iprima.cz'
     access_token = None
 
     _TESTS = [{
@@ -86,48 +84,18 @@ class IPrimaIE(InfoExtractor):
         if self.access_token:
             return
 
-        login_page = self._download_webpage(
-            f'{self._AUTH_ROOT}/oauth2/login', None, note='Downloading login page',
-            errnote='Downloading login page failed')
-
-        login_form = self._hidden_inputs(login_page)
-
-        login_form.update({
-            '_email': username,
-            '_password': password})
-
-        profile_select_html, login_handle = self._download_webpage_handle(
-            f'{self._AUTH_ROOT}/oauth2/login', None, data=urlencode_postdata(login_form),
-            note='Logging in')
-
-        # a profile may need to be selected first, even when there is only a single one
-        if '/profile-select' in login_handle.url:
-            profile_id = self._search_regex(
-                r'data-identifier\s*=\s*["\']?(\w+)', profile_select_html, 'profile id')
-
-            login_handle = self._request_webpage(
-                f'{self._AUTH_ROOT}/user/profile-select-perform/{profile_id}', None,
-                query={'continueUrl': '/user/login?redirect_uri=/user/'}, note='Selecting profile')
-
-        code = traverse_obj(login_handle.url, ({parse_qs}, 'code', 0))
-        if not code:
-            raise ExtractorError('Login failed', expected=True)
-
-        token_request_data = {
-            'scope': 'openid+email+profile+phone+address+offline_access',
-            'client_id': 'prima_sso',
-            'grant_type': 'authorization_code',
-            'code': code,
-            'redirect_uri': f'{self._AUTH_ROOT}/sso/auth-check'}
-
         token_data = self._download_json(
-            f'{self._AUTH_ROOT}/oauth2/token', None,
-            note='Downloading token', errnote='Downloading token failed',
-            data=urlencode_postdata(token_request_data))
+            'https://ucet.iprima.cz/api/session/create', None,
+            note='Logging in', errnote='Failed to log in',
+            data=json.dumps({
+                'email': username,
+                'password': password,
+                'deviceName': 'Windows Chrome',
+            }).encode(), headers={'content-type': 'application/json'})
 
-        self.access_token = token_data.get('access_token')
-        if self.access_token is None:
-            raise ExtractorError('Getting token failed', expected=True)
+        self.access_token = token_data['accessToken']['value']
+        if not self.access_token:
+            raise ExtractorError('Failed to fetch access token')
 
     def _real_initialize(self):
         if not self.access_token:

yt_dlp/extractor/jiosaavn.py

@@ -1,23 +1,33 @@
 import functools
+import itertools
 import math
 import re
 
 from .common import InfoExtractor
 from ..utils import (
     InAdvancePagedList,
+    ISO639Utils,
+    OnDemandPagedList,
     clean_html,
     int_or_none,
+    js_to_json,
     make_archive_id,
+    orderedSet,
     smuggle_url,
+    unified_strdate,
+    unified_timestamp,
     unsmuggle_url,
     url_basename,
     url_or_none,
     urlencode_postdata,
+    urljoin,
+    variadic,
 )
 from ..utils.traversal import traverse_obj
 
 
 class JioSaavnBaseIE(InfoExtractor):
+    _URL_BASE_RE = r'https?://(?:www\.)?(?:jio)?saavn\.com'
     _API_URL = 'https://www.jiosaavn.com/api.php'
     _VALID_BITRATES = {'16', '32', '64', '128', '320'}
 
@@ -30,16 +40,20 @@ class JioSaavnBaseIE(InfoExtractor):
                 f'Valid bitrates are: {", ".join(sorted(self._VALID_BITRATES, key=int))}')
         return requested_bitrates
 
-    def _extract_formats(self, song_data):
+    def _extract_formats(self, item_data):
+        # Show/episode JSON data has a slightly different structure than song JSON data
+        if media_url := traverse_obj(item_data, ('more_info', 'encrypted_media_url', {str})):
+            item_data.setdefault('encrypted_media_url', media_url)
+
         for bitrate in self.requested_bitrates:
             media_data = self._download_json(
-                self._API_URL, song_data['id'],
+                self._API_URL, item_data['id'],
                 f'Downloading format info for {bitrate}',
                 fatal=False, data=urlencode_postdata({
                     '__call': 'song.generateAuthToken',
                     '_format': 'json',
                     'bitrate': bitrate,
-                    'url': song_data['encrypted_media_url'],
+                    'url': item_data['encrypted_media_url'],
                 }))
             if not traverse_obj(media_data, ('auth_url', {url_or_none})):
                 self.report_warning(f'Unable to extract format info for {bitrate}')
@@ -53,24 +67,6 @@ class JioSaavnBaseIE(InfoExtractor):
                 'vcodec': 'none',
             }
 
-    def _extract_song(self, song_data, url=None):
-        info = traverse_obj(song_data, {
-            'id': ('id', {str}),
-            'title': ('song', {clean_html}),
-            'album': ('album', {clean_html}),
-            'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
-            'duration': ('duration', {int_or_none}),
-            'view_count': ('play_count', {int_or_none}),
-            'release_year': ('year', {int_or_none}),
-            'artists': ('primary_artists', {lambda x: x.split(', ') if x else None}),
-            'webpage_url': ('perma_url', {url_or_none}),
-        })
-        if webpage_url := info.get('webpage_url') or url:
-            info['display_id'] = url_basename(webpage_url)
-            info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
-
-        return info
-
     def _call_api(self, type_, token, note='API', params={}):
         return self._download_json(
             self._API_URL, token, f'Downloading {note} JSON', f'Unable to download {note} JSON',
@@ -84,19 +80,89 @@ class JioSaavnBaseIE(InfoExtractor):
                 **params,
             })
 
-    def _yield_songs(self, playlist_data):
-        for song_data in traverse_obj(playlist_data, ('songs', lambda _, v: v['id'] and v['perma_url'])):
-            song_info = self._extract_song(song_data)
-            url = smuggle_url(song_info['webpage_url'], {
-                'id': song_data['id'],
-                'encrypted_media_url': song_data['encrypted_media_url'],
-            })
-            yield self.url_result(url, JioSaavnSongIE, url_transparent=True, **song_info)
+    @staticmethod
+    def _extract_song(song_data, url=None):
+        info = traverse_obj(song_data, {
+            'id': ('id', {str}),
+            'title': (('song', 'title'), {clean_html}, any),
+            'album': ((None, 'more_info'), 'album', {clean_html}, any),
+            'duration': ((None, 'more_info'), 'duration', {int_or_none}, any),
+            'channel': ((None, 'more_info'), 'label', {str}, any),
+            'channel_id': ((None, 'more_info'), 'label_id', {str}, any),
+            'channel_url': ((None, 'more_info'), 'label_url', {urljoin('https://www.jiosaavn.com/')}, any),
+            'release_date': ((None, 'more_info'), 'release_date', {unified_strdate}, any),
+            'release_year': ('year', {int_or_none}),
+            'thumbnail': ('image', {url_or_none}, {lambda x: re.sub(r'-\d+x\d+\.', '-500x500.', x)}),
+            'view_count': ('play_count', {int_or_none}),
+            'language': ('language', {lambda x: ISO639Utils.short2long(x.casefold()) or 'und'}),
+            'webpage_url': ('perma_url', {url_or_none}),
+            'artists': ('more_info', 'artistMap', 'primary_artists', ..., 'name', {str}, filter, all),
+        })
+        if webpage_url := info.get('webpage_url') or url:
+            info['display_id'] = url_basename(webpage_url)
+            info['_old_archive_ids'] = [make_archive_id(JioSaavnSongIE, info['display_id'])]
+
+        if primary_artists := traverse_obj(song_data, ('primary_artists', {lambda x: x.split(', ') if x else None})):
+            info['artists'].extend(primary_artists)
+        if featured_artists := traverse_obj(song_data, ('featured_artists', {str}, filter)):
+            info['artists'].extend(featured_artists.split(', '))
+        info['artists'] = orderedSet(info['artists']) or None
+
+        return info
+
+    @staticmethod
+    def _extract_episode(episode_data, url=None):
+        info = JioSaavnBaseIE._extract_song(episode_data, url)
+        info.pop('_old_archive_ids', None)
+        info.update(traverse_obj(episode_data, {
+            'description': ('more_info', 'description', {str}),
+            'timestamp': ('more_info', 'release_time', {unified_timestamp}),
+            'series': ('more_info', 'show_title', {str}),
+            'series_id': ('more_info', 'show_id', {str}),
+            'season': ('more_info', 'season_title', {str}),
+            'season_number': ('more_info', 'season_no', {int_or_none}),
+            'season_id': ('more_info', 'season_id', {str}),
+            'episode_number': ('more_info', 'episode_number', {int_or_none}),
+            'cast': ('starring', {lambda x: x.split(', ') if x else None}),
+        }))
+        return info
+
+    def _extract_jiosaavn_result(self, url, endpoint, response_key, parse_func):
+        url, smuggled_data = unsmuggle_url(url)
+        data = traverse_obj(smuggled_data, ({
+            'id': ('id', {str}),
+            'encrypted_media_url': ('encrypted_media_url', {str}),
+        }))
+
+        if 'id' in data and 'encrypted_media_url' in data:
+            result = {'id': data['id']}
+        else:
+            # only extract metadata if this is not a url_transparent result
+            data = self._call_api(endpoint, self._match_id(url))[response_key][0]
+            result = parse_func(data, url)
+
+        result['formats'] = list(self._extract_formats(data))
+        return result
+
+    def _yield_items(self, playlist_data, keys=None, parse_func=None):
+        """Subclasses using this method must set _ENTRY_IE"""
+        if parse_func is None:
+            parse_func = self._extract_song
+
+        for item_data in traverse_obj(playlist_data, (
+            *variadic(keys, (str, bytes, dict, set)), lambda _, v: v['id'] and v['perma_url'],
+        )):
+            info = parse_func(item_data)
+            url = smuggle_url(info['webpage_url'], traverse_obj(item_data, {
+                'id': ('id', {str}),
+                'encrypted_media_url': ((None, 'more_info'), 'encrypted_media_url', {str}, any),
+            }))
+            yield self.url_result(url, self._ENTRY_IE, url_transparent=True, **info)
 
 
 class JioSaavnSongIE(JioSaavnBaseIE):
     IE_NAME = 'jiosaavn:song'
-    _VALID_URL = r'https?://(?:www\.)?(?:jiosaavn\.com/song/[^/?#]+/|saavn\.com/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'(?:/song/[^/?#]+/|/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.jiosaavn.com/song/leja-re/OQsEfQFVUXk',
         'md5': '3b84396d15ed9e083c3106f1fa589c04',
@@ -106,12 +172,38 @@ class JioSaavnSongIE(JioSaavnBaseIE):
             'ext': 'm4a',
             'title': 'Leja Re',
             'album': 'Leja Re',
-            'thumbnail': r're:https?://c.saavncdn.com/258/Leja-Re-Hindi-2018-20181124024539-500x500.jpg',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'duration': 205,
             'view_count': int,
             'release_year': 2018,
             'artists': ['Sandesh Shandilya', 'Dhvani Bhanushali', 'Tanishk Bagchi'],
             '_old_archive_ids': ['jiosaavnsong OQsEfQFVUXk'],
+            'channel': 'T-Series',
+            'language': 'hin',
+            'channel_id': '34297',
+            'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
+            'release_date': '20181124',
+        },
+    }, {
+        'url': 'https://www.jiosaavn.com/song/chuttamalle/P1FfWjZkQ0Q',
+        'md5': '96296c58d6ce488a417ef0728fd2d680',
+        'info_dict': {
+            'id': 'O94kBTtw',
+            'display_id': 'P1FfWjZkQ0Q',
+            'ext': 'm4a',
+            'title': 'Chuttamalle',
+            'album': 'Devara Part 1 - Telugu',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'duration': 222,
+            'view_count': int,
+            'release_year': 2024,
+            'artists': 'count:3',
+            '_old_archive_ids': ['jiosaavnsong P1FfWjZkQ0Q'],
+            'channel': 'T-Series',
+            'language': 'tel',
+            'channel_id': '34297',
+            'channel_url': 'https://www.jiosaavn.com/label/t-series-albums/6DLuXO3VoTo_',
+            'release_date': '20240926',
         },
     }, {
         'url': 'https://www.saavn.com/s/song/hindi/Saathiya/O-Humdum-Suniyo-Re/KAMiazoCblU',
@@ -119,26 +211,51 @@ class JioSaavnSongIE(JioSaavnBaseIE):
     }]
 
     def _real_extract(self, url):
-        url, smuggled_data = unsmuggle_url(url)
-        song_data = traverse_obj(smuggled_data, ({
-            'id': ('id', {str}),
-            'encrypted_media_url': ('encrypted_media_url', {str}),
-        }))
+        return self._extract_jiosaavn_result(url, 'song', 'songs', self._extract_song)
 
-        if 'id' in song_data and 'encrypted_media_url' in song_data:
-            result = {'id': song_data['id']}
-        else:
-            # only extract metadata if this is not a url_transparent result
-            song_data = self._call_api('song', self._match_id(url))['songs'][0]
-            result = self._extract_song(song_data, url)
 
-        result['formats'] = list(self._extract_formats(song_data))
-        return result
+class JioSaavnShowIE(JioSaavnBaseIE):
+    IE_NAME = 'jiosaavn:show'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/shows/[^/?#]+/(?P<id>[^/?#]{11,})/?(?:$|[?#])'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/shows/non-food-ways-to-boost-your-energy/XFMcKICOCgc_',
+        'md5': '0733cd254cfe74ef88bea1eaedcf1f4f',
+        'info_dict': {
+            'id': 'qqzh3RKZ',
+            'display_id': 'XFMcKICOCgc_',
+            'ext': 'mp3',
+            'title': 'Non-Food Ways To Boost Your Energy',
+            'description': 'md5:26e7129644b5c6aada32b8851c3997c8',
+            'episode': 'Episode 1',
+            'timestamp': 1640563200,
+            'series': 'Holistic Lifestyle With Neha Ranglani',
+            'series_id': '52397',
+            'season': 'Holistic Lifestyle With Neha Ranglani',
+            'season_number': 1,
+            'season_id': '61273',
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'duration': 311,
+            'view_count': int,
+            'release_year': 2021,
+            'language': 'eng',
+            'channel': 'Saavn OG',
+            'channel_id': '1953876',
+            'episode_number': 1,
+            'upload_date': '20211227',
+            'release_date': '20211227',
+        },
+    }, {
+        'url': 'https://www.jiosaavn.com/shows/himesh-reshammiya/Kr8fmfSN4vo_',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        return self._extract_jiosaavn_result(url, 'episode', 'episodes', self._extract_episode)
 
 
 class JioSaavnAlbumIE(JioSaavnBaseIE):
     IE_NAME = 'jiosaavn:album'
-    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/album/[^/?#]+/(?P<id>[^/?#]+)'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/album/[^/?#]+/(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.jiosaavn.com/album/96/buIOjYZDrNA_',
         'info_dict': {
@@ -147,18 +264,19 @@ class JioSaavnAlbumIE(JioSaavnBaseIE):
         },
         'playlist_count': 10,
     }]
+    _ENTRY_IE = JioSaavnSongIE
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         album_data = self._call_api('album', display_id)
 
         return self.playlist_result(
-            self._yield_songs(album_data), display_id, traverse_obj(album_data, ('title', {str})))
+            self._yield_items(album_data, 'songs'), display_id, traverse_obj(album_data, ('title', {str})))
 
 
 class JioSaavnPlaylistIE(JioSaavnBaseIE):
     IE_NAME = 'jiosaavn:playlist'
-    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/(?:s/playlist/(?:[^/?#]+/){2}|featured/[^/?#]+/)(?P<id>[^/?#]+)'
     _TESTS = [{
         'url': 'https://www.jiosaavn.com/s/playlist/2279fbe391defa793ad7076929a2f5c9/mood-english/LlJ8ZWT1ibN5084vKHRj2Q__',
         'info_dict': {
@@ -172,15 +290,16 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
             'id': 'DVR,pFUOwyXqIp77B1JF,A__',
             'title': 'Mood Hindi',
         },
-        'playlist_mincount': 801,
+        'playlist_mincount': 750,
     }, {
         'url': 'https://www.jiosaavn.com/featured/taaza-tunes/Me5RridRfDk_',
         'info_dict': {
             'id': 'Me5RridRfDk_',
             'title': 'Taaza Tunes',
         },
-        'playlist_mincount': 301,
+        'playlist_mincount': 50,
     }]
+    _ENTRY_IE = JioSaavnSongIE
     _PAGE_SIZE = 50
 
     def _fetch_page(self, token, page):
@@ -189,7 +308,7 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
 
     def _entries(self, token, first_page_data, page):
         page_data = first_page_data if not page else self._fetch_page(token, page + 1)
-        yield from self._yield_songs(page_data)
+        yield from self._yield_items(page_data, 'songs')
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
@@ -199,3 +318,95 @@ class JioSaavnPlaylistIE(JioSaavnBaseIE):
         return self.playlist_result(InAdvancePagedList(
             functools.partial(self._entries, display_id, playlist_data),
             total_pages, self._PAGE_SIZE), display_id, traverse_obj(playlist_data, ('listname', {str})))
+
+
+class JioSaavnShowPlaylistIE(JioSaavnBaseIE):
+    IE_NAME = 'jiosaavn:show:playlist'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/shows/(?P<show>[^#/?]+)/(?P<season>\d+)/[^/?#]+'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/shows/talking-music/1/PjReFP-Sguk_',
+        'info_dict': {
+            'id': 'talking-music-1',
+            'title': 'Talking Music',
+        },
+        'playlist_mincount': 11,
+    }]
+    _ENTRY_IE = JioSaavnShowIE
+    _PAGE_SIZE = 10
+
+    def _fetch_page(self, show_id, season_id, page):
+        return self._call_api('show', show_id, f'show page {page}', {
+            'p': page,
+            '__call': 'show.getAllEpisodes',
+            'show_id': show_id,
+            'season_number': season_id,
+            'api_version': '4',
+            'sort_order': 'desc',
+        })
+
+    def _entries(self, show_id, season_id, page):
+        page_data = self._fetch_page(show_id, season_id, page + 1)
+        yield from self._yield_items(page_data, keys=None, parse_func=self._extract_episode)
+
+    def _real_extract(self, url):
+        show_slug, season_id = self._match_valid_url(url).group('show', 'season')
+        playlist_id = f'{show_slug}-{season_id}'
+        webpage = self._download_webpage(url, playlist_id)
+
+        show_info = self._search_json(
+            r'window\.__INITIAL_DATA__\s*=', webpage, 'initial data',
+            playlist_id, transform_source=js_to_json)['showView']
+        show_id = show_info['current_id']
+
+        entries = OnDemandPagedList(functools.partial(self._entries, show_id, season_id), self._PAGE_SIZE)
+        return self.playlist_result(
+            entries, playlist_id, traverse_obj(show_info, ('show', 'title', 'text', {str})))
+
+
+class JioSaavnArtistIE(JioSaavnBaseIE):
+    IE_NAME = 'jiosaavn:artist'
+    _VALID_URL = JioSaavnBaseIE._URL_BASE_RE + r'/artist/[^/?#]+/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/artist/krsna-songs/rYLBEve2z3U_',
+        'info_dict': {
+            'id': 'rYLBEve2z3U_',
+            'title': 'KR$NA',
+        },
+        'playlist_mincount': 38,
+    }, {
+        'url': 'https://www.jiosaavn.com/artist/sanam-puri-songs/SkNEv3qRhDE_',
+        'info_dict': {
+            'id': 'SkNEv3qRhDE_',
+            'title': 'Sanam Puri',
+        },
+        'playlist_mincount': 51,
+    }]
+    _ENTRY_IE = JioSaavnSongIE
+    _PAGE_SIZE = 50
+
+    def _fetch_page(self, artist_id, page):
+        return self._call_api('artist', artist_id, f'artist page {page + 1}', {
+            'p': page,
+            'n_song': self._PAGE_SIZE,
+            'n_album': self._PAGE_SIZE,
+            'sub_type': '',
+            'includeMetaTags': '',
+            'api_version': '4',
+            'category': 'alphabetical',
+            'sort_order': 'asc',
+        })
+
+    def _entries(self, artist_id, first_page):
+        for page in itertools.count():
+            playlist_data = first_page if not page else self._fetch_page(artist_id, page)
+            if not traverse_obj(playlist_data, ('topSongs', ..., {dict})):
+                break
+            yield from self._yield_items(playlist_data, 'topSongs')
+
+    def _real_extract(self, url):
+        artist_id = self._match_id(url)
+        first_page = self._fetch_page(artist_id, 0)
+
+        return self.playlist_result(
+            self._entries(artist_id, first_page), artist_id,
+            traverse_obj(first_page, ('name', {str})))

yt_dlp/extractor/lrt.py

@@ -2,7 +2,6 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     merge_dicts,
-    str_or_none,
     traverse_obj,
     unified_timestamp,
     url_or_none,
@@ -138,13 +137,15 @@ class LRTRadioIE(LRTBaseIE):
             'https://www.lrt.lt/radioteka/api/media', video_id,
             query={'url': f'/mediateka/irasas/{video_id}/{path}'})
 
-        return traverse_obj(media, {
-            'id': ('id', {int}, {str_or_none}),
-            'title': ('title', {str}),
-            'tags': ('tags', ..., 'name', {str}),
-            'categories': ('playlist_item', 'category', {str}, filter, all, filter),
-            'description': ('content', {clean_html}, {str}),
-            'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
-            'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
-            'formats': ('playlist_item', 'file', {lambda x: self._extract_m3u8_formats(x, video_id)}),
-        })
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(media['playlist_item']['file'], video_id),
+            **traverse_obj(media, {
+                'title': ('title', {str}),
+                'tags': ('tags', ..., 'name', {str}),
+                'categories': ('playlist_item', 'category', {str}, filter, all, filter),
+                'description': ('content', {clean_html}, {str}),
+                'timestamp': ('date', {lambda x: x.replace('.', '/')}, {unified_timestamp}),
+                'thumbnail': ('playlist_item', 'image', {urljoin('https://www.lrt.lt')}),
+            }),
+        }

yt_dlp/extractor/nebula.py

@@ -3,6 +3,7 @@ import json
 
 from .art19 import Art19IE
 from .common import InfoExtractor
+from ..networking import PATCHRequest
 from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
@@ -74,7 +75,7 @@ class NebulaBaseIE(InfoExtractor):
                         'app_version': '23.10.0',
                         'platform': 'ios',
                     })
-                return {'formats': fmts, 'subtitles': subs}
+                break
             except ExtractorError as e:
                 if isinstance(e.cause, HTTPError) and e.cause.status == 401:
                     self.raise_login_required()
@@ -84,6 +85,9 @@ class NebulaBaseIE(InfoExtractor):
                     continue
                 raise
 
+        self.mark_watched(content_id, slug)
+        return {'formats': fmts, 'subtitles': subs}
+
     def _extract_video_metadata(self, episode):
         channel_url = traverse_obj(
             episode, (('channel_slug', 'class_slug'), {urljoin('https://nebula.tv/')}), get_all=False)
@@ -111,6 +115,13 @@ class NebulaBaseIE(InfoExtractor):
             'uploader_url': channel_url,
         }
 
+    def _mark_watched(self, content_id, slug):
+        self._call_api(
+            PATCHRequest(f'https://content.api.nebula.app/{content_id.split(":")[0]}s/{content_id}/progress/'),
+            slug, 'Marking watched', 'Unable to mark watched', fatal=False,
+            data=json.dumps({'completed': True}).encode(),
+            headers={'content-type': 'application/json'})
+
 
 class NebulaIE(NebulaBaseIE):
     IE_NAME = 'nebula:video'
@@ -322,6 +333,7 @@ class NebulaClassIE(NebulaBaseIE):
             if not episode_url and metadata.get('premium'):
                 self.raise_login_required()
 
+            self.mark_watched(metadata['id'], slug)
             if Art19IE.suitable(episode_url):
                 return self.url_result(episode_url, Art19IE)
             return traverse_obj(metadata, {

yt_dlp/extractor/niconico.py

@@ -16,6 +16,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    parse_bitrate,
     parse_duration,
     parse_iso8601,
     parse_qs,
@@ -23,7 +24,6 @@ from ..utils import (
     qualities,
     remove_start,
     str_or_none,
-    try_get,
     unescapeHTML,
     unified_timestamp,
     update_url_query,
@@ -32,7 +32,7 @@ from ..utils import (
     urlencode_postdata,
     urljoin,
 )
-from ..utils.traversal import find_element, traverse_obj
+from ..utils.traversal import find_element, require, traverse_obj
 
 
 class NiconicoBaseIE(InfoExtractor):
@@ -283,35 +283,54 @@ class NiconicoIE(NiconicoBaseIE):
                 lambda _, v: v['id'] == video_fmt['format_id'], 'qualityLevel', {int_or_none}, any)) or -1
             yield video_fmt
 
+    def _extract_server_response(self, webpage, video_id, fatal=True):
+        try:
+            return traverse_obj(
+                self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
+                ('data', 'response', {dict}, {require('server response')}))
+        except ExtractorError:
+            if not fatal:
+                return {}
+            raise
+
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         try:
             webpage, handle = self._download_webpage_handle(
-                'https://www.nicovideo.jp/watch/' + video_id, video_id)
+                f'https://www.nicovideo.jp/watch/{video_id}', video_id,
+                headers=self.geo_verification_headers())
             if video_id.startswith('so'):
                 video_id = self._match_id(handle.url)
 
-            api_data = traverse_obj(
-                self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
-                ('data', 'response', {dict}))
-            if not api_data:
-                raise ExtractorError('Server response data not found')
+            api_data = self._extract_server_response(webpage, video_id)
         except ExtractorError as e:
             try:
                 api_data = self._download_json(
-                    f'https://www.nicovideo.jp/api/watch/v3/{video_id}?_frontendId=6&_frontendVersion=0&actionTrackId=AAAAAAAAAA_{round(time.time() * 1000)}', video_id,
-                    note='Downloading API JSON', errnote='Unable to fetch data')['data']
+                    f'https://www.nicovideo.jp/api/watch/v3/{video_id}', video_id,
+                    'Downloading API JSON', 'Unable to fetch data', query={
+                        '_frontendId': '6',
+                        '_frontendVersion': '0',
+                        'actionTrackId': f'AAAAAAAAAA_{round(time.time() * 1000)}',
+                    }, headers=self.geo_verification_headers())['data']
             except ExtractorError:
                 if not isinstance(e.cause, HTTPError):
+                    # Raise if original exception was from _parse_json or utils.traversal.require
                     raise
+                # The webpage server response has more detailed error info than the API response
                 webpage = e.cause.response.read().decode('utf-8', 'replace')
-                error_msg = self._html_search_regex(
-                    r'(?s)<section\s+class="(?:(?:ErrorMessage|WatchExceptionPage-message)\s*)+">(.+?)</section>',
-                    webpage, 'error reason', default=None)
-                if not error_msg:
+                reason_code = self._extract_server_response(
+                    webpage, video_id, fatal=False).get('reasonCode')
+                if not reason_code:
                     raise
-                raise ExtractorError(clean_html(error_msg), expected=True)
+                if reason_code in ('DOMESTIC_VIDEO', 'HIGH_RISK_COUNTRY_VIDEO'):
+                    self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+                elif reason_code == 'HIDDEN_VIDEO':
+                    raise ExtractorError(
+                        'The viewing period of this video has expired', expected=True)
+                elif reason_code == 'DELETED_VIDEO':
+                    raise ExtractorError('This video has been deleted', expected=True)
+                raise ExtractorError(f'Niconico says: {reason_code}')
 
         availability = self._availability(**(traverse_obj(api_data, ('payment', 'video', {
             'needs_premium': ('isPremium', {bool}),
@@ -785,8 +804,6 @@ class NiconicoLiveIE(NiconicoBaseIE):
         'only_matching': True,
     }]
 
-    _KNOWN_LATENCY = ('high', 'low')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
@@ -802,22 +819,19 @@ class NiconicoLiveIE(NiconicoBaseIE):
         })
 
         hostname = remove_start(urllib.parse.urlparse(urlh.url).hostname, 'sp.')
-        latency = try_get(self._configuration_arg('latency'), lambda x: x[0])
-        if latency not in self._KNOWN_LATENCY:
-            latency = 'high'
 
         ws = self._request_webpage(
             Request(ws_url, headers={'Origin': f'https://{hostname}'}),
             video_id=video_id, note='Connecting to WebSocket server')
 
-        self.write_debug('[debug] Sending HLS server request')
+        self.write_debug('Sending HLS server request')
         ws.send(json.dumps({
             'type': 'startWatching',
             'data': {
                 'stream': {
                     'quality': 'abr',
-                    'protocol': 'hls+fmp4',
-                    'latency': latency,
+                    'protocol': 'hls',
+                    'latency': 'high',
                     'accessRightMethod': 'single_cookie',
                     'chasePlay': False,
                 },
@@ -881,18 +895,29 @@ class NiconicoLiveIE(NiconicoBaseIE):
         for cookie in cookies:
             self._set_cookie(
                 cookie['domain'], cookie['name'], cookie['value'],
-                expire_time=unified_timestamp(cookie['expires']), path=cookie['path'], secure=cookie['secure'])
+                expire_time=unified_timestamp(cookie.get('expires')), path=cookie['path'], secure=cookie['secure'])
+
+        fmt_common = {
+            'live_latency': 'high',
+            'origin': hostname,
+            'protocol': 'niconico_live',
+            'video_id': video_id,
+            'ws': ws,
+        }
+        q_iter = (q for q in qualities[1:] if not q.startswith('audio_'))  # ignore initial 'abr'
+        a_map = {96: 'audio_low', 192: 'audio_high'}
 
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
-        for fmt, q in zip(formats, reversed(qualities[1:])):
-            fmt.update({
-                'format_id': q,
-                'protocol': 'niconico_live',
-                'ws': ws,
-                'video_id': video_id,
-                'live_latency': latency,
-                'origin': hostname,
-            })
+        for fmt in formats:
+            if fmt.get('acodec') == 'none':
+                fmt['format_id'] = next(q_iter, fmt['format_id'])
+            elif fmt.get('vcodec') == 'none':
+                abr = parse_bitrate(fmt['url'].lower())
+                fmt.update({
+                    'abr': abr,
+                    'format_id': a_map.get(abr, fmt['format_id']),
+                })
+            fmt.update(fmt_common)
 
         return {
             'id': video_id,

yt_dlp/extractor/nytimes.py

@@ -181,6 +181,7 @@ class NYTimesArticleIE(NYTimesBaseIE):
             'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
             'duration': 119.0,
         },
+        'skip': 'HTTP Error 500: Internal Server Error',
     }, {
         # article with audio and no video
         'url': 'https://www.nytimes.com/2023/09/29/health/mosquitoes-genetic-engineering.html',
@@ -190,13 +191,14 @@ class NYTimesArticleIE(NYTimesBaseIE):
             'ext': 'mp3',
             'title': 'The Gamble: Can Genetically Modified Mosquitoes End Disease?',
             'description': 'md5:9ff8b47acbaf7f3ca8c732f5c815be2e',
-            'timestamp': 1695960700,
+            'timestamp': 1696008129,
             'upload_date': '20230929',
-            'creator': 'Stephanie Nolen, Natalija Gormalova',
+            'creators': ['Stephanie Nolen', 'Natalija Gormalova'],
             'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
             'duration': 1322,
         },
     }, {
+        # lede_media_block already has sourceId
         'url': 'https://www.nytimes.com/2023/11/29/business/dealbook/kamala-harris-biden-voters.html',
         'md5': '3eb5ddb1d6f86254fe4f233826778737',
         'info_dict': {
@@ -207,7 +209,7 @@ class NYTimesArticleIE(NYTimesBaseIE):
             'timestamp': 1701290997,
             'upload_date': '20231129',
             'uploader': 'By The New York Times',
-            'creator': 'Katie Rogers',
+            'creators': ['Katie Rogers'],
             'thumbnail': r're:https?://\w+\.nyt.com/images/.*\.jpg',
             'duration': 97.631,
         },
@@ -222,10 +224,22 @@ class NYTimesArticleIE(NYTimesBaseIE):
             'title': 'Drunk and Asleep on the Job: Air Traffic Controllers Pushed to the Brink',
             'description': 'md5:549e5a5e935bf7d048be53ba3d2c863d',
             'upload_date': '20231202',
-            'creator': 'Emily Steel, Sydney Ember',
+            'creators': ['Emily Steel', 'Sydney Ember'],
             'timestamp': 1701511264,
         },
         'playlist_count': 3,
+    }, {
+        # lede_media_block does not have sourceId
+        'url': 'https://www.nytimes.com/2025/04/30/well/move/hip-mobility-routine.html',
+        'info_dict': {
+            'id': 'hip-mobility-routine',
+            'title': 'Tight Hips? These Moves Can Help.',
+            'description': 'Sitting all day is hard on your hips. Try this simple routine for better mobility.',
+            'creators': ['Alyssa Ages', 'Theodore Tae'],
+            'timestamp': 1746003629,
+            'upload_date': '20250430',
+        },
+        'playlist_count': 7,
     }, {
         'url': 'https://www.nytimes.com/2023/12/02/business/media/netflix-squid-game-challenge.html',
         'only_matching': True,
@@ -256,14 +270,18 @@ class NYTimesArticleIE(NYTimesBaseIE):
 
     def _real_extract(self, url):
         page_id = self._match_id(url)
-        webpage = self._download_webpage(url, page_id)
+        webpage = self._download_webpage(url, page_id, impersonate=True)
         art_json = self._search_json(
             r'window\.__preloadedData\s*=', webpage, 'media details', page_id,
             transform_source=lambda x: x.replace('undefined', 'null'))['initialData']['data']['article']
+        content = art_json['sprinkledBody']['content']
 
-        blocks = traverse_obj(art_json, (
-            'sprinkledBody', 'content', ..., ('ledeMedia', None),
-            lambda _, v: v['__typename'] in ('Video', 'Audio')))
+        blocks = []
+        block_filter = lambda k, v: k == 'media' and v['__typename'] in ('Video', 'Audio')
+        if lede_media_block := traverse_obj(content, (..., 'ledeMedia', block_filter, any)):
+            lede_media_block.setdefault('sourceId', art_json.get('sourceId'))
+            blocks.append(lede_media_block)
+        blocks.extend(traverse_obj(content, (..., block_filter)))
         if not blocks:
             raise ExtractorError('Unable to extract any media blocks from webpage')
 
@@ -273,8 +291,7 @@ class NYTimesArticleIE(NYTimesBaseIE):
                 'sprinkledBody', 'content', ..., 'summary', 'content', ..., 'text', {str}),
                 get_all=False) or self._html_search_meta(['og:description', 'twitter:description'], webpage),
             'timestamp': traverse_obj(art_json, ('firstPublished', {parse_iso8601})),
-            'creator': ', '.join(
-                traverse_obj(art_json, ('bylines', ..., 'creators', ..., 'displayName'))),  # TODO: change to 'creators' (list)
+            'creators': traverse_obj(art_json, ('bylines', ..., 'creators', ..., 'displayName', {str})),
             'thumbnails': self._extract_thumbnails(traverse_obj(
                 art_json, ('promotionalMedia', 'assetCrops', ..., 'renditions', ...))),
         }

yt_dlp/extractor/once.py

@@ -1,40 +0,0 @@
-import re
-
-from .common import InfoExtractor
-
-
-class OnceIE(InfoExtractor):  # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
-    _VALID_URL = r'https?://.+?\.unicornmedia\.com/now/(?:ads/vmap/)?[^/]+/[^/]+/(?P<domain_id>[^/]+)/(?P<application_id>[^/]+)/(?:[^/]+/)?(?P<media_item_id>[^/]+)/content\.(?:once|m3u8|mp4)'
-    ADAPTIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/master/playlist/%s/%s/%s/content.m3u8'
-    PROGRESSIVE_URL_TEMPLATE = 'http://once.unicornmedia.com/now/media/progressive/%s/%s/%s/%s/content.mp4'
-
-    def _extract_once_formats(self, url, http_formats_preference=None):
-        domain_id, application_id, media_item_id = re.match(
-            OnceIE._VALID_URL, url).groups()
-        formats = self._extract_m3u8_formats(
-            self.ADAPTIVE_URL_TEMPLATE % (
-                domain_id, application_id, media_item_id),
-            media_item_id, 'mp4', m3u8_id='hls', fatal=False)
-        progressive_formats = []
-        for adaptive_format in formats:
-            # Prevent advertisement from embedding into m3u8 playlist (see
-            # https://github.com/ytdl-org/youtube-dl/issues/8893#issuecomment-199912684)
-            adaptive_format['url'] = re.sub(
-                r'\badsegmentlength=\d+', r'adsegmentlength=0', adaptive_format['url'])
-            rendition_id = self._search_regex(
-                r'/now/media/playlist/[^/]+/[^/]+/([^/]+)',
-                adaptive_format['url'], 'redition id', default=None)
-            if rendition_id:
-                progressive_format = adaptive_format.copy()
-                progressive_format.update({
-                    'url': self.PROGRESSIVE_URL_TEMPLATE % (
-                        domain_id, application_id, rendition_id, media_item_id),
-                    'format_id': adaptive_format['format_id'].replace(
-                        'hls', 'http'),
-                    'protocol': 'http',
-                    'preference': http_formats_preference,
-                })
-                progressive_formats.append(progressive_format)
-        self._check_formats(progressive_formats, media_item_id)
-        formats.extend(progressive_formats)
-        return formats

yt_dlp/extractor/picarto.py

@@ -10,7 +10,8 @@ from ..utils import (
 
 
 class PicartoIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[a-zA-Z0-9]+)'
+    IE_NAME = 'picarto'
+    _VALID_URL = r'https?://(?:www.)?picarto\.tv/(?P<id>[^/#?]+)/?(?:$|[?#])'
     _TEST = {
         'url': 'https://picarto.tv/Setz',
         'info_dict': {
@@ -89,7 +90,8 @@ class PicartoIE(InfoExtractor):
 
 
 class PicartoVodIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+/videos)/(?P<id>[^/?#&]+)'
+    IE_NAME = 'picarto:vod'
+    _VALID_URL = r'https?://(?:www\.)?picarto\.tv/(?:videopopout|\w+(?:/profile)?/videos)/(?P<id>[^/?#&]+)'
     _TESTS = [{
         'url': 'https://picarto.tv/videopopout/ArtofZod_2017.12.12.00.13.23.flv',
         'md5': '3ab45ba4352c52ee841a28fb73f2d9ca',
@@ -111,6 +113,18 @@ class PicartoVodIE(InfoExtractor):
             'channel': 'ArtofZod',
             'age_limit': 18,
         },
+    }, {
+        'url': 'https://picarto.tv/DrechuArt/profile/videos/400347',
+        'md5': 'f9ea54868b1d9dec40eb554b484cc7bf',
+        'info_dict': {
+            'id': '400347',
+            'ext': 'mp4',
+            'title': 'Welcome to the Show',
+            'thumbnail': r're:^https?://.*\.jpg',
+            'channel': 'DrechuArt',
+            'age_limit': 0,
+        },
+
     }, {
         'url': 'https://picarto.tv/videopopout/Plague',
         'only_matching': True,

yt_dlp/extractor/playsuisse.py

@@ -7,11 +7,12 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     parse_qs,
-    traverse_obj,
     update_url_query,
     urlencode_postdata,
 )
+from ..utils.traversal import traverse_obj, unpack
 
 
 class PlaySuisseIE(InfoExtractor):
@@ -26,12 +27,12 @@ class PlaySuisseIE(InfoExtractor):
         {
             # episode in a series
             'url': 'https://www.playsuisse.ch/watch/763182?episodeId=763211',
-            'md5': '82df2a470b2dfa60c2d33772a8a60cf8',
+            'md5': 'e20d1ede6872a03b41905ca1060a1ef2',
             'info_dict': {
                 'id': '763211',
                 'ext': 'mp4',
                 'title': 'Knochen',
-                'description': 'md5:8ea7a8076ba000cd9e8bc132fd0afdd8',
+                'description': 'md5:3bdd80e2ce20227c47aab1df2a79a519',
                 'duration': 3344,
                 'series': 'Wilder',
                 'season': 'Season 1',
@@ -42,24 +43,33 @@ class PlaySuisseIE(InfoExtractor):
             },
         }, {
             # film
-            'url': 'https://www.playsuisse.ch/watch/808675',
-            'md5': '818b94c1d2d7c4beef953f12cb8f3e75',
+            'url': 'https://www.playsuisse.ch/detail/2573198',
+            'md5': '1f115bb0a5191477b1a5771643a4283d',
             'info_dict': {
-                'id': '808675',
+                'id': '2573198',
                 'ext': 'mp4',
-                'title': 'Der Läufer',
-                'description': 'md5:9f61265c7e6dcc3e046137a792b275fd',
-                'duration': 5280,
+                'title': 'Azor',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'genres': ['Fiction'],
+                'creators': ['Andreas Fontana'],
+                'cast': ['Fabrizio Rongione', 'Stéphanie Cléau', 'Gilles Privat', 'Alexandre Trocki'],
+                'location': 'France; Argentine',
+                'release_year': 2021,
+                'duration': 5981,
                 'thumbnail': 're:https://playsuisse-img.akamaized.net/',
             },
         }, {
             # series (treated as a playlist)
             'url': 'https://www.playsuisse.ch/detail/1115687',
             'info_dict': {
-                'description': 'md5:e4a2ae29a8895823045b5c3145a02aa3',
                 'id': '1115687',
                 'series': 'They all came out to Montreux',
                 'title': 'They all came out to Montreux',
+                'description': 'md5:0fefd8c5b4468a0bb35e916887681520',
+                'genres': ['Documentary'],
+                'creators': ['Oliver Murray'],
+                'location': 'Switzerland',
+                'release_year': 2021,
             },
             'playlist': [{
                 'info_dict': {
@@ -120,6 +130,12 @@ class PlaySuisseIE(InfoExtractor):
             id
             name
             description
+            descriptionLong
+            year
+            contentTypes
+            directors
+            mainCast
+            productionCountries
             duration
             episodeNumber
             seasonNumber
@@ -215,9 +231,7 @@ class PlaySuisseIE(InfoExtractor):
         if not self._ID_TOKEN:
             raise ExtractorError('Login failed')
 
-    def _get_media_data(self, media_id):
-        # NOTE In the web app, the "locale" header is used to switch between languages,
-        # However this doesn't seem to take effect when passing the header here.
+    def _get_media_data(self, media_id, locale=None):
         response = self._download_json(
             'https://www.playsuisse.ch/api/graphql',
             media_id, data=json.dumps({
@@ -225,7 +239,7 @@ class PlaySuisseIE(InfoExtractor):
                 'query': self._GRAPHQL_QUERY,
                 'variables': {'assetId': media_id},
             }).encode(),
-            headers={'Content-Type': 'application/json', 'locale': 'de'})
+            headers={'Content-Type': 'application/json', 'locale': locale or 'de'})
 
         return response['data']['assetV2']
 
@@ -234,7 +248,7 @@ class PlaySuisseIE(InfoExtractor):
             self.raise_login_required(method='password')
 
         media_id = self._match_id(url)
-        media_data = self._get_media_data(media_id)
+        media_data = self._get_media_data(media_id, traverse_obj(parse_qs(url), ('locale', 0)))
         info = self._extract_single(media_data)
         if media_data.get('episodes'):
             info.update({
@@ -257,15 +271,22 @@ class PlaySuisseIE(InfoExtractor):
             self._merge_subtitles(subs, target=subtitles)
 
         return {
-            'id': media_data['id'],
-            'title': media_data.get('name'),
-            'description': media_data.get('description'),
             'thumbnails': thumbnails,
-            'duration': int_or_none(media_data.get('duration')),
             'formats': formats,
             'subtitles': subtitles,
-            'series': media_data.get('seriesName'),
-            'season_number': int_or_none(media_data.get('seasonNumber')),
-            'episode': media_data.get('name') if media_data.get('episodeNumber') else None,
-            'episode_number': int_or_none(media_data.get('episodeNumber')),
+            **traverse_obj(media_data, {
+                'id': ('id', {str}),
+                'title': ('name', {str}),
+                'description': (('descriptionLong', 'description'), {str}, any),
+                'genres': ('contentTypes', ..., {str}),
+                'creators': ('directors', ..., {str}),
+                'cast': ('mainCast', ..., {str}),
+                'location': ('productionCountries', ..., {str}, all, {unpack(join_nonempty, delim='; ')}, filter),
+                'release_year': ('year', {str}, {lambda x: x[:4]}, {int_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'series': ('seriesName', {str}),
+                'season_number': ('seasonNumber', {int_or_none}),
+                'episode': ('name', {str}, {lambda x: x if media_data['episodeNumber'] is not None else None}),
+                'episode_number': ('episodeNumber', {int_or_none}),
+            }),
         }

yt_dlp/extractor/soundcloud.py

@@ -697,7 +697,7 @@ class SoundcloudIE(SoundcloudBaseIE):
             try:
                 return self._extract_info_dict(info, full_title, token)
             except ExtractorError as e:
-                if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
+                if not isinstance(e.cause, HTTPError) or e.cause.status != 429:
                     raise
                 self.report_warning(
                     'You have reached the API rate limit, which is ~600 requests per '

yt_dlp/extractor/sprout.py

@@ -1,61 +0,0 @@
-from .adobepass import AdobePassIE
-from ..utils import (
-    int_or_none,
-    smuggle_url,
-    update_url_query,
-)
-
-
-class SproutIE(AdobePassIE):
-    _VALID_URL = r'https?://(?:www\.)?(?:sproutonline|universalkids)\.com/(?:watch|(?:[^/]+/)*videos)/(?P<id>[^/?#]+)'
-    _TESTS = [{
-        'url': 'https://www.universalkids.com/shows/remy-and-boo/season/1/videos/robot-bike-race',
-        'info_dict': {
-            'id': 'bm0foJFaTKqb',
-            'ext': 'mp4',
-            'title': 'Robot Bike Race',
-            'description': 'md5:436b1d97117cc437f54c383f4debc66d',
-            'timestamp': 1606148940,
-            'upload_date': '20201123',
-            'uploader': 'NBCU-MPAT',
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }, {
-        'url': 'http://www.sproutonline.com/watch/cowboy-adventure',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.universalkids.com/watch/robot-bike-race',
-        'only_matching': True,
-    }]
-    _GEO_COUNTRIES = ['US']
-
-    def _real_extract(self, url):
-        display_id = self._match_id(url)
-        mpx_metadata = self._download_json(
-            # http://nbcuunikidsprod.apps.nbcuni.com/networks/universalkids/content/videos/
-            'https://www.universalkids.com/_api/videos/' + display_id,
-            display_id)['mpxMetadata']
-        media_pid = mpx_metadata['mediaPid']
-        theplatform_url = 'https://link.theplatform.com/s/HNK2IC/' + media_pid
-        query = {
-            'mbr': 'true',
-            'manifest': 'm3u',
-        }
-        if mpx_metadata.get('entitlement') == 'auth':
-            query['auth'] = self._extract_mvpd_auth(url, media_pid, 'sprout', 'sprout')
-        theplatform_url = smuggle_url(
-            update_url_query(theplatform_url, query), {
-                'force_smil_url': True,
-                'geo_countries': self._GEO_COUNTRIES,
-            })
-        return {
-            '_type': 'url_transparent',
-            'id': media_pid,
-            'url': theplatform_url,
-            'series': mpx_metadata.get('seriesName'),
-            'season_number': int_or_none(mpx_metadata.get('seasonNumber')),
-            'episode_number': int_or_none(mpx_metadata.get('episodeNumber')),
-            'ie_key': 'ThePlatform',
-        }

yt_dlp/extractor/svt.py

@@ -471,8 +471,7 @@ class SVTPageIE(SVTBaseIE):
         webpage = self._download_webpage(url, display_id)
         title = self._og_search_title(webpage)
 
-        urql_state = self._search_json(
-            r'window\.svt\.(?:nyh\.)?urqlState\s*=', webpage, 'json data', display_id)
+        urql_state = self._search_json(r'urqlState\s*[=:]', webpage, 'json data', display_id)
 
         data = traverse_obj(urql_state, (..., 'data', {str}, {json.loads}), get_all=False) or {}
 

yt_dlp/extractor/theplatform.py

@@ -4,7 +4,6 @@ import re
 import time
 
 from .adobepass import AdobePassIE
-from .once import OnceIE
 from ..networking import HEADRequest, Request
 from ..utils import (
     ExtractorError,
@@ -26,7 +25,7 @@ default_ns = 'http://www.w3.org/2005/SMIL21/Language'
 _x = lambda p: xpath_with_ns(p, {'smil': default_ns})
 
 
-class ThePlatformBaseIE(OnceIE):
+class ThePlatformBaseIE(AdobePassIE):
     _TP_TLD = 'com'
 
     def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL data'):
@@ -54,16 +53,13 @@ class ThePlatformBaseIE(OnceIE):
 
         formats = []
         for _format in smil_formats:
-            if OnceIE.suitable(_format['url']):
-                formats.extend(self._extract_once_formats(_format['url']))
-            else:
-                media_url = _format['url']
-                if determine_ext(media_url) == 'm3u8':
-                    hdnea2 = self._get_cookies(media_url).get('hdnea2')
-                    if hdnea2:
-                        _format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
+            media_url = _format['url']
+            if determine_ext(media_url) == 'm3u8':
+                hdnea2 = self._get_cookies(media_url).get('hdnea2')
+                if hdnea2:
+                    _format['url'] = update_url_query(media_url, {'hdnea3': hdnea2.value})
 
-                formats.append(_format)
+            formats.append(_format)
 
         return formats, subtitles
 
@@ -129,7 +125,7 @@ class ThePlatformBaseIE(OnceIE):
         return self._parse_theplatform_metadata(info)
 
 
-class ThePlatformIE(ThePlatformBaseIE, AdobePassIE):
+class ThePlatformIE(ThePlatformBaseIE):
     _VALID_URL = r'''(?x)
         (?:https?://(?:link|player)\.theplatform\.com/[sp]/(?P<provider_id>[^/]+)/
            (?:(?:(?:[^/]+/)+select/)?(?P<media>media/(?:guid/\d+/)?)?|(?P<config>(?:[^/\?]+/(?:swf|config)|onsite)/select/))?

yt_dlp/extractor/twitch.py

@@ -187,7 +187,7 @@ class TwitchBaseIE(InfoExtractor):
             'url': thumbnail,
         }] if thumbnail else None
 
-    def _extract_twitch_m3u8_formats(self, path, video_id, token, signature):
+    def _extract_twitch_m3u8_formats(self, path, video_id, token, signature, live_from_start=False):
         formats = self._extract_m3u8_formats(
             f'{self._USHER_BASE}/{path}/{video_id}.m3u8', video_id, 'mp4', query={
                 'allow_source': 'true',
@@ -204,7 +204,10 @@ class TwitchBaseIE(InfoExtractor):
         for fmt in formats:
             if fmt.get('vcodec') and fmt['vcodec'].startswith('av01'):
                 # mpegts does not yet have proper support for av1
-                fmt['downloader_options'] = {'ffmpeg_args_out': ['-f', 'mp4']}
+                fmt.setdefault('downloader_options', {}).update({'ffmpeg_args_out': ['-f', 'mp4']})
+            if live_from_start:
+                fmt.setdefault('downloader_options', {}).update({'ffmpeg_args': ['-live_start_index', '0']})
+                fmt['is_from_start'] = True
 
         return formats
 
@@ -550,7 +553,8 @@ class TwitchVodIE(TwitchBaseIE):
         access_token = self._download_access_token(vod_id, 'video', 'id')
 
         formats = self._extract_twitch_m3u8_formats(
-            'vod', vod_id, access_token['value'], access_token['signature'])
+            'vod', vod_id, access_token['value'], access_token['signature'],
+            live_from_start=self.get_param('live_from_start'))
         formats.extend(self._extract_storyboard(vod_id, video.get('storyboard'), info.get('duration')))
 
         self._prefer_source(formats)
@@ -633,6 +637,10 @@ class TwitchPlaylistBaseIE(TwitchBaseIE):
     _PAGE_LIMIT = 100
 
     def _entries(self, channel_name, *args):
+        """
+        Subclasses must define _make_variables() and _extract_entry(),
+        as well as set _OPERATION_NAME, _ENTRY_KIND, _EDGE_KIND, and _NODE_KIND
+        """
         cursor = None
         variables_common = self._make_variables(channel_name, *args)
         entries_key = f'{self._ENTRY_KIND}s'
@@ -672,7 +680,22 @@ class TwitchPlaylistBaseIE(TwitchBaseIE):
                 break
 
 
-class TwitchVideosIE(TwitchPlaylistBaseIE):
+class TwitchVideosBaseIE(TwitchPlaylistBaseIE):
+    _OPERATION_NAME = 'FilterableVideoTower_Videos'
+    _ENTRY_KIND = 'video'
+    _EDGE_KIND = 'VideoEdge'
+    _NODE_KIND = 'Video'
+
+    @staticmethod
+    def _make_variables(channel_name, broadcast_type, sort):
+        return {
+            'channelOwnerLogin': channel_name,
+            'broadcastType': broadcast_type,
+            'videoSort': sort.upper(),
+        }
+
+
+class TwitchVideosIE(TwitchVideosBaseIE):
     _VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:videos|profile)'
 
     _TESTS = [{
@@ -751,11 +774,6 @@ class TwitchVideosIE(TwitchPlaylistBaseIE):
         'views': 'Popular',
     }
 
-    _OPERATION_NAME = 'FilterableVideoTower_Videos'
-    _ENTRY_KIND = 'video'
-    _EDGE_KIND = 'VideoEdge'
-    _NODE_KIND = 'Video'
-
     @classmethod
     def suitable(cls, url):
         return (False
@@ -764,14 +782,6 @@ class TwitchVideosIE(TwitchPlaylistBaseIE):
                     TwitchVideosCollectionsIE))
                 else super().suitable(url))
 
-    @staticmethod
-    def _make_variables(channel_name, broadcast_type, sort):
-        return {
-            'channelOwnerLogin': channel_name,
-            'broadcastType': broadcast_type,
-            'videoSort': sort.upper(),
-        }
-
     @staticmethod
     def _extract_entry(node):
         return _make_video_result(node)
@@ -919,7 +929,7 @@ class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
             playlist_title=f'{channel_name} - Collections')
 
 
-class TwitchStreamIE(TwitchBaseIE):
+class TwitchStreamIE(TwitchVideosBaseIE):
     IE_NAME = 'twitch:stream'
     _VALID_URL = r'''(?x)
                     https?://
@@ -982,6 +992,7 @@ class TwitchStreamIE(TwitchBaseIE):
             'skip_download': 'Livestream',
         },
     }]
+    _PAGE_LIMIT = 1
 
     @classmethod
     def suitable(cls, url):
@@ -995,6 +1006,20 @@ class TwitchStreamIE(TwitchBaseIE):
                     TwitchClipsIE))
                 else super().suitable(url))
 
+    @staticmethod
+    def _extract_entry(node):
+        if not isinstance(node, dict) or not node.get('id'):
+            return None
+        video_id = node['id']
+        return {
+            '_type': 'url',
+            'ie_key': TwitchVodIE.ie_key(),
+            'id': 'v' + video_id,
+            'url': f'https://www.twitch.tv/videos/{video_id}',
+            'title': node.get('title'),
+            'timestamp': unified_timestamp(node.get('publishedAt')) or 0,
+        }
+
     def _real_extract(self, url):
         channel_name = self._match_id(url).lower()
 
@@ -1029,6 +1054,16 @@ class TwitchStreamIE(TwitchBaseIE):
         if not stream:
             raise UserNotLive(video_id=channel_name)
 
+        timestamp = unified_timestamp(stream.get('createdAt'))
+
+        if self.get_param('live_from_start'):
+            self.to_screen(f'{channel_name}: Extracting VOD to download live from start')
+            entry = next(self._entries(channel_name, None, 'time'), None)
+            if entry and entry.pop('timestamp') >= (timestamp or float('inf')):
+                return entry
+            self.report_warning(
+                'Unable to extract the VOD associated with this livestream', video_id=channel_name)
+
         access_token = self._download_access_token(
             channel_name, 'stream', 'channelName')
 
@@ -1038,7 +1073,6 @@ class TwitchStreamIE(TwitchBaseIE):
         self._prefer_source(formats)
 
         view_count = stream.get('viewers')
-        timestamp = unified_timestamp(stream.get('createdAt'))
 
         sq_user = try_get(gql, lambda x: x[1]['data']['user'], dict) or {}
         uploader = sq_user.get('displayName')

yt_dlp/extractor/twitter.py

@@ -1342,7 +1342,7 @@ class TwitterIE(TwitterBaseIE):
                     'tweet_mode': 'extended',
                 })
         except ExtractorError as e:
-            if not isinstance(e.cause, HTTPError) or not e.cause.status == 429:
+            if not isinstance(e.cause, HTTPError) or e.cause.status != 429:
                 raise
             self.report_warning('Rate-limit exceeded; falling back to syndication endpoint')
             status = self._call_syndication_api(twid)

yt_dlp/extractor/vimeo.py

@@ -3,6 +3,7 @@ import functools
 import itertools
 import json
 import re
+import time
 import urllib.parse
 
 from .common import InfoExtractor
@@ -13,10 +14,12 @@ from ..utils import (
     OnDemandPagedList,
     clean_html,
     determine_ext,
+    filter_dict,
     get_element_by_class,
     int_or_none,
     join_nonempty,
     js_to_json,
+    jwt_decode_hs256,
     merge_dicts,
     parse_filesize,
     parse_iso8601,
@@ -39,6 +42,9 @@ class VimeoBaseInfoExtractor(InfoExtractor):
     _NETRC_MACHINE = 'vimeo'
     _LOGIN_REQUIRED = False
     _LOGIN_URL = 'https://vimeo.com/log_in'
+    _REFERER_HINT = (
+        'Cannot download embed-only video without embedding URL. Please call yt-dlp '
+        'with the URL of the page that embeds this video.')
     _IOS_CLIENT_AUTH = 'MTMxNzViY2Y0NDE0YTQ5YzhjZTc0YmU0NjVjNDQxYzNkYWVjOWRlOTpHKzRvMmgzVUh4UkxjdU5FRW80cDNDbDhDWGR5dVJLNUJZZ055dHBHTTB4V1VzaG41bEx1a2hiN0NWYWNUcldSSW53dzRUdFRYZlJEZmFoTTArOTBUZkJHS3R4V2llYU04Qnl1bERSWWxUdXRidjNqR2J4SHFpVmtFSUcyRktuQw=='
     _IOS_CLIENT_HEADERS = {
         'Accept': 'application/vnd.vimeo.*+json; version=3.4.10',
@@ -47,6 +53,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
     }
     _IOS_OAUTH_CACHE_KEY = 'oauth-token-ios'
     _ios_oauth_token = None
+    _viewer_info = None
 
     @staticmethod
     def _smuggle_referrer(url, referrer_url):
@@ -60,8 +67,21 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             headers['Referer'] = data['referer']
         return url, data, headers
 
+    def _jwt_is_expired(self, token):
+        return jwt_decode_hs256(token)['exp'] - time.time() < 120
+
+    def _fetch_viewer_info(self, display_id=None, fatal=True):
+        if self._viewer_info and not self._jwt_is_expired(self._viewer_info['jwt']):
+            return self._viewer_info
+
+        self._viewer_info = self._download_json(
+            'https://vimeo.com/_next/viewer', display_id, 'Downloading web token info',
+            'Failed to download web token info', fatal=fatal, headers={'Accept': 'application/json'})
+
+        return self._viewer_info
+
     def _perform_login(self, username, password):
-        viewer = self._download_json('https://vimeo.com/_next/viewer', None, 'Downloading login token')
+        viewer = self._fetch_viewer_info()
         data = {
             'action': 'login',
             'email': username,
@@ -96,11 +116,10 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                 expected=True)
         return password
 
-    def _verify_video_password(self, video_id):
+    def _verify_video_password(self, video_id, path=None):
         video_password = self._get_video_password()
-        token = self._download_json(
-            'https://vimeo.com/_next/viewer', video_id, 'Downloading viewer info')['xsrft']
-        url = f'https://vimeo.com/{video_id}'
+        token = self._fetch_viewer_info(video_id)['xsrft']
+        url = join_nonempty('https://vimeo.com', path, video_id, delim='/')
         try:
             self._request_webpage(
                 f'{url}/password', video_id,
@@ -117,6 +136,10 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                 raise ExtractorError('Wrong password', expected=True)
             raise
 
+    def _extract_config_url(self, webpage, **kwargs):
+        return self._html_search_regex(
+            r'\bdata-config-url="([^"]+)"', webpage, 'config URL', **kwargs)
+
     def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
         vimeo_config = self._search_regex(
             r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
@@ -164,6 +187,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
         sep_pattern = r'/sep/video/'
         for files_type in ('hls', 'dash'):
             for cdn_name, cdn_data in (try_get(config_files, lambda x: x[files_type]['cdns']) or {}).items():
+                # TODO: Also extract 'avc_url'? Investigate if there are 'hevc_url', 'av1_url'?
                 manifest_url = cdn_data.get('url')
                 if not manifest_url:
                     continue
@@ -244,7 +268,10 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             'formats': formats,
             'subtitles': subtitles,
             'live_status': live_status,
-            'release_timestamp': traverse_obj(live_event, ('ingest', 'scheduled_start_time', {parse_iso8601})),
+            'release_timestamp': traverse_obj(live_event, ('ingest', (
+                ('scheduled_start_time', {parse_iso8601}),
+                ('start_time', {int_or_none}),
+            ), any)),
             # Note: Bitrates are completely broken. Single m3u8 may contain entries in kbps and bps
             # at the same time without actual units specified.
             '_format_sort_fields': ('quality', 'res', 'fps', 'hdr:12', 'source'),
@@ -353,7 +380,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                          (?:
                              (?P<u>user)|
                              (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
-                             (?:.*?/)??
+                             (?:(?!event/).*?/)??
                              (?P<q>
                                  (?:
                                      play_redirect_hls|
@@ -933,8 +960,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             r'vimeo\.com/(?:album|showcase)/([^/]+)', url, 'album id', default=None)
         if not album_id:
             return
-        viewer = self._download_json(
-            'https://vimeo.com/_rv/viewer', album_id, fatal=False)
+        viewer = self._fetch_viewer_info(album_id, fatal=False)
         if not viewer:
             webpage = self._download_webpage(url, album_id)
             viewer = self._parse_json(self._search_regex(
@@ -992,9 +1018,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
                 raise
             errmsg = error.cause.response.read()
             if b'Because of its privacy settings, this video cannot be played here' in errmsg:
-                raise ExtractorError(
-                    'Cannot download embed-only video without embedding URL. Please call yt-dlp '
-                    'with the URL of the page that embeds this video.', expected=True)
+                raise ExtractorError(self._REFERER_HINT, expected=True)
             # 403 == vimeo.com TLS fingerprint or DC IP block; 429 == player.vimeo.com TLS FP block
             status = error.cause.status
             dcip_msg = 'If you are using a data center IP or VPN/proxy, your IP may be blocked'
@@ -1039,8 +1063,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         channel_id = self._search_regex(
             r'vimeo\.com/channels/([^/]+)', url, 'channel id', default=None)
         if channel_id:
-            config_url = self._html_search_regex(
-                r'\bdata-config-url="([^"]+)"', webpage, 'config URL', default=None)
+            config_url = self._extract_config_url(webpage, default=None)
             video_description = clean_html(get_element_by_class('description', webpage))
             info_dict.update({
                 'channel_id': channel_id,
@@ -1333,8 +1356,7 @@ class VimeoAlbumIE(VimeoBaseInfoExtractor):
 
     def _real_extract(self, url):
         album_id = self._match_id(url)
-        viewer = self._download_json(
-            'https://vimeo.com/_rv/viewer', album_id, fatal=False)
+        viewer = self._fetch_viewer_info(album_id, fatal=False)
         if not viewer:
             webpage = self._download_webpage(url, album_id)
             viewer = self._parse_json(self._search_regex(
@@ -1626,3 +1648,377 @@ class VimeoProIE(VimeoBaseInfoExtractor):
 
         return self.url_result(vimeo_url, VimeoIE, video_id, url_transparent=True,
                                description=description)
+
+
+class VimeoEventIE(VimeoBaseInfoExtractor):
+    IE_NAME = 'vimeo:event'
+    _VALID_URL = r'''(?x)
+        https?://(?:www\.)?vimeo\.com/event/(?P<id>\d+)(?:/
+            (?:
+                (?:embed/)?(?P<unlisted_hash>[\da-f]{10})|
+                videos/(?P<video_id>\d+)
+            )
+        )?'''
+    _EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>https?://vimeo\.com/event/\d+/embed(?:[/?][^"\']*)?)["\'][^>]*>']
+    _TESTS = [{
+        # stream_privacy.view: 'anybody'
+        'url': 'https://vimeo.com/event/5116195',
+        'info_dict': {
+            'id': '1082194134',
+            'ext': 'mp4',
+            'display_id': '5116195',
+            'title': 'Skidmore College Commencement 2025',
+            'description': 'md5:1902dd5165d21f98aa198297cc729d23',
+            'uploader': 'Skidmore College',
+            'uploader_id': 'user116066434',
+            'uploader_url': 'https://vimeo.com/user116066434',
+            'comment_count': int,
+            'like_count': int,
+            'duration': 9810,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'timestamp': 1747502974,
+            'upload_date': '20250517',
+            'release_timestamp': 1747502998,
+            'release_date': '20250517',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # stream_privacy.view: 'embed_only'
+        'url': 'https://vimeo.com/event/5034253/embed',
+        'info_dict': {
+            'id': '1071439154',
+            'ext': 'mp4',
+            'display_id': '5034253',
+            'title': 'Advancing Humans with AI',
+            'description': r're:AI is here to stay, but how do we ensure that people flourish in a world of pervasive AI use.{322}$',
+            'uploader': 'MIT Media Lab',
+            'uploader_id': 'mitmedialab',
+            'uploader_url': 'https://vimeo.com/mitmedialab',
+            'duration': 23235,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'chapters': 'count:37',
+            'release_timestamp': 1744290000,
+            'release_date': '20250410',
+            'live_status': 'was_live',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+            'http_headers': {'Referer': 'https://www.media.mit.edu/events/aha-symposium/'},
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # Last entry on 2nd page of the 37 video playlist, but use clip_to_play_id API param shortcut
+        'url': 'https://vimeo.com/event/4753126/videos/1046153257',
+        'info_dict': {
+            'id': '1046153257',
+            'ext': 'mp4',
+            'display_id': '4753126',
+            'title': 'January 12, 2025 The True Vine (Pastor John Mindrup)',
+            'description': 'The True Vine (Pastor \tJohn Mindrup)',
+            'uploader': 'Salem United Church of Christ',
+            'uploader_id': 'user230181094',
+            'uploader_url': 'https://vimeo.com/user230181094',
+            'comment_count': int,
+            'like_count': int,
+            'duration': 4962,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'timestamp': 1736702464,
+            'upload_date': '20250112',
+            'release_timestamp': 1736702543,
+            'release_date': '20250112',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # "24/7" livestream
+        'url': 'https://vimeo.com/event/4768062',
+        'info_dict': {
+            'id': '1079901414',
+            'ext': 'mp4',
+            'display_id': '4768062',
+            'title': r're:GRACELAND CAM \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
+            'description': '24/7 camera at Graceland Mansion',
+            'uploader': 'Elvis Presley\'s Graceland',
+            'uploader_id': 'visitgraceland',
+            'uploader_url': 'https://vimeo.com/visitgraceland',
+            'release_timestamp': 1745975450,
+            'release_date': '20250430',
+            'live_status': 'is_live',
+        },
+        'params': {'skip_download': 'livestream'},
+    }, {
+        # stream_privacy.view: 'unlisted' with unlisted_hash in URL path (stream_privacy.embed: 'whitelist')
+        'url': 'https://vimeo.com/event/4259978/3db517c479',
+        'info_dict': {
+            'id': '939104114',
+            'ext': 'mp4',
+            'display_id': '4259978',
+            'title': 'Enhancing Credibility in Your Community Science Project',
+            'description': 'md5:eab953341168b9c146bc3cfe3f716070',
+            'uploader': 'NOAA Research',
+            'uploader_id': 'noaaresearch',
+            'uploader_url': 'https://vimeo.com/noaaresearch',
+            'comment_count': int,
+            'like_count': int,
+            'duration': 3961,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'timestamp': 1716408008,
+            'upload_date': '20240522',
+            'release_timestamp': 1716408062,
+            'release_date': '20240522',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # "done" event with video_id in URL and unlisted_hash in VimeoIE URL
+        'url': 'https://vimeo.com/event/595460/videos/498149131/',
+        'info_dict': {
+            'id': '498149131',
+            'ext': 'mp4',
+            'display_id': '595460',
+            'title': '2021 Eighth Annual John Cardinal Foley Lecture on Social Communications',
+            'description': 'Replay: https://vimeo.com/catholicphilly/review/498149131/544f26a12f',
+            'uploader': 'Kearns Media Consulting LLC',
+            'uploader_id': 'kearnsmediaconsulting',
+            'uploader_url': 'https://vimeo.com/kearnsmediaconsulting',
+            'comment_count': int,
+            'like_count': int,
+            'duration': 4466,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'timestamp': 1612228466,
+            'upload_date': '20210202',
+            'release_timestamp': 1612228538,
+            'release_date': '20210202',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # stream_privacy.view: 'password'; stream_privacy.embed: 'public'
+        'url': 'https://vimeo.com/event/4940578',
+        'info_dict': {
+            'id': '1059263570',
+            'ext': 'mp4',
+            'display_id': '4940578',
+            'title': 'TMAC AKC AGILITY 2-22-2025',
+            'uploader': 'Paws \'N Effect',
+            'uploader_id': 'pawsneffect',
+            'uploader_url': 'https://vimeo.com/pawsneffect',
+            'comment_count': int,
+            'like_count': int,
+            'duration': 33115,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'timestamp': 1740261836,
+            'upload_date': '20250222',
+            'release_timestamp': 1740261873,
+            'release_date': '20250222',
+            'live_status': 'was_live',
+        },
+        'params': {
+            'videopassword': '22',
+            'skip_download': 'm3u8',
+        },
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }, {
+        # API serves a playlist of 37 videos, but the site only streams the newest one (changes every Sunday)
+        'url': 'https://vimeo.com/event/4753126',
+        'only_matching': True,
+    }, {
+        # Scheduled for 2025.05.15 but never started; "unavailable"; stream_privacy.view: "anybody"
+        'url': 'https://vimeo.com/event/5120811/embed',
+        'only_matching': True,
+    }, {
+        'url': 'https://vimeo.com/event/5112969/embed?muted=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://vimeo.com/event/5097437/embed/interaction?muted=1',
+        'only_matching': True,
+    }, {
+        'url': 'https://vimeo.com/event/5113032/embed?autoplay=1&muted=1',
+        'only_matching': True,
+    }, {
+        # Ended livestream with video_id
+        'url': 'https://vimeo.com/event/595460/videos/507329569/',
+        'only_matching': True,
+    }, {
+        # stream_privacy.view: 'unlisted' with unlisted_hash in URL path (stream_privacy.embed: 'public')
+        'url': 'https://vimeo.com/event/4606123/embed/358d60ce2e',
+        'only_matching': True,
+    }]
+    _WEBPAGE_TESTS = [{
+        # Same result as https://vimeo.com/event/5034253/embed
+        'url': 'https://www.media.mit.edu/events/aha-symposium/',
+        'info_dict': {
+            'id': '1071439154',
+            'ext': 'mp4',
+            'display_id': '5034253',
+            'title': 'Advancing Humans with AI',
+            'description': r're:AI is here to stay, but how do we ensure that people flourish in a world of pervasive AI use.{322}$',
+            'uploader': 'MIT Media Lab',
+            'uploader_id': 'mitmedialab',
+            'uploader_url': 'https://vimeo.com/mitmedialab',
+            'duration': 23235,
+            'thumbnail': r're:https://i\.vimeocdn\.com/video/\d+-[\da-f]+-d',
+            'chapters': 'count:37',
+            'release_timestamp': 1744290000,
+            'release_date': '20250410',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+        'expected_warnings': ['Failed to parse XML: not well-formed'],
+    }]
+
+    _EVENT_FIELDS = (
+        'title', 'uri', 'schedule', 'stream_description', 'stream_privacy.embed', 'stream_privacy.view',
+        'clip_to_play.name', 'clip_to_play.uri', 'clip_to_play.config_url', 'clip_to_play.live.status',
+        'clip_to_play.privacy.embed', 'clip_to_play.privacy.view', 'clip_to_play.password',
+        'streamable_clip.name', 'streamable_clip.uri', 'streamable_clip.config_url', 'streamable_clip.live.status',
+    )
+    _VIDEOS_FIELDS = ('items', 'uri', 'name', 'config_url', 'duration', 'live.status')
+
+    def _call_events_api(
+        self, event_id, ep=None, unlisted_hash=None, note=None,
+        fields=(), referrer=None, query=None, headers=None,
+    ):
+        resource = join_nonempty('event', ep, note, 'API JSON', delim=' ')
+
+        return self._download_json(
+            join_nonempty(
+                'https://api.vimeo.com/live_events',
+                join_nonempty(event_id, unlisted_hash, delim=':'), ep, delim='/'),
+            event_id, f'Downloading {resource}', f'Failed to download {resource}',
+            query=filter_dict({
+                'fields': ','.join(fields) or [],
+                # Correct spelling with 4 R's is deliberate
+                'referrer': referrer,
+                **(query or {}),
+            }), headers=filter_dict({
+                'Accept': 'application/json',
+                'Authorization': f'jwt {self._fetch_viewer_info(event_id)["jwt"]}',
+                'Referer': referrer,
+                **(headers or {}),
+            }))
+
+    @staticmethod
+    def _extract_video_id_and_unlisted_hash(video):
+        if not traverse_obj(video, ('uri', {lambda x: x.startswith('/videos/')})):
+            return None, None
+        video_id, _, unlisted_hash = video['uri'][8:].partition(':')
+        return video_id, unlisted_hash or None
+
+    def _vimeo_url_result(self, video_id, unlisted_hash=None, event_id=None):
+        # VimeoIE can extract more metadata and formats for was_live event videos
+        return self.url_result(
+            join_nonempty('https://vimeo.com', video_id, unlisted_hash, delim='/'), VimeoIE,
+            video_id, display_id=event_id, live_status='was_live', url_transparent=True)
+
+    @classmethod
+    def _extract_embed_urls(cls, url, webpage):
+        for embed_url in super()._extract_embed_urls(url, webpage):
+            yield cls._smuggle_referrer(embed_url, url)
+
+    def _real_extract(self, url):
+        url, _, headers = self._unsmuggle_headers(url)
+        # XXX: Keep key name in sync with _unsmuggle_headers
+        referrer = headers.get('Referer')
+        event_id, unlisted_hash, video_id = self._match_valid_url(url).group('id', 'unlisted_hash', 'video_id')
+
+        for retry in (False, True):
+            try:
+                live_event_data = self._call_events_api(
+                    event_id, unlisted_hash=unlisted_hash, fields=self._EVENT_FIELDS,
+                    referrer=referrer, query={'clip_to_play_id': video_id or '0'},
+                    headers={'Accept': 'application/vnd.vimeo.*+json;version=3.4.9'})
+                break
+            except ExtractorError as e:
+                if retry or not isinstance(e.cause, HTTPError) or e.cause.status not in (400, 403):
+                    raise
+                response = traverse_obj(e.cause.response.read(), ({json.loads}, {dict})) or {}
+                error_code = response.get('error_code')
+                if error_code == 2204:
+                    self._verify_video_password(event_id, path='event')
+                    continue
+                if error_code == 3200:
+                    raise ExtractorError(self._REFERER_HINT, expected=True)
+                if error_msg := response.get('error'):
+                    raise ExtractorError(f'Vimeo says: {error_msg}', expected=True)
+                raise
+
+        # stream_privacy.view can be: 'anybody', 'embed_only', 'nobody', 'password', 'unlisted'
+        view_policy = live_event_data['stream_privacy']['view']
+        if view_policy == 'nobody':
+            raise ExtractorError('This event has not been made available to anyone', expected=True)
+
+        clip_data = traverse_obj(live_event_data, ('clip_to_play', {dict})) or {}
+        # live.status can be: 'streaming' (is_live), 'done' (was_live), 'unavailable' (is_upcoming OR dead)
+        clip_status = traverse_obj(clip_data, ('live', 'status', {str}))
+        start_time = traverse_obj(live_event_data, ('schedule', 'start_time', {str}))
+        release_timestamp = parse_iso8601(start_time)
+
+        if clip_status == 'unavailable' and release_timestamp and release_timestamp > time.time():
+            self.raise_no_formats(f'This live event is scheduled for {start_time}', expected=True)
+            live_status = 'is_upcoming'
+            config_url = None
+
+        elif view_policy == 'embed_only':
+            webpage = self._download_webpage(
+                join_nonempty('https://vimeo.com/event', event_id, 'embed', unlisted_hash, delim='/'),
+                event_id, 'Downloading embed iframe webpage', impersonate=True, headers=headers)
+            # The _parse_config result will overwrite live_status w/ 'is_live' if livestream is active
+            live_status = 'was_live'
+            config_url = self._extract_config_url(webpage)
+
+        else:  # view_policy in ('anybody', 'password', 'unlisted')
+            if video_id:
+                clip_id, clip_hash = self._extract_video_id_and_unlisted_hash(clip_data)
+                if video_id == clip_id and clip_status == 'done' and (clip_hash or view_policy != 'unlisted'):
+                    return self._vimeo_url_result(clip_id, clip_hash, event_id)
+
+                video_filter = lambda _, v: self._extract_video_id_and_unlisted_hash(v)[0] == video_id
+            else:
+                video_filter = lambda _, v: v['live']['status'] in ('streaming', 'done')
+
+            for page in itertools.count(1):
+                videos_data = self._call_events_api(
+                    event_id, 'videos', unlisted_hash=unlisted_hash, note=f'page {page}',
+                    fields=self._VIDEOS_FIELDS, referrer=referrer, query={'page': page},
+                    headers={'Accept': 'application/vnd.vimeo.*;version=3.4.1'})
+
+                video = traverse_obj(videos_data, ('data', video_filter, any))
+                if video or not traverse_obj(videos_data, ('paging', 'next', {str})):
+                    break
+
+            live_status = {
+                'streaming': 'is_live',
+                'done': 'was_live',
+            }.get(traverse_obj(video, ('live', 'status', {str})))
+
+            if not live_status:  # requested video_id is unavailable or no videos are available
+                raise ExtractorError('This event video is unavailable', expected=True)
+            elif live_status == 'was_live':
+                return self._vimeo_url_result(*self._extract_video_id_and_unlisted_hash(video), event_id)
+            config_url = video['config_url']
+
+        if config_url:  # view_policy == 'embed_only' or live_status == 'is_live'
+            info = filter_dict(self._parse_config(
+                self._download_json(config_url, event_id, 'Downloading config JSON'), event_id))
+        else:  # live_status == 'is_upcoming'
+            info = {'id': event_id}
+
+        if info.get('live_status') == 'post_live':
+            self.report_warning('This live event recently ended and some formats may not yet be available')
+
+        return {
+            **traverse_obj(live_event_data, {
+                'title': ('title', {str}),
+                'description': ('stream_description', {str}),
+            }),
+            'display_id': event_id,
+            'live_status': live_status,
+            'release_timestamp': release_timestamp,
+            **info,
+        }

yt_dlp/extractor/voxmedia.py

@@ -1,7 +1,6 @@
 import urllib.parse
 
 from .common import InfoExtractor
-from .once import OnceIE
 from ..utils import (
     ExtractorError,
     int_or_none,
@@ -10,7 +9,7 @@ from ..utils import (
 )
 
 
-class VoxMediaVolumeIE(OnceIE):
+class VoxMediaVolumeIE(InfoExtractor):
     _VALID_URL = r'https?://volume\.vox-cdn\.com/embed/(?P<id>[0-9a-f]{9})'
 
     def _real_extract(self, url):
@@ -57,7 +56,8 @@ class VoxMediaVolumeIE(OnceIE):
             if not provider_video_id:
                 continue
             if provider_video_type == 'brightcove':
-                info['formats'] = self._extract_once_formats(provider_video_id)
+                # TODO: Find embed example or confirm that Vox has stopped using Brightcove
+                raise ExtractorError('Vox Brightcove embeds are currently unsupported')
             else:
                 info.update({
                     '_type': 'url_transparent',
@@ -155,20 +155,6 @@ class VoxMediaIE(InfoExtractor):
             },
         }],
         'skip': 'Page no longer contain videos',
-    }, {
-        # volume embed, Brightcove Once
-        'url': 'https://www.recode.net/2014/6/17/11628066/post-post-pc-ceo-the-full-code-conference-video-of-microsofts-satya',
-        'md5': '2dbc77b8b0bff1894c2fce16eded637d',
-        'info_dict': {
-            'id': '1231c973d',
-            'ext': 'mp4',
-            'title': 'Post-Post-PC CEO: The Full Code Conference Video of Microsoft\'s Satya Nadella',
-            'description': 'The longtime veteran was chosen earlier this year as the software giant\'s third leader in its history.',
-            'timestamp': 1402938000,
-            'upload_date': '20140616',
-            'duration': 4114,
-        },
-        'add_ie': ['VoxMediaVolume'],
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/wat.py

@@ -2,9 +2,11 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     try_get,
     unified_strdate,
 )
+from ..utils.traversal import traverse_obj
 
 
 class WatIE(InfoExtractor):
@@ -70,8 +72,14 @@ class WatIE(InfoExtractor):
 
         error_desc = video_info.get('error_desc')
         if error_desc:
-            if video_info.get('error_code') == 'GEOBLOCKED':
+            error_code = video_info.get('error_code')
+            if error_code == 'GEOBLOCKED':
                 self.raise_geo_restricted(error_desc, video_info.get('geoList'))
+            elif error_code == 'DELIVERY_ERROR':
+                if traverse_obj(video_data, ('delivery', 'code')) == 500:
+                    self.report_drm(video_id)
+                error_desc = join_nonempty(
+                    error_desc, traverse_obj(video_data, ('delivery', 'error', {str})), delim=': ')
             raise ExtractorError(error_desc, expected=True)
 
         title = video_info['title']

yt_dlp/extractor/weverse.py

@@ -290,12 +290,14 @@ class WeverseIE(WeverseBaseIE):
 
         elif live_status == 'is_live':
             video_info = self._call_api(
-                f'/video/v1.2/lives/{api_video_id}/playInfo?preview.format=json&preview.version=v2',
+                f'/video/v1.3/lives/{api_video_id}/playInfo?preview.format=json&preview.version=v2',
                 video_id, note='Downloading live JSON')
             playback = self._parse_json(video_info['lipPlayback'], video_id)
             m3u8_url = traverse_obj(playback, (
                 'media', lambda _, v: v['protocol'] == 'HLS', 'path', {url_or_none}), get_all=False)
-            formats = self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls', live=True)
+            # Live subtitles are not downloadable, but extract to silence "ignoring subs" warning
+            formats, _ = self._extract_m3u8_formats_and_subtitles(
+                m3u8_url, video_id, 'mp4', m3u8_id='hls', live=True)
 
         elif live_status == 'post_live':
             if availability in ('premium_only', 'subscriber_only'):

yt_dlp/extractor/xinpianchang.py

@@ -45,7 +45,7 @@ class XinpianchangIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id=video_id)
+        webpage = self._download_webpage(url, video_id=video_id, headers={'Referer': url})
         video_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['detail']['video']
 
         data = self._download_json(

yt_dlp/extractor/youtube/_base.py

@@ -35,6 +35,7 @@ from ...utils import (
 class _PoTokenContext(enum.Enum):
     PLAYER = 'player'
     GVS = 'gvs'
+    SUBS = 'subs'
 
 
 # any clients starting with _ cannot be explicitly requested by the user
@@ -787,6 +788,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     def _download_ytcfg(self, client, video_id):
         url = {
+            'mweb': 'https://m.youtube.com',
             'web': 'https://www.youtube.com',
             'web_music': 'https://music.youtube.com',
             'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1',

yt_dlp/extractor/youtube/_clip.py

@@ -37,6 +37,7 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
             'chapters': 'count:20',
             'comment_count': int,
             'heatmap': 'count:100',
+            'media_type': 'clip',
         },
     }]
 
@@ -59,6 +60,7 @@ class YoutubeClipIE(YoutubeTabBaseInfoExtractor):
             'url': f'https://www.youtube.com/watch?v={video_id}',
             'ie_key': YoutubeIE.ie_key(),
             'id': clip_id,
+            'media_type': 'clip',
             'section_start': int(clip_data['startTimeMs']) / 1000,
             'section_end': int(clip_data['endTimeMs']) / 1000,
             '_format_sort_fields': (  # https protocol is prioritized for ffmpeg compatibility

yt_dlp/extractor/youtube/_redirect.py

@@ -35,6 +35,7 @@ class YoutubeYtBeIE(YoutubeBaseInfoExtractor):
             'duration': 59,
             'comment_count': int,
             'channel_follower_count': int,
+            'media_type': 'short',
         },
         'params': {
             'noplaylist': True,

yt_dlp/extractor/youtube/_video.py

@@ -23,6 +23,8 @@ from ._base import (
     _split_innertube_client,
     short_client_name,
 )
+from .pot._director import initialize_pot_director
+from .pot.provider import PoTokenContext, PoTokenRequest
 from ..openload import PhantomJSwrapper
 from ...jsinterp import JSInterpreter
 from ...networking.exceptions import HTTPError
@@ -66,9 +68,13 @@ from ...utils import (
     urljoin,
     variadic,
 )
+from ...utils.networking import clean_headers, clean_proxies, select_proxy
 
 STREAMING_DATA_CLIENT_NAME = '__yt_dlp_client'
 STREAMING_DATA_INITIAL_PO_TOKEN = '__yt_dlp_po_token'
+STREAMING_DATA_FETCH_SUBS_PO_TOKEN = '__yt_dlp_fetch_subs_po_token'
+STREAMING_DATA_INNERTUBE_CONTEXT = '__yt_dlp_innertube_context'
+
 PO_TOKEN_GUIDE_URL = 'https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide'
 
 
@@ -376,6 +382,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Afrojack',
                 'uploader_url': 'https://www.youtube.com/@Afrojack',
                 'uploader_id': '@Afrojack',
+                'media_type': 'video',
             },
             'params': {
                 'youtube_include_dash_manifest': True,
@@ -413,10 +420,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1401991663,
+                'media_type': 'video',
             },
         },
         {
-            'note': 'Age-gate video with embed allowed in public site',
+            'note': 'Formerly an age-gate video with embed allowed in public site',
             'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
             'info_dict': {
                 'id': 'HsUATh_Nc2U',
@@ -424,8 +432,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Godzilla 2 (Official Video)',
                 'description': 'md5:bf77e03fcae5529475e500129b05668a',
                 'upload_date': '20200408',
-                'age_limit': 18,
-                'availability': 'needs_auth',
+                'age_limit': 0,
+                'availability': 'public',
                 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
                 'channel': 'FlyingKitty',
                 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
@@ -443,8 +451,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@FlyingKitty900',
                 'comment_count': int,
                 'channel_is_verified': True,
+                'media_type': 'video',
             },
-            'skip': 'Age-restricted; requires authentication',
         },
         {
             'note': 'Age-gate video embedable only with clientScreen=EMBED',
@@ -507,6 +515,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Herr Lurik',
                 'uploader_url': 'https://www.youtube.com/@HerrLurik',
                 'uploader_id': '@HerrLurik',
+                'media_type': 'video',
             },
         },
         {
@@ -546,6 +555,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'deadmau5',
                 'uploader_url': 'https://www.youtube.com/@deadmau5',
                 'uploader_id': '@deadmau5',
+                'media_type': 'video',
             },
             'expected_warnings': [
                 'DASH manifest missing',
@@ -581,6 +591,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@Olympics',
                 'channel_is_verified': True,
                 'timestamp': 1440707674,
+                'media_type': 'livestream',
             },
             'params': {
                 'skip_download': 'requires avconv',
@@ -615,6 +626,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@AllenMeow',
                 'uploader_id': '@AllenMeow',
                 'timestamp': 1299776999,
+                'media_type': 'video',
             },
         },
         # url_encoded_fmt_stream_map is empty string
@@ -809,6 +821,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'like_count': int,
                 'age_limit': 0,
                 'channel_follower_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -868,6 +881,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@BKCHarvard',
                 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
                 'timestamp': 1422422076,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -904,6 +918,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1447987198,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -968,6 +983,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'timestamp': 1484761047,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1070,6 +1086,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'tags': 'count:11',
                 'live_status': 'not_live',
                 'channel_follower_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1124,6 +1141,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
                 'uploader_id': '@ElevageOrVert',
                 'timestamp': 1497343210,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1163,6 +1181,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1377976349,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1207,6 +1226,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_follower_count': int,
                 'uploader': 'The Cinematic Orchestra',
                 'comment_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1275,6 +1295,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
                 'uploader_id': '@walkaroundjapan7124',
                 'timestamp': 1605884416,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1371,6 +1392,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1395685455,
+                'media_type': 'video',
             }, 'params': {'format': 'mhtml', 'skip_download': True},
         }, {
             # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
@@ -1401,6 +1423,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@LeonNguyen',
                 'heatmap': 'count:100',
                 'timestamp': 1641170939,
+                'media_type': 'video',
             },
         }, {
             # date text is premiered video, ensure upload date in UTC (published 1641172509)
@@ -1434,6 +1457,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1641172509,
+                'media_type': 'video',
             },
         },
         {   # continuous livestream.
@@ -1495,6 +1519,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Lesmiscore',
                 'uploader_url': 'https://www.youtube.com/@lesmiscore',
                 'timestamp': 1648005313,
+                'media_type': 'short',
             },
         }, {
             # Prefer primary title+description language metadata by default
@@ -1523,6 +1548,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@coletdjnz',
                 'uploader': 'cole-dlp-test-acc',
                 'timestamp': 1662677394,
+                'media_type': 'video',
             },
             'params': {'skip_download': True},
         }, {
@@ -1551,6 +1577,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'cole-dlp-test-acc',
                 'timestamp': 1659073275,
                 'like_count': int,
+                'media_type': 'video',
             },
             'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
             'expected_warnings': [r'Preferring "fr" translated fields'],
@@ -1587,6 +1614,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
+                'media_type': 'video',
             },
             'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
         }, {
@@ -1687,6 +1715,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
+                'media_type': 'video',
             },
             'params': {
                 'extractor_args': {'youtube': {'player_client': ['ios'], 'player_skip': ['webpage']}},
@@ -1719,6 +1748,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_follower_count': int,
                 'categories': ['People & Blogs'],
                 'tags': [],
+                'media_type': 'short',
             },
         },
     ]
@@ -1754,6 +1784,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@ChristopherSykesDocumentaries',
                 'heatmap': 'count:100',
                 'timestamp': 1211825920,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1784,6 +1815,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         super().__init__(*args, **kwargs)
         self._code_cache = {}
         self._player_cache = {}
+        self._pot_director = None
+
+    def _real_initialize(self):
+        super()._real_initialize()
+        self._pot_director = initialize_pot_director(self)
 
     def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
         lock = threading.Lock()
@@ -1819,6 +1855,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     else:
                         retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
                     continue
+
+                # Formats from ended premieres will be missing a manifest_url
+                # See https://github.com/yt-dlp/yt-dlp/issues/8543
+                if not f.get('manifest_url'):
+                    break
+
                 return f['manifest_url'], f['manifest_stream_number'], is_live
             return None
 
@@ -2824,7 +2866,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 continue
 
     def fetch_po_token(self, client='web', context=_PoTokenContext.GVS, ytcfg=None, visitor_data=None,
-                       data_sync_id=None, session_index=None, player_url=None, video_id=None, **kwargs):
+                       data_sync_id=None, session_index=None, player_url=None, video_id=None, webpage=None,
+                       required=False, **kwargs):
         """
         Fetch a PO Token for a given client and context. This function will validate required parameters for a given context and client.
 
@@ -2838,10 +2881,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         @param session_index: session index.
         @param player_url: player URL.
         @param video_id: video ID.
+        @param webpage: video webpage.
+        @param required: Whether the PO Token is required (i.e. try to fetch unless policy is "never").
         @param kwargs: Additional arguments to pass down. May be more added in the future.
         @return: The fetched PO Token. None if it could not be fetched.
         """
 
+        # TODO(future): This validation should be moved into pot framework.
+        #  Some sort of middleware or validation provider perhaps?
+
         # GVS WebPO Token is bound to visitor_data / Visitor ID when logged out.
         # Must have visitor_data for it to function.
         if player_url and context == _PoTokenContext.GVS and not visitor_data and not self.is_authenticated:
@@ -2863,6 +2911,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     f'Got a GVS PO Token for {client} client, but missing Data Sync ID for account. Formats may not work.'
                     f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"')
 
+            self.write_debug(f'{video_id}: Retrieved a {context.value} PO Token for {client} client from config')
             return config_po_token
 
         # Require GVS WebPO Token if logged in for external fetching
@@ -2872,7 +2921,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 f'You may need to pass a Data Sync ID with --extractor-args "youtube:data_sync_id=XXX"')
             return
 
-        return self._fetch_po_token(
+        po_token = self._fetch_po_token(
             client=client,
             context=context.value,
             ytcfg=ytcfg,
@@ -2881,11 +2930,68 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             session_index=session_index,
             player_url=player_url,
             video_id=video_id,
+            video_webpage=webpage,
+            required=required,
             **kwargs,
         )
 
+        if po_token:
+            self.write_debug(f'{video_id}: Retrieved a {context.value} PO Token for {client} client')
+            return po_token
+
     def _fetch_po_token(self, client, **kwargs):
-        """(Unstable) External PO Token fetch stub"""
+        context = kwargs.get('context')
+
+        # Avoid fetching PO Tokens when not required
+        fetch_pot_policy = self._configuration_arg('fetch_pot', [''], ie_key=YoutubeIE)[0]
+        if fetch_pot_policy not in ('never', 'auto', 'always'):
+            fetch_pot_policy = 'auto'
+        if (
+            fetch_pot_policy == 'never'
+            or (
+                fetch_pot_policy == 'auto'
+                and _PoTokenContext(context) not in self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
+                and not kwargs.get('required', False)
+            )
+        ):
+            return None
+
+        headers = self.get_param('http_headers').copy()
+        proxies = self._downloader.proxies.copy()
+        clean_headers(headers)
+        clean_proxies(proxies, headers)
+
+        innertube_host = self._select_api_hostname(None, default_client=client)
+
+        pot_request = PoTokenRequest(
+            context=PoTokenContext(context),
+            innertube_context=traverse_obj(kwargs, ('ytcfg', 'INNERTUBE_CONTEXT')),
+            innertube_host=innertube_host,
+            internal_client_name=client,
+            session_index=kwargs.get('session_index'),
+            player_url=kwargs.get('player_url'),
+            video_webpage=kwargs.get('video_webpage'),
+            is_authenticated=self.is_authenticated,
+            visitor_data=kwargs.get('visitor_data'),
+            data_sync_id=kwargs.get('data_sync_id'),
+            video_id=kwargs.get('video_id'),
+            request_cookiejar=self._downloader.cookiejar,
+
+            # All requests that would need to be proxied should be in the
+            # context of www.youtube.com or the innertube host
+            request_proxy=(
+                select_proxy('https://www.youtube.com', proxies)
+                or select_proxy(f'https://{innertube_host}', proxies)
+            ),
+            request_headers=headers,
+            request_timeout=self.get_param('socket_timeout'),
+            request_verify_tls=not self.get_param('nocheckcertificate'),
+            request_source_address=self.get_param('source_address'),
+
+            bypass_cache=False,
+        )
+
+        return self._pot_director.get_po_token(pot_request)
 
     @staticmethod
     def _is_agegated(player_response):
@@ -3034,6 +3140,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 player_url = self._download_player_url(video_id)
                 tried_iframe_fallback = True
 
+            pr = initial_pr if client == 'web' else None
+
             visitor_data = visitor_data or self._extract_visitor_data(master_ytcfg, initial_pr, player_ytcfg)
             data_sync_id = data_sync_id or self._extract_data_sync_id(master_ytcfg, initial_pr, player_ytcfg)
 
@@ -3043,16 +3151,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'video_id': video_id,
                 'data_sync_id': data_sync_id if self.is_authenticated else None,
                 'player_url': player_url if require_js_player else None,
+                'webpage': webpage,
                 'session_index': self._extract_session_index(master_ytcfg, player_ytcfg),
-                'ytcfg': player_ytcfg,
+                'ytcfg': player_ytcfg or self._get_default_ytcfg(client),
             }
 
-            player_po_token = self.fetch_po_token(
+            # Don't need a player PO token for WEB if using player response from webpage
+            player_po_token = None if pr else self.fetch_po_token(
                 context=_PoTokenContext.PLAYER, **fetch_po_token_args)
 
             gvs_po_token = self.fetch_po_token(
                 context=_PoTokenContext.GVS, **fetch_po_token_args)
 
+            fetch_subs_po_token_func = functools.partial(
+                self.fetch_po_token,
+                context=_PoTokenContext.SUBS,
+                **fetch_po_token_args,
+            )
+
             required_pot_contexts = self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
 
             if (
@@ -3079,7 +3195,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     only_once=True)
                 deprioritize_pr = True
 
-            pr = initial_pr if client == 'web' else None
             try:
                 pr = pr or self._extract_player_response(
                     client, video_id,
@@ -3097,10 +3212,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if pr_id := self._invalid_player_response(pr, video_id):
                 skipped_clients[client] = pr_id
             elif pr:
-                # Save client name for introspection later
-                sd = traverse_obj(pr, ('streamingData', {dict})) or {}
+                # Save client details for introspection later
+                innertube_context = traverse_obj(player_ytcfg or self._get_default_ytcfg(client), 'INNERTUBE_CONTEXT')
+                sd = pr.setdefault('streamingData', {})
                 sd[STREAMING_DATA_CLIENT_NAME] = client
                 sd[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
+                sd[STREAMING_DATA_INNERTUBE_CONTEXT] = innertube_context
+                sd[STREAMING_DATA_FETCH_SUBS_PO_TOKEN] = fetch_subs_po_token_func
                 for f in traverse_obj(sd, (('formats', 'adaptiveFormats'), ..., {dict})):
                     f[STREAMING_DATA_CLIENT_NAME] = client
                     f[STREAMING_DATA_INITIAL_PO_TOKEN] = gvs_po_token
@@ -3109,9 +3227,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 else:
                     prs.append(pr)
 
+            # web_embedded can work around age-gate and age-verification for some embeddable videos
+            if self._is_agegated(pr) and variant != 'web_embedded':
+                append_client(f'web_embedded.{base_client}')
+            # Unauthenticated users will only get web_embedded client formats if age-gated
+            if self._is_agegated(pr) and not self.is_authenticated:
+                self.to_screen(
+                    f'{video_id}: This video is age-restricted; some formats may be missing '
+                    f'without authentication. {self._youtube_login_hint}', only_once=True)
+
             # EU countries require age-verification for accounts to access age-restricted videos
             # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
-            if self.is_authenticated and self._is_agegated(pr):
+            embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr)
+            if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
                 self.to_screen(
                     f'{video_id}: This video is age-restricted and YouTube is requiring '
                     'account age-verification; some formats may be missing', only_once=True)
@@ -3152,6 +3280,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         else:
             self.report_warning(msg, only_once=True)
 
+    def _report_pot_subtitles_skipped(self, video_id, client_name, msg=None):
+        msg = msg or (
+            f'{video_id}: Some {client_name} client subtitles require a PO Token which was not provided. '
+            'They will be discarded since they are not downloadable as-is. '
+            f'You can manually pass a Subtitles PO Token for this client with '
+            f'--extractor-args "youtube:po_token={client_name}.subs+XXX" . '
+            f'For more information, refer to  {PO_TOKEN_GUIDE_URL}')
+
+        subs_wanted = any((
+            self.get_param('writesubtitles'),
+            self.get_param('writeautomaticsub'),
+            self.get_param('listsubtitles')))
+
+        # Only raise a warning for non-default clients, to not confuse users.
+        if not subs_wanted or client_name in (*self._DEFAULT_CLIENTS, *self._DEFAULT_AUTHED_CLIENTS):
+            self.write_debug(msg, only_once=True)
+        else:
+            self.report_warning(msg, only_once=True)
+
     def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
         CHUNK_SIZE = 10 << 20
         PREFERRED_LANG_VALUE = 10
@@ -3443,6 +3590,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     hls_manifest_url = hls_manifest_url.rstrip('/') + f'/pot/{po_token}'
                 fmts, subs = self._extract_m3u8_formats_and_subtitles(
                     hls_manifest_url, video_id, 'mp4', fatal=False, live=live_status == 'is_live')
+                for sub in traverse_obj(subs, (..., ..., {dict})):
+                    # HLS subs (m3u8) do not need a PO token; save client name for debugging
+                    sub[STREAMING_DATA_CLIENT_NAME] = client_name
                 subtitles = self._merge_subtitles(subs, subtitles)
                 for f in fmts:
                     if process_manifest_format(f, 'hls', client_name, self._search_regex(
@@ -3454,6 +3604,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 if po_token:
                     dash_manifest_url = dash_manifest_url.rstrip('/') + f'/pot/{po_token}'
                 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
+                for sub in traverse_obj(subs, (..., ..., {dict})):
+                    # TODO: Investigate if DASH subs ever need a PO token; save client name for debugging
+                    sub[STREAMING_DATA_CLIENT_NAME] = client_name
                 subtitles = self._merge_subtitles(subs, subtitles)  # Prioritize HLS subs over DASH
                 for f in formats:
                     if process_manifest_format(f, 'dash', client_name, f['format_id'], po_token):
@@ -3645,7 +3798,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
             subreason = clean_html(self._get_text(pemr, 'subreason') or '')
             if subreason:
-                if subreason == 'The uploader has not made this video available in your country.':
+                if subreason.startswith('The uploader has not made this video available in your country'):
                     countries = get_first(microformats, 'availableCountries')
                     if not countries:
                         regions_allowed = search_meta('regionsAllowed')
@@ -3771,53 +3924,90 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'tags': keywords,
             'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
             'live_status': live_status,
-            'media_type': 'livestream' if get_first(video_details, 'isLiveContent') else None,
+            'media_type': (
+                'livestream' if get_first(video_details, 'isLiveContent')
+                else 'short' if get_first(microformats, 'isShortsEligible')
+                else 'video'),
             'release_timestamp': live_start_time,
             '_format_sort_fields': (  # source_preference is lower for potentially damaged formats
                 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang', 'proto'),
         }
 
+        def get_lang_code(track):
+            return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
+                    or track.get('languageCode'))
+
+        def process_language(container, base_url, lang_code, sub_name, client_name, query):
+            lang_subs = container.setdefault(lang_code, [])
+            for fmt in self._SUBTITLE_FORMATS:
+                query = {**query, 'fmt': fmt}
+                lang_subs.append({
+                    'ext': fmt,
+                    'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
+                    'name': sub_name,
+                    STREAMING_DATA_CLIENT_NAME: client_name,
+                })
+
         subtitles = {}
-        pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
-        if pctr:
-            def get_lang_code(track):
-                return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
-                        or track.get('languageCode'))
+        skipped_subs_clients = set()
+        prs = traverse_obj(player_responses, (
+            # Filter out initial_pr which does not have streamingData (smuggled client context)
+            lambda _, v: v['streamingData'] and v['captions']['playerCaptionsTracklistRenderer']))
 
-            # Converted into dicts to remove duplicates
-            captions = {
-                get_lang_code(sub): sub
-                for sub in traverse_obj(pctr, (..., 'captionTracks', ...))}
-            translation_languages = {
-                lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
-                for lang in traverse_obj(pctr, (..., 'translationLanguages', ...))}
+        pctrs = traverse_obj(prs, (..., 'captions', 'playerCaptionsTracklistRenderer', {dict}))
+        translation_languages = {
+            lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
+            for lang in traverse_obj(pctrs, (..., 'translationLanguages', ..., {dict}))}
+        # NB: Constructing the full subtitle dictionary is slow
+        get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
+            self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
 
-            def process_language(container, base_url, lang_code, sub_name, query):
-                lang_subs = container.setdefault(lang_code, [])
-                for fmt in self._SUBTITLE_FORMATS:
-                    query.update({
-                        'fmt': fmt,
-                    })
-                    lang_subs.append({
-                        'ext': fmt,
-                        'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
-                        'name': sub_name,
-                    })
+        all_captions = traverse_obj(pctrs, (..., 'captionTracks', ..., {dict}))
+        need_subs_langs = {get_lang_code(sub) for sub in all_captions if sub.get('kind') != 'asr'}
+        need_caps_langs = {
+            remove_start(get_lang_code(sub), 'a-')
+            for sub in all_captions if sub.get('kind') == 'asr'}
 
-            # NB: Constructing the full subtitle dictionary is slow
-            get_translated_subs = 'translated_subs' not in self._configuration_arg('skip') and (
-                self.get_param('writeautomaticsub', False) or self.get_param('listsubtitles'))
-            for lang_code, caption_track in captions.items():
-                base_url = caption_track.get('baseUrl')
-                orig_lang = parse_qs(base_url).get('lang', [None])[-1]
-                if not base_url:
-                    continue
+        for pr in prs:
+            pctr = pr['captions']['playerCaptionsTracklistRenderer']
+            client_name = pr['streamingData'][STREAMING_DATA_CLIENT_NAME]
+            innertube_client_name = pr['streamingData'][STREAMING_DATA_INNERTUBE_CONTEXT]['client']['clientName']
+            required_contexts = self._get_default_ytcfg(client_name)['PO_TOKEN_REQUIRED_CONTEXTS']
+            fetch_subs_po_token_func = pr['streamingData'][STREAMING_DATA_FETCH_SUBS_PO_TOKEN]
+
+            pot_params = {}
+            already_fetched_pot = False
+
+            for caption_track in traverse_obj(pctr, ('captionTracks', lambda _, v: v['baseUrl'])):
+                base_url = caption_track['baseUrl']
+                qs = parse_qs(base_url)
+                lang_code = get_lang_code(caption_track)
+                requires_pot = (
+                    # We can detect the experiment for now
+                    any(e in traverse_obj(qs, ('exp', ...)) for e in ('xpe', 'xpv'))
+                    or _PoTokenContext.SUBS in required_contexts)
+
+                if not already_fetched_pot:
+                    already_fetched_pot = True
+                    if subs_po_token := fetch_subs_po_token_func(required=requires_pot):
+                        pot_params.update({
+                            'pot': subs_po_token,
+                            'potc': '1',
+                            'c': innertube_client_name,
+                        })
+
+                if not pot_params and requires_pot:
+                    skipped_subs_clients.add(client_name)
+                    self._report_pot_subtitles_skipped(video_id, client_name)
+                    break
+
+                orig_lang = qs.get('lang', [None])[-1]
                 lang_name = self._get_text(caption_track, 'name', max_runs=1)
                 if caption_track.get('kind') != 'asr':
                     if not lang_code:
                         continue
                     process_language(
-                        subtitles, base_url, lang_code, lang_name, {})
+                        subtitles, base_url, lang_code, lang_name, client_name, pot_params)
                     if not caption_track.get('isTranslatable'):
                         continue
                 for trans_code, trans_name in translation_languages.items():
@@ -3837,10 +4027,25 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                         # Add an "-orig" label to the original language so that it can be distinguished.
                         # The subs are returned without "-orig" as well for compatibility
                         process_language(
-                            automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
+                            automatic_captions, base_url, f'{trans_code}-orig',
+                            f'{trans_name} (Original)', client_name, pot_params)
                     # Setting tlang=lang returns damaged subtitles.
-                    process_language(automatic_captions, base_url, trans_code, trans_name,
-                                     {} if orig_lang == orig_trans_code else {'tlang': trans_code})
+                    process_language(
+                        automatic_captions, base_url, trans_code, trans_name, client_name,
+                        pot_params if orig_lang == orig_trans_code else {'tlang': trans_code, **pot_params})
+
+            # Avoid duplication if we've already got everything we need
+            need_subs_langs.difference_update(subtitles)
+            need_caps_langs.difference_update(automatic_captions)
+            if not (need_subs_langs or need_caps_langs):
+                break
+
+        if skipped_subs_clients and (need_subs_langs or need_caps_langs):
+            self._report_pot_subtitles_skipped(video_id, True, msg=join_nonempty(
+                f'{video_id}: There are missing subtitles languages because a PO token was not provided.',
+                need_subs_langs and f'Subtitles for these languages are missing: {", ".join(need_subs_langs)}.',
+                need_caps_langs and f'Automatic captions for {len(need_caps_langs)} languages are missing.',
+                delim=' '))
 
         info['automatic_captions'] = automatic_captions
         info['subtitles'] = subtitles

yt_dlp/extractor/youtube/pot/README.md

@@ -0,0 +1,309 @@
+# YoutubeIE PO Token Provider Framework
+
+As part of the YouTube extractor, we have a framework for providing PO Tokens programmatically. This can be used by plugins.
+
+Refer to the [PO Token Guide](https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide) for more information on PO Tokens.
+
+> [!TIP]
+> If publishing a PO Token Provider plugin to GitHub, add the [yt-dlp-pot-provider](https://github.com/topics/yt-dlp-pot-provider) topic to your repository to help users find it.
+
+
+## Public APIs
+
+- `yt_dlp.extractor.youtube.pot.cache`
+- `yt_dlp.extractor.youtube.pot.provider`
+- `yt_dlp.extractor.youtube.pot.utils`
+
+Everything else is internal-only and no guarantees are made about the API stability.
+
+> [!WARNING]
+> We will try our best to maintain stability with the public APIs.
+> However, due to the nature of extractors and YouTube, we may need to remove or change APIs in the future.
+> If you are using these APIs outside yt-dlp plugins, please account for this by importing them safely.
+
+## PO Token Provider
+
+`yt_dlp.extractor.youtube.pot.provider`
+
+```python
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenRequest,
+    PoTokenContext,
+    PoTokenProvider,
+    PoTokenResponse,
+    PoTokenProviderError,
+    PoTokenProviderRejectedRequest,
+    register_provider,
+    register_preference,
+    ExternalRequestFeature,
+)
+from yt_dlp.networking.common import Request
+from yt_dlp.extractor.youtube.pot.utils import get_webpo_content_binding
+from yt_dlp.utils import traverse_obj
+from yt_dlp.networking.exceptions import RequestError
+import json
+
+
+@register_provider
+class MyPoTokenProviderPTP(PoTokenProvider):  # Provider class name must end with "PTP"
+    PROVIDER_VERSION = '0.2.1'
+    # Define a unique display name for the provider
+    PROVIDER_NAME = 'my-provider'
+    BUG_REPORT_LOCATION = 'https://issues.example.com/report'
+
+    # -- Validation shortcuts. Set these to None to disable. --
+
+    # Innertube Client Name.
+    # For example, "WEB", "ANDROID", "TVHTML5".
+    # For a list of WebPO client names, 
+    #  see yt_dlp.extractor.youtube.pot.utils.WEBPO_CLIENTS.
+    # Also see yt_dlp.extractor.youtube._base.INNERTUBE_CLIENTS 
+    #  for a list of client names currently supported by the YouTube extractor.
+    _SUPPORTED_CLIENTS = ('WEB', 'TVHTML5')
+
+    _SUPPORTED_CONTEXTS = (
+        PoTokenContext.GVS,
+    )
+
+    # If your provider makes external requests to websites (i.e. to youtube.com) 
+    #  using another library or service (i.e., not _request_webpage),
+    # set the request features that are supported here.
+    # If only using _request_webpage to make external requests, set this to None.
+    _SUPPORTED_EXTERNAL_REQUEST_FEATURES = (
+        ExternalRequestFeature.PROXY_SCHEME_HTTP, 
+        ExternalRequestFeature.SOURCE_ADDRESS, 
+        ExternalRequestFeature.DISABLE_TLS_VERIFICATION
+    )
+
+    def is_available(self) -> bool:
+        """
+        Check if the provider is available (e.g. all required dependencies are available)
+        This is used to determine if the provider should be used and to provide debug information.
+
+        IMPORTANT: This method SHOULD NOT make any network requests or perform any expensive operations.
+
+        Since this is called multiple times, we recommend caching the result.
+        """
+        return True
+
+    def close(self):
+        # Optional close hook, called when YoutubeDL is closed.
+        pass
+
+    def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+        # ℹ️ If you need to validate the request before making the request to the external source.
+        # Raise yt_dlp.extractor.youtube.pot.provider.PoTokenProviderRejectedRequest if the request is not supported.
+        if request.is_authenticated:
+            raise PoTokenProviderRejectedRequest(
+                'This provider does not support authenticated requests'
+            )
+
+        # ℹ️ Settings are pulled from extractor args passed to yt-dlp with the key `youtubepot-<PROVIDER_KEY>`.
+        # For this example, the extractor arg would be:
+        # `--extractor-args "youtubepot-mypotokenprovider:url=https://custom.example.com/get_pot"`
+        external_provider_url = self._configuration_arg(
+            'url', default=['https://provider.example.com/get_pot'])[0]
+        
+        # See below for logging guidelines
+        self.logger.trace(f'Using external provider URL: {external_provider_url}')
+        
+        # You should use the internal HTTP client to make requests where possible,
+        # as it will handle cookies and other networking settings passed to yt-dlp.
+        try:
+            # See docstring in _request_webpage method for request tips
+            response = self._request_webpage(
+                Request(external_provider_url, data=json.dumps({
+                    'content_binding': get_webpo_content_binding(request),
+                    'proxy': request.request_proxy,
+                    'headers': request.request_headers,
+                    'source_address': request.request_source_address,
+                    'verify_tls': request.request_verify_tls,
+                    # Important: If your provider has its own caching, please respect `bypass_cache`.
+                    # This may be used in the future to request a fresh PO Token if required.
+                    'do_not_cache': request.bypass_cache,
+                }).encode(), proxies={'all': None}), 
+                pot_request=request, 
+                note=(
+                  f'Requesting {request.context.value} PO Token '
+                  f'for {request.internal_client_name} client from external provider'),
+            )
+
+        except RequestError as e:
+            # ℹ️ If there is an error, raise PoTokenProviderError.
+            # You can specify whether it is expected or not. If it is unexpected, 
+            #  the log will include a link to the bug report location (BUG_REPORT_LOCATION).
+            raise PoTokenProviderError(
+                'Networking error while fetching to get PO Token from external provider',
+                expected=True
+            ) from e
+
+        # Note: PO Token is expected to be base64url encoded
+        po_token = traverse_obj(response, 'po_token')
+        if not po_token:
+            raise PoTokenProviderError(
+                'Bad PO Token Response from external provider',
+                expected=False
+            )
+
+        return PoTokenResponse(
+            po_token=po_token,
+            # Optional, add a custom expiration timestamp for the token. Use for caching.
+            # By default, yt-dlp will use the default ttl from a registered cache spec (see below)
+            # Set to 0 or -1 to not cache this response.
+            expires_at=None,
+        )
+
+
+# If there are multiple PO Token Providers that can handle the same PoTokenRequest,
+# you can define a preference function to increase/decrease the priority of providers.
+
+@register_preference(MyPoTokenProviderPTP)
+def my_provider_preference(provider: PoTokenProvider, request: PoTokenRequest) -> int:
+    return 50
+```
+
+## Logging Guidelines
+
+- Use the `self.logger` object to log messages.
+- When making HTTP requests or any other expensive operation, use `self.logger.info` to log a message to standard non-verbose output.
+  - This lets users know what is happening when a time-expensive operation is taking place.
+  - It is recommended to include the PO Token context and internal client name in the message if possible.
+  - For example, `self.logger.info(f'Requesting {request.context.value} PO Token for {request.internal_client_name} client from external provider')`.
+- Use `self.logger.debug` to log a message to the verbose output (`--verbose`).
+  - For debugging information visible to users posting verbose logs.
+  - Try to not log too much, prefer using trace logging for detailed debug messages.
+- Use `self.logger.trace` to log a message to the PO Token debug output (`--extractor-args "youtube:pot_trace=true"`). 
+  - Log as much as you like here as needed for debugging your provider.
+- Avoid logging PO Tokens or any sensitive information to debug or info output.
+
+## Debugging
+
+- Use `-v --extractor-args "youtube:pot_trace=true"` to enable PO Token debug output.
+
+## Caching
+
+> [!WARNING]
+> The following describes more advance features that most users/developers will not need to use.
+
+> [!IMPORTANT]
+> yt-dlp currently has a built-in LRU Memory Cache Provider and a cache spec provider for WebPO Tokens. 
+> You should only need to implement cache providers if you want an external cache, or a cache spec if you are handling non-WebPO Tokens.
+
+### Cache Providers
+
+`yt_dlp.extractor.youtube.pot.cache`
+
+```python
+from yt_dlp.extractor.youtube.pot.cache import (
+    PoTokenCacheProvider,
+    register_preference,
+    register_provider
+)
+
+from yt_dlp.extractor.youtube.pot.provider import PoTokenRequest
+
+
+@register_provider
+class MyCacheProviderPCP(PoTokenCacheProvider):  # Provider class name must end with "PCP"
+    PROVIDER_VERSION = '0.1.0'
+    # Define a unique display name for the provider
+    PROVIDER_NAME = 'my-cache-provider'
+    BUG_REPORT_LOCATION = 'https://issues.example.com/report'
+
+    def is_available(self) -> bool:
+        """
+        Check if the provider is available (e.g. all required dependencies are available)
+        This is used to determine if the provider should be used and to provide debug information.
+
+        IMPORTANT: This method SHOULD NOT make any network requests or perform any expensive operations.
+
+        Since this is called multiple times, we recommend caching the result.
+        """
+        return True
+
+    def get(self, key: str):
+        # ℹ️ Similar to PO Token Providers, Cache Providers and Cache Spec Providers 
+        # are passed down extractor args matching key youtubepot-<PROVIDER_KEY>.
+        some_setting = self._configuration_arg('some_setting', default=['default_value'])[0]
+        return self.my_cache.get(key)
+
+    def store(self, key: str, value: str, expires_at: int):
+        # ⚠ expires_at MUST be respected. 
+        # Cache entries should not be returned if they have expired.
+        self.my_cache.store(key, value, expires_at)
+
+    def delete(self, key: str):
+        self.my_cache.delete(key)
+
+    def close(self):
+        # Optional close hook, called when the YoutubeDL instance is closed.
+        pass
+
+# If there are multiple PO Token Cache Providers available, you can 
+# define a preference function to increase/decrease the priority of providers. 
+
+# IMPORTANT: Providers should be in preference of cache lookup time. 
+# For example, a memory cache should have a higher preference than a disk cache. 
+
+# VERY IMPORTANT: yt-dlp has a built-in memory cache with a priority of 10000. 
+# Your cache provider should be lower than this.
+
+
+@register_preference(MyCacheProviderPCP)
+def my_cache_preference(provider: PoTokenCacheProvider, request: PoTokenRequest) -> int:
+    return 50
+```
+
+### Cache Specs
+
+`yt_dlp.extractor.youtube.pot.cache`
+
+These are used to provide information on how to cache a particular PO Token Request. 
+You might have a different cache spec for different kinds of PO Tokens.
+
+```python
+from yt_dlp.extractor.youtube.pot.cache import (
+    PoTokenCacheSpec,
+    PoTokenCacheSpecProvider,
+    CacheProviderWritePolicy,
+    register_spec,
+)
+from yt_dlp.utils import traverse_obj
+from yt_dlp.extractor.youtube.pot.provider import PoTokenRequest
+
+
+@register_spec
+class MyCacheSpecProviderPCSP(PoTokenCacheSpecProvider):  # Provider class name must end with "PCSP"
+    PROVIDER_VERSION = '0.1.0'
+    # Define a unique display name for the provider
+    PROVIDER_NAME = 'mycachespec'
+    BUG_REPORT_LOCATION = 'https://issues.example.com/report'
+
+    def generate_cache_spec(self, request: PoTokenRequest):
+
+        client_name = traverse_obj(request.innertube_context, ('client', 'clientName'))
+        if client_name != 'ANDROID':
+            # ℹ️ If the request is not supported by the cache spec, return None
+            return None
+
+        # Generate a cache spec for the request
+        return PoTokenCacheSpec(
+            # Key bindings to uniquely identify the request. These are used to generate a cache key.
+            key_bindings={
+                'client_name': client_name,
+                'content_binding': 'unique_content_binding',
+                'ip': traverse_obj(request.innertube_context, ('client', 'remoteHost')),
+                'source_address': request.request_source_address,
+                'proxy': request.request_proxy,
+            },
+            # Default Cache TTL in seconds
+            default_ttl=21600,
+
+            # Optional: Specify a write policy.
+            # WRITE_FIRST will write to the highest priority provider only, 
+            #  whereas WRITE_ALL will write to all providers.
+            # WRITE_FIRST may be useful if the PO Token is short-lived 
+            #  and there is no use writing to all providers.
+            write_policy=CacheProviderWritePolicy.WRITE_ALL,
+        )
+```

yt_dlp/extractor/youtube/pot/__init__.py

@@ -0,0 +1,3 @@
+# Trigger import of built-in providers
+from ._builtin.memory_cache import MemoryLRUPCP as _MemoryLRUPCP  # noqa: F401
+from ._builtin.webpo_cachespec import WebPoPCSP as _WebPoPCSP  # noqa: F401

yt_dlp/extractor/youtube/pot/_builtin/memory_cache.py

@@ -0,0 +1,78 @@
+from __future__ import annotations
+
+import datetime as dt
+import typing
+from threading import Lock
+
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.extractor.youtube.pot._registry import _pot_memory_cache
+from yt_dlp.extractor.youtube.pot.cache import (
+    PoTokenCacheProvider,
+    register_preference,
+    register_provider,
+)
+
+
+def initialize_global_cache(max_size: int):
+    if _pot_memory_cache.value.get('cache') is None:
+        _pot_memory_cache.value['cache'] = {}
+        _pot_memory_cache.value['lock'] = Lock()
+        _pot_memory_cache.value['max_size'] = max_size
+
+    if _pot_memory_cache.value['max_size'] != max_size:
+        raise ValueError('Cannot change max_size of initialized global memory cache')
+
+    return (
+        _pot_memory_cache.value['cache'],
+        _pot_memory_cache.value['lock'],
+        _pot_memory_cache.value['max_size'],
+    )
+
+
+@register_provider
+class MemoryLRUPCP(PoTokenCacheProvider, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'memory'
+    DEFAULT_CACHE_SIZE = 25
+
+    def __init__(
+        self,
+        *args,
+        initialize_cache: typing.Callable[[int], tuple[dict[str, tuple[str, int]], Lock, int]] = initialize_global_cache,
+        **kwargs,
+    ):
+        super().__init__(*args, **kwargs)
+        self.cache, self.lock, self.max_size = initialize_cache(self.DEFAULT_CACHE_SIZE)
+
+    def is_available(self) -> bool:
+        return True
+
+    def get(self, key: str) -> str | None:
+        with self.lock:
+            if key not in self.cache:
+                return None
+            value, expires_at = self.cache.pop(key)
+            if expires_at < int(dt.datetime.now(dt.timezone.utc).timestamp()):
+                return None
+            self.cache[key] = (value, expires_at)
+            return value
+
+    def store(self, key: str, value: str, expires_at: int):
+        with self.lock:
+            if expires_at < int(dt.datetime.now(dt.timezone.utc).timestamp()):
+                return
+            if key in self.cache:
+                self.cache.pop(key)
+            self.cache[key] = (value, expires_at)
+            if len(self.cache) > self.max_size:
+                oldest_key = next(iter(self.cache))
+                self.cache.pop(oldest_key)
+
+    def delete(self, key: str):
+        with self.lock:
+            self.cache.pop(key, None)
+
+
+@register_preference(MemoryLRUPCP)
+def memorylru_preference(*_, **__):
+    # Memory LRU Cache SHOULD be the highest priority
+    return 10000

yt_dlp/extractor/youtube/pot/_builtin/webpo_cachespec.py

@@ -0,0 +1,48 @@
+from __future__ import annotations
+
+from yt_dlp.extractor.youtube.pot._provider import BuiltinIEContentProvider
+from yt_dlp.extractor.youtube.pot.cache import (
+    CacheProviderWritePolicy,
+    PoTokenCacheSpec,
+    PoTokenCacheSpecProvider,
+    register_spec,
+)
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenRequest,
+)
+from yt_dlp.extractor.youtube.pot.utils import ContentBindingType, get_webpo_content_binding
+from yt_dlp.utils import traverse_obj
+
+
+@register_spec
+class WebPoPCSP(PoTokenCacheSpecProvider, BuiltinIEContentProvider):
+    PROVIDER_NAME = 'webpo'
+
+    def generate_cache_spec(self, request: PoTokenRequest) -> PoTokenCacheSpec | None:
+        bind_to_visitor_id = self._configuration_arg(
+            'bind_to_visitor_id', default=['true'])[0] == 'true'
+
+        content_binding, content_binding_type = get_webpo_content_binding(
+            request, bind_to_visitor_id=bind_to_visitor_id)
+
+        if not content_binding or not content_binding_type:
+            return None
+
+        write_policy = CacheProviderWritePolicy.WRITE_ALL
+        if content_binding_type == ContentBindingType.VIDEO_ID:
+            write_policy = CacheProviderWritePolicy.WRITE_FIRST
+
+        return PoTokenCacheSpec(
+            key_bindings={
+                't': 'webpo',
+                'cb': content_binding,
+                'cbt': content_binding_type.value,
+                'ip': traverse_obj(request.innertube_context, ('client', 'remoteHost')),
+                'sa': request.request_source_address,
+                'px': request.request_proxy,
+            },
+            # Integrity token response usually states it has a ttl of 12 hours (43200 seconds).
+            # We will default to 6 hours to be safe.
+            default_ttl=21600,
+            write_policy=write_policy,
+        )

yt_dlp/extractor/youtube/pot/_director.py

@@ -0,0 +1,468 @@
+from __future__ import annotations
+
+import base64
+import binascii
+import dataclasses
+import datetime as dt
+import hashlib
+import json
+import typing
+import urllib.parse
+from collections.abc import Iterable
+
+from yt_dlp.extractor.youtube.pot._provider import (
+    BuiltinIEContentProvider,
+    IEContentProvider,
+    IEContentProviderLogger,
+)
+from yt_dlp.extractor.youtube.pot._registry import (
+    _pot_cache_provider_preferences,
+    _pot_cache_providers,
+    _pot_pcs_providers,
+    _pot_providers,
+    _ptp_preferences,
+)
+from yt_dlp.extractor.youtube.pot.cache import (
+    CacheProviderWritePolicy,
+    PoTokenCacheProvider,
+    PoTokenCacheProviderError,
+    PoTokenCacheSpec,
+    PoTokenCacheSpecProvider,
+)
+from yt_dlp.extractor.youtube.pot.provider import (
+    PoTokenProvider,
+    PoTokenProviderError,
+    PoTokenProviderRejectedRequest,
+    PoTokenRequest,
+    PoTokenResponse,
+    provider_bug_report_message,
+)
+from yt_dlp.utils import bug_reports_message, format_field, join_nonempty
+
+if typing.TYPE_CHECKING:
+    from yt_dlp.extractor.youtube.pot.cache import CacheProviderPreference
+    from yt_dlp.extractor.youtube.pot.provider import Preference
+
+
+class YoutubeIEContentProviderLogger(IEContentProviderLogger):
+    def __init__(self, ie, prefix, log_level: IEContentProviderLogger.LogLevel | None = None):
+        self.__ie = ie
+        self.prefix = prefix
+        self.log_level = log_level if log_level is not None else self.LogLevel.INFO
+
+    def _format_msg(self, message: str):
+        prefixstr = format_field(self.prefix, None, '[%s] ')
+        return f'{prefixstr}{message}'
+
+    def trace(self, message: str):
+        if self.log_level <= self.LogLevel.TRACE:
+            self.__ie.write_debug(self._format_msg('TRACE: ' + message))
+
+    def debug(self, message: str):
+        if self.log_level <= self.LogLevel.DEBUG:
+            self.__ie.write_debug(self._format_msg(message))
+
+    def info(self, message: str):
+        if self.log_level <= self.LogLevel.INFO:
+            self.__ie.to_screen(self._format_msg(message))
+
+    def warning(self, message: str, *, once=False):
+        if self.log_level <= self.LogLevel.WARNING:
+            self.__ie.report_warning(self._format_msg(message), only_once=once)
+
+    def error(self, message: str):
+        if self.log_level <= self.LogLevel.ERROR:
+            self.__ie._downloader.report_error(self._format_msg(message), is_error=False)
+
+
+class PoTokenCache:
+
+    def __init__(
+        self,
+        logger: IEContentProviderLogger,
+        cache_providers: list[PoTokenCacheProvider],
+        cache_spec_providers: list[PoTokenCacheSpecProvider],
+        cache_provider_preferences: list[CacheProviderPreference] | None = None,
+    ):
+        self.cache_providers: dict[str, PoTokenCacheProvider] = {
+            provider.PROVIDER_KEY: provider for provider in (cache_providers or [])}
+        self.cache_provider_preferences: list[CacheProviderPreference] = cache_provider_preferences or []
+        self.cache_spec_providers: dict[str, PoTokenCacheSpecProvider] = {
+            provider.PROVIDER_KEY: provider for provider in (cache_spec_providers or [])}
+        self.logger = logger
+
+    def _get_cache_providers(self, request: PoTokenRequest) -> Iterable[PoTokenCacheProvider]:
+        """Sorts available cache providers by preference, given a request"""
+        preferences = {
+            provider: sum(pref(provider, request) for pref in self.cache_provider_preferences)
+            for provider in self.cache_providers.values()
+        }
+        if self.logger.log_level <= self.logger.LogLevel.TRACE:
+            # calling is_available() for every PO Token provider upfront may have some overhead
+            self.logger.trace(f'PO Token Cache Providers: {provider_display_list(self.cache_providers.values())}')
+            self.logger.trace('Cache Provider preferences for this request: {}'.format(', '.join(
+                f'{provider.PROVIDER_KEY}={pref}' for provider, pref in preferences.items())))
+
+        return (
+            provider for provider in sorted(
+                self.cache_providers.values(), key=preferences.get, reverse=True) if provider.is_available())
+
+    def _get_cache_spec(self, request: PoTokenRequest) -> PoTokenCacheSpec | None:
+        for provider in self.cache_spec_providers.values():
+            if not provider.is_available():
+                continue
+            try:
+                spec = provider.generate_cache_spec(request)
+                if not spec:
+                    continue
+                if not validate_cache_spec(spec):
+                    self.logger.error(
+                        f'PoTokenCacheSpecProvider "{provider.PROVIDER_KEY}" generate_cache_spec() '
+                        f'returned invalid spec {spec}{provider_bug_report_message(provider)}')
+                    continue
+                spec = dataclasses.replace(spec, _provider=provider)
+                self.logger.trace(
+                    f'Retrieved cache spec {spec} from cache spec provider "{provider.PROVIDER_NAME}"')
+                return spec
+            except Exception as e:
+                self.logger.error(
+                    f'Error occurred with "{provider.PROVIDER_NAME}" PO Token cache spec provider: '
+                    f'{e!r}{provider_bug_report_message(provider)}')
+                continue
+        return None
+
+    def _generate_key_bindings(self, spec: PoTokenCacheSpec) -> dict[str, str]:
+        bindings_cleaned = {
+            **{k: v for k, v in spec.key_bindings.items() if v is not None},
+            # Allow us to invalidate caches if such need arises
+            '_dlp_cache': 'v1',
+        }
+        if spec._provider:
+            bindings_cleaned['_p'] = spec._provider.PROVIDER_KEY
+        self.logger.trace(f'Generated cache key bindings: {bindings_cleaned}')
+        return bindings_cleaned
+
+    def _generate_key(self, bindings: dict) -> str:
+        binding_string = ''.join(repr(dict(sorted(bindings.items()))))
+        return hashlib.sha256(binding_string.encode()).hexdigest()
+
+    def get(self, request: PoTokenRequest) -> PoTokenResponse | None:
+        spec = self._get_cache_spec(request)
+        if not spec:
+            self.logger.trace('No cache spec available for this request, unable to fetch from cache')
+            return None
+
+        cache_key = self._generate_key(self._generate_key_bindings(spec))
+        self.logger.trace(f'Attempting to access PO Token cache using key: {cache_key}')
+
+        for idx, provider in enumerate(self._get_cache_providers(request)):
+            try:
+                self.logger.trace(
+                    f'Attempting to fetch PO Token response from "{provider.PROVIDER_NAME}" cache provider')
+                cache_response = provider.get(cache_key)
+                if not cache_response:
+                    continue
+                try:
+                    po_token_response = PoTokenResponse(**json.loads(cache_response))
+                except (TypeError, ValueError, json.JSONDecodeError):
+                    po_token_response = None
+                if not validate_response(po_token_response):
+                    self.logger.error(
+                        f'Invalid PO Token response retrieved from cache provider "{provider.PROVIDER_NAME}": '
+                        f'{cache_response}{provider_bug_report_message(provider)}')
+                    provider.delete(cache_key)
+                    continue
+                self.logger.trace(
+                    f'PO Token response retrieved from cache using "{provider.PROVIDER_NAME}" provider: '
+                    f'{po_token_response}')
+                if idx > 0:
+                    # Write back to the highest priority cache provider,
+                    # so we stop trying to fetch from lower priority providers
+                    self.logger.trace('Writing PO Token response to highest priority cache provider')
+                    self.store(request, po_token_response, write_policy=CacheProviderWritePolicy.WRITE_FIRST)
+
+                return po_token_response
+            except PoTokenCacheProviderError as e:
+                self.logger.warning(
+                    f'Error from "{provider.PROVIDER_NAME}" PO Token cache provider: '
+                    f'{e!r}{provider_bug_report_message(provider) if not e.expected else ""}')
+                continue
+            except Exception as e:
+                self.logger.error(
+                    f'Error occurred with "{provider.PROVIDER_NAME}" PO Token cache provider: '
+                    f'{e!r}{provider_bug_report_message(provider)}',
+                )
+                continue
+        return None
+
+    def store(
+        self,
+        request: PoTokenRequest,
+        response: PoTokenResponse,
+        write_policy: CacheProviderWritePolicy | None = None,
+    ):
+        spec = self._get_cache_spec(request)
+        if not spec:
+            self.logger.trace('No cache spec available for this request. Not caching.')
+            return
+
+        if not validate_response(response):
+            self.logger.error(
+                f'Invalid PO Token response provided to PoTokenCache.store(): '
+                f'{response}{bug_reports_message()}')
+            return
+
+        cache_key = self._generate_key(self._generate_key_bindings(spec))
+        self.logger.trace(f'Attempting to access PO Token cache using key: {cache_key}')
+
+        default_expires_at = int(dt.datetime.now(dt.timezone.utc).timestamp()) + spec.default_ttl
+        cache_response = dataclasses.replace(response, expires_at=response.expires_at or default_expires_at)
+
+        write_policy = write_policy or spec.write_policy
+        self.logger.trace(f'Using write policy: {write_policy}')
+
+        for idx, provider in enumerate(self._get_cache_providers(request)):
+            try:
+                self.logger.trace(
+                    f'Caching PO Token response in "{provider.PROVIDER_NAME}" cache provider '
+                    f'(key={cache_key}, expires_at={cache_response.expires_at})')
+                provider.store(
+                    key=cache_key,
+                    value=json.dumps(dataclasses.asdict(cache_response)),
+                    expires_at=cache_response.expires_at)
+            except PoTokenCacheProviderError as e:
+                self.logger.warning(
+                    f'Error from "{provider.PROVIDER_NAME}" PO Token cache provider: '
+                    f'{e!r}{provider_bug_report_message(provider) if not e.expected else ""}')
+            except Exception as e:
+                self.logger.error(
+                    f'Error occurred with "{provider.PROVIDER_NAME}" PO Token cache provider: '
+                    f'{e!r}{provider_bug_report_message(provider)}')
+
+            # WRITE_FIRST should not write to lower priority providers in the case the highest priority provider fails
+            if idx == 0 and write_policy == CacheProviderWritePolicy.WRITE_FIRST:
+                return
+
+    def close(self):
+        for provider in self.cache_providers.values():
+            provider.close()
+        for spec_provider in self.cache_spec_providers.values():
+            spec_provider.close()
+
+
+class PoTokenRequestDirector:
+
+    def __init__(self, logger: IEContentProviderLogger, cache: PoTokenCache):
+        self.providers: dict[str, PoTokenProvider] = {}
+        self.preferences: list[Preference] = []
+        self.cache = cache
+        self.logger = logger
+
+    def register_provider(self, provider: PoTokenProvider):
+        self.providers[provider.PROVIDER_KEY] = provider
+
+    def register_preference(self, preference: Preference):
+        self.preferences.append(preference)
+
+    def _get_providers(self, request: PoTokenRequest) -> Iterable[PoTokenProvider]:
+        """Sorts available providers by preference, given a request"""
+        preferences = {
+            provider: sum(pref(provider, request) for pref in self.preferences)
+            for provider in self.providers.values()
+        }
+        if self.logger.log_level <= self.logger.LogLevel.TRACE:
+            # calling is_available() for every PO Token provider upfront may have some overhead
+            self.logger.trace(f'PO Token Providers: {provider_display_list(self.providers.values())}')
+            self.logger.trace('Provider preferences for this request: {}'.format(', '.join(
+                f'{provider.PROVIDER_NAME}={pref}' for provider, pref in preferences.items())))
+
+        return (
+            provider for provider in sorted(
+                self.providers.values(), key=preferences.get, reverse=True)
+            if provider.is_available()
+        )
+
+    def _get_po_token(self, request) -> PoTokenResponse | None:
+        for provider in self._get_providers(request):
+            try:
+                self.logger.trace(
+                    f'Attempting to fetch a PO Token from "{provider.PROVIDER_NAME}" provider')
+                response = provider.request_pot(request.copy())
+            except PoTokenProviderRejectedRequest as e:
+                self.logger.trace(
+                    f'PO Token Provider "{provider.PROVIDER_NAME}" rejected this request, '
+                    f'trying next available provider. Reason: {e}')
+                continue
+            except PoTokenProviderError as e:
+                self.logger.warning(
+                    f'Error fetching PO Token from "{provider.PROVIDER_NAME}" provider: '
+                    f'{e!r}{provider_bug_report_message(provider) if not e.expected else ""}')
+                continue
+            except Exception as e:
+                self.logger.error(
+                    f'Unexpected error when fetching PO Token from "{provider.PROVIDER_NAME}" provider: '
+                    f'{e!r}{provider_bug_report_message(provider)}')
+                continue
+
+            self.logger.trace(f'PO Token response from "{provider.PROVIDER_NAME}" provider: {response}')
+
+            if not validate_response(response):
+                self.logger.error(
+                    f'Invalid PO Token response received from "{provider.PROVIDER_NAME}" provider: '
+                    f'{response}{provider_bug_report_message(provider)}')
+                continue
+
+            return response
+
+        self.logger.trace('No PO Token providers were able to provide a valid PO Token')
+        return None
+
+    def get_po_token(self, request: PoTokenRequest) -> str | None:
+        if not request.bypass_cache:
+            if pot_response := self.cache.get(request):
+                return clean_pot(pot_response.po_token)
+
+        if not self.providers:
+            self.logger.trace('No PO Token providers registered')
+            return None
+
+        pot_response = self._get_po_token(request)
+        if not pot_response:
+            return None
+
+        pot_response.po_token = clean_pot(pot_response.po_token)
+
+        if pot_response.expires_at is None or pot_response.expires_at > 0:
+            self.cache.store(request, pot_response)
+        else:
+            self.logger.trace(
+                f'PO Token response will not be cached (expires_at={pot_response.expires_at})')
+
+        return pot_response.po_token
+
+    def close(self):
+        for provider in self.providers.values():
+            provider.close()
+        self.cache.close()
+
+
+EXTRACTOR_ARG_PREFIX = 'youtubepot'
+
+
+def initialize_pot_director(ie):
+    assert ie._downloader is not None, 'Downloader not set'
+
+    enable_trace = ie._configuration_arg(
+        'pot_trace', ['false'], ie_key='youtube', casesense=False)[0] == 'true'
+
+    if enable_trace:
+        log_level = IEContentProviderLogger.LogLevel.TRACE
+    elif ie.get_param('verbose', False):
+        log_level = IEContentProviderLogger.LogLevel.DEBUG
+    else:
+        log_level = IEContentProviderLogger.LogLevel.INFO
+
+    def get_provider_logger_and_settings(provider, logger_key):
+        logger_prefix = f'{logger_key}:{provider.PROVIDER_NAME}'
+        extractor_key = f'{EXTRACTOR_ARG_PREFIX}-{provider.PROVIDER_KEY.lower()}'
+        return (
+            YoutubeIEContentProviderLogger(ie, logger_prefix, log_level=log_level),
+            ie.get_param('extractor_args', {}).get(extractor_key, {}))
+
+    cache_providers = []
+    for cache_provider in _pot_cache_providers.value.values():
+        logger, settings = get_provider_logger_and_settings(cache_provider, 'pot:cache')
+        cache_providers.append(cache_provider(ie, logger, settings))
+    cache_spec_providers = []
+    for cache_spec_provider in _pot_pcs_providers.value.values():
+        logger, settings = get_provider_logger_and_settings(cache_spec_provider, 'pot:cache:spec')
+        cache_spec_providers.append(cache_spec_provider(ie, logger, settings))
+
+    cache = PoTokenCache(
+        logger=YoutubeIEContentProviderLogger(ie, 'pot:cache', log_level=log_level),
+        cache_providers=cache_providers,
+        cache_spec_providers=cache_spec_providers,
+        cache_provider_preferences=list(_pot_cache_provider_preferences.value),
+    )
+
+    director = PoTokenRequestDirector(
+        logger=YoutubeIEContentProviderLogger(ie, 'pot', log_level=log_level),
+        cache=cache,
+    )
+
+    ie._downloader.add_close_hook(director.close)
+
+    for provider in _pot_providers.value.values():
+        logger, settings = get_provider_logger_and_settings(provider, 'pot')
+        director.register_provider(provider(ie, logger, settings))
+
+    for preference in _ptp_preferences.value:
+        director.register_preference(preference)
+
+    if director.logger.log_level <= director.logger.LogLevel.DEBUG:
+        # calling is_available() for every PO Token provider upfront may have some overhead
+        director.logger.debug(f'PO Token Providers: {provider_display_list(director.providers.values())}')
+        director.logger.debug(f'PO Token Cache Providers: {provider_display_list(cache.cache_providers.values())}')
+        director.logger.debug(f'PO Token Cache Spec Providers: {provider_display_list(cache.cache_spec_providers.values())}')
+        director.logger.trace(f'Registered {len(director.preferences)} provider preferences')
+        director.logger.trace(f'Registered {len(cache.cache_provider_preferences)} cache provider preferences')
+
+    return director
+
+
+def provider_display_list(providers: Iterable[IEContentProvider]):
+    def provider_display_name(provider):
+        display_str = join_nonempty(
+            provider.PROVIDER_NAME,
+            provider.PROVIDER_VERSION if not isinstance(provider, BuiltinIEContentProvider) else None)
+        statuses = []
+        if not isinstance(provider, BuiltinIEContentProvider):
+            statuses.append('external')
+        if not provider.is_available():
+            statuses.append('unavailable')
+        if statuses:
+            display_str += f' ({", ".join(statuses)})'
+        return display_str
+
+    return ', '.join(provider_display_name(provider) for provider in providers) or 'none'
+
+
+def clean_pot(po_token: str):
+    # Clean and validate the PO Token. This will strip invalid characters off
+    # (e.g. additional url params the user may accidentally include)
+    try:
+        return base64.urlsafe_b64encode(
+            base64.urlsafe_b64decode(urllib.parse.unquote(po_token))).decode()
+    except (binascii.Error, ValueError):
+        raise ValueError('Invalid PO Token')
+
+
+def validate_response(response: PoTokenResponse | None):
+    if (
+        not isinstance(response, PoTokenResponse)
+        or not isinstance(response.po_token, str)
+        or not response.po_token
+    ):  # noqa: SIM103
+        return False
+
+    try:
+        clean_pot(response.po_token)
+    except ValueError:
+        return False
+
+    if not isinstance(response.expires_at, int):
+        return response.expires_at is None
+
+    return response.expires_at <= 0 or response.expires_at > int(dt.datetime.now(dt.timezone.utc).timestamp())
+
+
+def validate_cache_spec(spec: PoTokenCacheSpec):
+    return (
+        isinstance(spec, PoTokenCacheSpec)
+        and isinstance(spec.write_policy, CacheProviderWritePolicy)
+        and isinstance(spec.default_ttl, int)
+        and isinstance(spec.key_bindings, dict)
+        and all(isinstance(k, str) for k in spec.key_bindings)
+        and all(v is None or isinstance(v, str) for v in spec.key_bindings.values())
+        and bool([v for v in spec.key_bindings.values() if v is not None])
+    )

yt_dlp/extractor/youtube/pot/_provider.py

@@ -0,0 +1,156 @@
+from __future__ import annotations
+
+import abc
+import enum
+import functools
+
+from yt_dlp.extractor.common import InfoExtractor
+from yt_dlp.utils import NO_DEFAULT, bug_reports_message, classproperty, traverse_obj
+from yt_dlp.version import __version__
+
+# xxx: these could be generalized outside YoutubeIE eventually
+
+
+class IEContentProviderLogger(abc.ABC):
+
+    class LogLevel(enum.IntEnum):
+        TRACE = 0
+        DEBUG = 10
+        INFO = 20
+        WARNING = 30
+        ERROR = 40
+
+        @classmethod
+        def _missing_(cls, value):
+            if isinstance(value, str):
+                value = value.upper()
+                if value in dir(cls):
+                    return cls[value]
+
+            return cls.INFO
+
+    log_level = LogLevel.INFO
+
+    @abc.abstractmethod
+    def trace(self, message: str):
+        pass
+
+    @abc.abstractmethod
+    def debug(self, message: str):
+        pass
+
+    @abc.abstractmethod
+    def info(self, message: str):
+        pass
+
+    @abc.abstractmethod
+    def warning(self, message: str, *, once=False):
+        pass
+
+    @abc.abstractmethod
+    def error(self, message: str):
+        pass
+
+
+class IEContentProviderError(Exception):
+    def __init__(self, msg=None, expected=False):
+        super().__init__(msg)
+        self.expected = expected
+
+
+class IEContentProvider(abc.ABC):
+    PROVIDER_VERSION: str = '0.0.0'
+    BUG_REPORT_LOCATION: str = '(developer has not provided a bug report location)'
+
+    def __init__(
+        self,
+        ie: InfoExtractor,
+        logger: IEContentProviderLogger,
+        settings: dict[str, list[str]], *_, **__,
+    ):
+        self.ie = ie
+        self.settings = settings or {}
+        self.logger = logger
+        super().__init__()
+
+    @classmethod
+    def __init_subclass__(cls, *, suffix=None, **kwargs):
+        if suffix:
+            cls._PROVIDER_KEY_SUFFIX = suffix
+        return super().__init_subclass__(**kwargs)
+
+    @classproperty
+    def PROVIDER_NAME(cls) -> str:
+        return cls.__name__[:-len(cls._PROVIDER_KEY_SUFFIX)]
+
+    @classproperty
+    def BUG_REPORT_MESSAGE(cls):
+        return f'please report this issue to the provider developer at  {cls.BUG_REPORT_LOCATION}  .'
+
+    @classproperty
+    def PROVIDER_KEY(cls) -> str:
+        assert hasattr(cls, '_PROVIDER_KEY_SUFFIX'), 'Content Provider implementation must define a suffix for the provider key'
+        assert cls.__name__.endswith(cls._PROVIDER_KEY_SUFFIX), f'PoTokenProvider class names must end with "{cls._PROVIDER_KEY_SUFFIX}"'
+        return cls.__name__[:-len(cls._PROVIDER_KEY_SUFFIX)]
+
+    @abc.abstractmethod
+    def is_available(self) -> bool:
+        """
+        Check if the provider is available (e.g. all required dependencies are available)
+        This is used to determine if the provider should be used and to provide debug information.
+
+        IMPORTANT: This method should not make any network requests or perform any expensive operations.
+         It is called multiple times.
+        """
+        raise NotImplementedError
+
+    def close(self):  # noqa: B027
+        pass
+
+    def _configuration_arg(self, key, default=NO_DEFAULT, *, casesense=False):
+        """
+        @returns            A list of values for the setting given by "key"
+                            or "default" if no such key is present
+        @param default      The default value to return when the key is not present (default: [])
+        @param casesense    When false, the values are converted to lower case
+        """
+        val = traverse_obj(self.settings, key)
+        if val is None:
+            return [] if default is NO_DEFAULT else default
+        return list(val) if casesense else [x.lower() for x in val]
+
+
+class BuiltinIEContentProvider(IEContentProvider, abc.ABC):
+    PROVIDER_VERSION = __version__
+    BUG_REPORT_MESSAGE = bug_reports_message(before='')
+
+
+def register_provider_generic(
+    provider,
+    base_class,
+    registry,
+):
+    """Generic function to register a provider class"""
+    assert issubclass(provider, base_class), f'{provider} must be a subclass of {base_class.__name__}'
+    assert provider.PROVIDER_KEY not in registry, f'{base_class.__name__} {provider.PROVIDER_KEY} already registered'
+    registry[provider.PROVIDER_KEY] = provider
+    return provider
+
+
+def register_preference_generic(
+    base_class,
+    registry,
+    *providers,
+):
+    """Generic function to register a preference for a provider"""
+    assert all(issubclass(provider, base_class) for provider in providers)
+
+    def outer(preference):
+        @functools.wraps(preference)
+        def inner(provider, *args, **kwargs):
+            if not providers or isinstance(provider, providers):
+                return preference(provider, *args, **kwargs)
+            return 0
+        registry.add(inner)
+        return preference
+    return outer

yt_dlp/extractor/youtube/pot/_registry.py

@@ -0,0 +1,8 @@
+from yt_dlp.globals import Indirect
+
+_pot_providers = Indirect({})
+_ptp_preferences = Indirect(set())
+_pot_pcs_providers = Indirect({})
+_pot_cache_providers = Indirect({})
+_pot_cache_provider_preferences = Indirect(set())
+_pot_memory_cache = Indirect({})

yt_dlp/extractor/youtube/pot/cache.py

@@ -0,0 +1,97 @@
+"""PUBLIC API"""
+
+from __future__ import annotations
+
+import abc
+import dataclasses
+import enum
+import typing
+
+from yt_dlp.extractor.youtube.pot._provider import (
+    IEContentProvider,
+    IEContentProviderError,
+    register_preference_generic,
+    register_provider_generic,
+)
+from yt_dlp.extractor.youtube.pot._registry import (
+    _pot_cache_provider_preferences,
+    _pot_cache_providers,
+    _pot_pcs_providers,
+)
+from yt_dlp.extractor.youtube.pot.provider import PoTokenRequest
+
+
+class PoTokenCacheProviderError(IEContentProviderError):
+    """An error occurred while fetching a PO Token"""
+
+
+class PoTokenCacheProvider(IEContentProvider, abc.ABC, suffix='PCP'):
+    @abc.abstractmethod
+    def get(self, key: str) -> str | None:
+        pass
+
+    @abc.abstractmethod
+    def store(self, key: str, value: str, expires_at: int):
+        pass
+
+    @abc.abstractmethod
+    def delete(self, key: str):
+        pass
+
+
+class CacheProviderWritePolicy(enum.Enum):
+    WRITE_ALL = enum.auto()    # Write to all cache providers
+    WRITE_FIRST = enum.auto()  # Write to only the first cache provider
+
+
+@dataclasses.dataclass
+class PoTokenCacheSpec:
+    key_bindings: dict[str, str | None]
+    default_ttl: int
+    write_policy: CacheProviderWritePolicy = CacheProviderWritePolicy.WRITE_ALL
+
+    # Internal
+    _provider: PoTokenCacheSpecProvider | None = None
+
+
+class PoTokenCacheSpecProvider(IEContentProvider, abc.ABC, suffix='PCSP'):
+
+    def is_available(self) -> bool:
+        return True
+
+    @abc.abstractmethod
+    def generate_cache_spec(self, request: PoTokenRequest) -> PoTokenCacheSpec | None:
+        """Generate a cache spec for the given request"""
+        pass
+
+
+def register_provider(provider: type[PoTokenCacheProvider]):
+    """Register a PoTokenCacheProvider class"""
+    return register_provider_generic(
+        provider=provider,
+        base_class=PoTokenCacheProvider,
+        registry=_pot_cache_providers.value,
+    )
+
+
+def register_spec(provider: type[PoTokenCacheSpecProvider]):
+    """Register a PoTokenCacheSpecProvider class"""
+    return register_provider_generic(
+        provider=provider,
+        base_class=PoTokenCacheSpecProvider,
+        registry=_pot_pcs_providers.value,
+    )
+
+
+def register_preference(
+        *providers: type[PoTokenCacheProvider]) -> typing.Callable[[CacheProviderPreference], CacheProviderPreference]:
+    """Register a preference for a PoTokenCacheProvider"""
+    return register_preference_generic(
+        PoTokenCacheProvider,
+        _pot_cache_provider_preferences.value,
+        *providers,
+    )
+
+
+if typing.TYPE_CHECKING:
+    CacheProviderPreference = typing.Callable[[PoTokenCacheProvider, PoTokenRequest], int]

yt_dlp/extractor/youtube/pot/provider.py

@@ -0,0 +1,281 @@
+"""PUBLIC API"""
+
+from __future__ import annotations
+
+import abc
+import copy
+import dataclasses
+import enum
+import functools
+import typing
+import urllib.parse
+
+from yt_dlp.cookies import YoutubeDLCookieJar
+from yt_dlp.extractor.youtube.pot._provider import (
+    IEContentProvider,
+    IEContentProviderError,
+    register_preference_generic,
+    register_provider_generic,
+)
+from yt_dlp.extractor.youtube.pot._registry import _pot_providers, _ptp_preferences
+from yt_dlp.networking import Request, Response
+from yt_dlp.utils import traverse_obj
+from yt_dlp.utils.networking import HTTPHeaderDict
+
+__all__ = [
+    'ExternalRequestFeature',
+    'PoTokenContext',
+    'PoTokenProvider',
+    'PoTokenProviderError',
+    'PoTokenProviderRejectedRequest',
+    'PoTokenRequest',
+    'PoTokenResponse',
+    'provider_bug_report_message',
+    'register_preference',
+    'register_provider',
+]
+
+
+class PoTokenContext(enum.Enum):
+    GVS = 'gvs'
+    PLAYER = 'player'
+    SUBS = 'subs'
+
+
+@dataclasses.dataclass
+class PoTokenRequest:
+    # YouTube parameters
+    context: PoTokenContext
+    innertube_context: InnertubeContext
+    innertube_host: str | None = None
+    session_index: str | None = None
+    player_url: str | None = None
+    is_authenticated: bool = False
+    video_webpage: str | None = None
+    internal_client_name: str | None = None
+
+    # Content binding parameters
+    visitor_data: str | None = None
+    data_sync_id: str | None = None
+    video_id: str | None = None
+
+    # Networking parameters
+    request_cookiejar: YoutubeDLCookieJar = dataclasses.field(default_factory=YoutubeDLCookieJar)
+    request_proxy: str | None = None
+    request_headers: HTTPHeaderDict = dataclasses.field(default_factory=HTTPHeaderDict)
+    request_timeout: float | None = None
+    request_source_address: str | None = None
+    request_verify_tls: bool = True
+
+    # Generate a new token, do not used a cached token
+    # The token should still be cached for future requests
+    bypass_cache: bool = False
+
+    def copy(self):
+        return dataclasses.replace(
+            self,
+            request_headers=HTTPHeaderDict(self.request_headers),
+            innertube_context=copy.deepcopy(self.innertube_context),
+        )
+
+
+@dataclasses.dataclass
+class PoTokenResponse:
+    po_token: str
+    expires_at: int | None = None
+
+
+class PoTokenProviderRejectedRequest(IEContentProviderError):
+    """Reject the PoTokenRequest (cannot handle the request)"""
+
+
+class PoTokenProviderError(IEContentProviderError):
+    """An error occurred while fetching a PO Token"""
+
+
+class ExternalRequestFeature(enum.Enum):
+    PROXY_SCHEME_HTTP = enum.auto()
+    PROXY_SCHEME_HTTPS = enum.auto()
+    PROXY_SCHEME_SOCKS4 = enum.auto()
+    PROXY_SCHEME_SOCKS4A = enum.auto()
+    PROXY_SCHEME_SOCKS5 = enum.auto()
+    PROXY_SCHEME_SOCKS5H = enum.auto()
+    SOURCE_ADDRESS = enum.auto()
+    DISABLE_TLS_VERIFICATION = enum.auto()
+
+
+class PoTokenProvider(IEContentProvider, abc.ABC, suffix='PTP'):
+
+    # Set to None to disable the check
+    _SUPPORTED_CONTEXTS: tuple[PoTokenContext] | None = ()
+
+    # Innertube Client Name.
+    # For example, "WEB", "ANDROID", "TVHTML5".
+    # For a list of WebPO client names, see yt_dlp.extractor.youtube.pot.utils.WEBPO_CLIENTS.
+    # Also see yt_dlp.extractor.youtube._base.INNERTUBE_CLIENTS
+    #  for a list of client names currently supported by the YouTube extractor.
+    _SUPPORTED_CLIENTS: tuple[str] | None = ()
+
+    # If making external requests to websites (i.e. to youtube.com)
+    #  using another library or service (i.e., not _request_webpage),
+    #  add the request features that are supported.
+    # If only using _request_webpage to make external requests, set this to None.
+    _SUPPORTED_EXTERNAL_REQUEST_FEATURES: tuple[ExternalRequestFeature] | None = ()
+
+    def __validate_request(self, request: PoTokenRequest):
+        if not self.is_available():
+            raise PoTokenProviderRejectedRequest(f'{self.PROVIDER_NAME} is not available')
+
+        # Validate request using built-in settings
+        if (
+            self._SUPPORTED_CONTEXTS is not None
+            and request.context not in self._SUPPORTED_CONTEXTS
+        ):
+            raise PoTokenProviderRejectedRequest(
+                f'PO Token Context "{request.context}" is not supported by {self.PROVIDER_NAME}')
+
+        if self._SUPPORTED_CLIENTS is not None:
+            client_name = traverse_obj(
+                request.innertube_context, ('client', 'clientName'))
+            if client_name not in self._SUPPORTED_CLIENTS:
+                raise PoTokenProviderRejectedRequest(
+                    f'Client "{client_name}" is not supported by {self.PROVIDER_NAME}. '
+                    f'Supported clients: {", ".join(self._SUPPORTED_CLIENTS) or "none"}')
+
+        self.__validate_external_request_features(request)
+
+    @functools.cached_property
+    def _supported_proxy_schemes(self):
+        return {
+            scheme: feature
+            for scheme, feature in {
+                'http': ExternalRequestFeature.PROXY_SCHEME_HTTP,
+                'https': ExternalRequestFeature.PROXY_SCHEME_HTTPS,
+                'socks4': ExternalRequestFeature.PROXY_SCHEME_SOCKS4,
+                'socks4a': ExternalRequestFeature.PROXY_SCHEME_SOCKS4A,
+                'socks5': ExternalRequestFeature.PROXY_SCHEME_SOCKS5,
+                'socks5h': ExternalRequestFeature.PROXY_SCHEME_SOCKS5H,
+            }.items()
+            if feature in (self._SUPPORTED_EXTERNAL_REQUEST_FEATURES or [])
+        }
+
+    def __validate_external_request_features(self, request: PoTokenRequest):
+        if self._SUPPORTED_EXTERNAL_REQUEST_FEATURES is None:
+            return
+
+        if request.request_proxy:
+            scheme = urllib.parse.urlparse(request.request_proxy).scheme
+            if scheme.lower() not in self._supported_proxy_schemes:
+                raise PoTokenProviderRejectedRequest(
+                    f'External requests by "{self.PROVIDER_NAME}" provider do not '
+                    f'support proxy scheme "{scheme}". Supported proxy schemes: '
+                    f'{", ".join(self._supported_proxy_schemes) or "none"}')
+
+        if (
+            request.request_source_address
+            and ExternalRequestFeature.SOURCE_ADDRESS not in self._SUPPORTED_EXTERNAL_REQUEST_FEATURES
+        ):
+            raise PoTokenProviderRejectedRequest(
+                f'External requests by "{self.PROVIDER_NAME}" provider '
+                f'do not support setting source address')
+
+        if (
+            not request.request_verify_tls
+            and ExternalRequestFeature.DISABLE_TLS_VERIFICATION not in self._SUPPORTED_EXTERNAL_REQUEST_FEATURES
+        ):
+            raise PoTokenProviderRejectedRequest(
+                f'External requests by "{self.PROVIDER_NAME}" provider '
+                f'do not support ignoring TLS certificate failures')
+
+    def request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+        self.__validate_request(request)
+        return self._real_request_pot(request)
+
+    @abc.abstractmethod
+    def _real_request_pot(self, request: PoTokenRequest) -> PoTokenResponse:
+        """To be implemented by subclasses"""
+        pass
+
+    # Helper functions
+
+    def _request_webpage(self, request: Request, pot_request: PoTokenRequest | None = None, note=None, **kwargs) -> Response:
+        """Make a request using the internal HTTP Client.
+        Use this instead of calling requests, urllib3 or other HTTP client libraries directly!
+
+        YouTube cookies will be automatically applied if this request is made to YouTube.
+
+        @param request: The request to make
+        @param pot_request: The PoTokenRequest to use. Request parameters will be merged from it.
+        @param note: Custom log message to display when making the request. Set to `False` to disable logging.
+
+        Tips:
+        - Disable proxy (e.g. if calling local service): Request(..., proxies={'all': None})
+        - Set request timeout:  Request(..., extensions={'timeout': 5.0})
+        """
+        req = request.copy()
+
+        # Merge some ctx request settings into the request
+        # Most of these will already be used by the configured ydl instance,
+        # however, the YouTube extractor may override some.
+        if pot_request is not None:
+            req.headers = HTTPHeaderDict(pot_request.request_headers, req.headers)
+            req.proxies = req.proxies or ({'all': pot_request.request_proxy} if pot_request.request_proxy else {})
+
+            if pot_request.request_cookiejar is not None:
+                req.extensions['cookiejar'] = req.extensions.get('cookiejar', pot_request.request_cookiejar)
+
+        if note is not False:
+            self.logger.info(str(note) if note else 'Requesting webpage')
+        return self.ie._downloader.urlopen(req)
+
+
+def register_provider(provider: type[PoTokenProvider]):
+    """Register a PoTokenProvider class"""
+    return register_provider_generic(
+        provider=provider,
+        base_class=PoTokenProvider,
+        registry=_pot_providers.value,
+    )
+
+
+def provider_bug_report_message(provider: IEContentProvider, before=';'):
+    msg = provider.BUG_REPORT_MESSAGE
+
+    before = before.rstrip()
+    if not before or before.endswith(('.', '!', '?')):
+        msg = msg[0].title() + msg[1:]
+
+    return f'{before} {msg}' if before else msg
+
+
+def register_preference(*providers: type[PoTokenProvider]) -> typing.Callable[[Preference], Preference]:
+    """Register a preference for a PoTokenProvider"""
+    return register_preference_generic(
+        PoTokenProvider,
+        _ptp_preferences.value,
+        *providers,
+    )
+
+
+if typing.TYPE_CHECKING:
+    Preference = typing.Callable[[PoTokenProvider, PoTokenRequest], int]
+    __all__.append('Preference')
+
+    # Barebones innertube context. There may be more fields.
+    class ClientInfo(typing.TypedDict, total=False):
+        hl: str | None
+        gl: str | None
+        remoteHost: str | None
+        deviceMake: str | None
+        deviceModel: str | None
+        visitorData: str | None
+        userAgent: str | None
+        clientName: str
+        clientVersion: str
+        osName: str | None
+        osVersion: str | None
+
+    class InnertubeContext(typing.TypedDict, total=False):
+        client: ClientInfo
+        request: dict
+        user: dict

yt_dlp/extractor/youtube/pot/utils.py

@@ -0,0 +1,73 @@
+"""PUBLIC API"""
+
+from __future__ import annotations
+
+import base64
+import contextlib
+import enum
+import re
+import urllib.parse
+
+from yt_dlp.extractor.youtube.pot.provider import PoTokenContext, PoTokenRequest
+from yt_dlp.utils import traverse_obj
+
+__all__ = ['WEBPO_CLIENTS', 'ContentBindingType', 'get_webpo_content_binding']
+
+WEBPO_CLIENTS = (
+    'WEB',
+    'MWEB',
+    'TVHTML5',
+    'WEB_EMBEDDED_PLAYER',
+    'WEB_CREATOR',
+    'WEB_REMIX',
+    'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
+)
+
+
+class ContentBindingType(enum.Enum):
+    VISITOR_DATA = 'visitor_data'
+    DATASYNC_ID = 'datasync_id'
+    VIDEO_ID = 'video_id'
+    VISITOR_ID = 'visitor_id'
+
+
+def get_webpo_content_binding(
+    request: PoTokenRequest,
+    webpo_clients=WEBPO_CLIENTS,
+    bind_to_visitor_id=False,
+) -> tuple[str | None, ContentBindingType | None]:
+
+    client_name = traverse_obj(request.innertube_context, ('client', 'clientName'))
+    if not client_name or client_name not in webpo_clients:
+        return None, None
+
+    if request.context == PoTokenContext.GVS or client_name in ('WEB_REMIX', ):
+        if request.is_authenticated:
+            return request.data_sync_id, ContentBindingType.DATASYNC_ID
+        else:
+            if bind_to_visitor_id:
+                visitor_id = _extract_visitor_id(request.visitor_data)
+                if visitor_id:
+                    return visitor_id, ContentBindingType.VISITOR_ID
+            return request.visitor_data, ContentBindingType.VISITOR_DATA
+
+    elif request.context in (PoTokenContext.PLAYER, PoTokenContext.SUBS):
+        return request.video_id, ContentBindingType.VIDEO_ID
+
+    return None, None
+
+
+def _extract_visitor_id(visitor_data):
+    if not visitor_data:
+        return None
+
+    # Attempt to extract the visitor ID from the visitor_data protobuf
+    # xxx: ideally should use a protobuf parser
+    with contextlib.suppress(Exception):
+        visitor_id = base64.urlsafe_b64decode(
+            urllib.parse.unquote_plus(visitor_data))[2:13].decode()
+        # check that visitor id is all letters and numbers
+        if re.fullmatch(r'[A-Za-z0-9_-]{11}', visitor_id):
+            return visitor_id
+
+    return None

yt_dlp/jsinterp.py

@@ -590,39 +590,12 @@ class JSInterpreter:
                     return ret, True
             return ret, False
 
-        for m in re.finditer(rf'''(?x)
-                (?P<pre_sign>\+\+|--)(?P<var1>{_NAME_RE})|
-                (?P<var2>{_NAME_RE})(?P<post_sign>\+\+|--)''', expr):
-            var = m.group('var1') or m.group('var2')
-            start, end = m.span()
-            sign = m.group('pre_sign') or m.group('post_sign')
-            ret = local_vars[var]
-            local_vars[var] += 1 if sign[0] == '+' else -1
-            if m.group('pre_sign'):
-                ret = local_vars[var]
-            expr = expr[:start] + self._dump(ret, local_vars) + expr[end:]
-
-        if not expr:
-            return None, should_return
-
         m = re.match(fr'''(?x)
-            (?P<assign>
                 (?P<out>{_NAME_RE})(?:\[(?P<index>{_NESTED_BRACKETS})\])?\s*
                 (?P<op>{"|".join(map(re.escape, set(_OPERATORS) - _COMP_OPERATORS))})?
                 =(?!=)(?P<expr>.*)$
-            )|(?P<return>
-                (?!if|return|true|false|null|undefined|NaN)(?P<name>{_NAME_RE})$
-            )|(?P<attribute>
-                (?P<var>{_NAME_RE})(?:
-                    (?P<nullish>\?)?\.(?P<member>[^(]+)|
-                    \[(?P<member2>{_NESTED_BRACKETS})\]
-                )\s*
-            )|(?P<indexing>
-                (?P<in>{_NAME_RE})\[(?P<idx>.+)\]$
-            )|(?P<function>
-                (?P<fname>{_NAME_RE})\((?P<args>.*)\)$
-            )''', expr)
-        if m and m.group('assign'):
+            ''', expr)
+        if m:  # We are assigning a value to a variable
             left_val = local_vars.get(m.group('out'))
 
             if not m.group('index'):
@@ -640,7 +613,35 @@ class JSInterpreter:
                 m.group('op'), self._index(left_val, idx), m.group('expr'), expr, local_vars, allow_recursion)
             return left_val[idx], should_return
 
-        elif expr.isdigit():
+        for m in re.finditer(rf'''(?x)
+                (?P<pre_sign>\+\+|--)(?P<var1>{_NAME_RE})|
+                (?P<var2>{_NAME_RE})(?P<post_sign>\+\+|--)''', expr):
+            var = m.group('var1') or m.group('var2')
+            start, end = m.span()
+            sign = m.group('pre_sign') or m.group('post_sign')
+            ret = local_vars[var]
+            local_vars[var] += 1 if sign[0] == '+' else -1
+            if m.group('pre_sign'):
+                ret = local_vars[var]
+            expr = expr[:start] + self._dump(ret, local_vars) + expr[end:]
+
+        if not expr:
+            return None, should_return
+
+        m = re.match(fr'''(?x)
+            (?P<return>
+                (?!if|return|true|false|null|undefined|NaN)(?P<name>{_NAME_RE})$
+            )|(?P<attribute>
+                (?P<var>{_NAME_RE})(?:
+                    (?P<nullish>\?)?\.(?P<member>[^(]+)|
+                    \[(?P<member2>{_NESTED_BRACKETS})\]
+                )\s*
+            )|(?P<indexing>
+                (?P<in>{_NAME_RE})\[(?P<idx>.+)\]$
+            )|(?P<function>
+                (?P<fname>{_NAME_RE})\((?P<args>.*)\)$
+            )''', expr)
+        if expr.isdigit():
             return int(expr), should_return
 
         elif expr == 'break':

yt_dlp/networking/_curlcffi.py

@@ -6,7 +6,8 @@ import math
 import re
 import urllib.parse
 
-from ._helper import InstanceStoreMixin, select_proxy
+from ._helper import InstanceStoreMixin
+from ..utils.networking import select_proxy
 from .common import (
     Features,
     Request,

yt_dlp/networking/_helper.py

@@ -13,7 +13,6 @@ import urllib.request
 from .exceptions import RequestError
 from ..dependencies import certifi
 from ..socks import ProxyType, sockssocket
-from ..utils import format_field, traverse_obj
 
 if typing.TYPE_CHECKING:
     from collections.abc import Iterable
@@ -82,19 +81,6 @@ def make_socks_proxy_opts(socks_proxy):
     }
 
 
-def select_proxy(url, proxies):
-    """Unified proxy selector for all backends"""
-    url_components = urllib.parse.urlparse(url)
-    if 'no' in proxies:
-        hostport = url_components.hostname + format_field(url_components.port, None, ':%s')
-        if urllib.request.proxy_bypass_environment(hostport, {'no': proxies['no']}):
-            return
-        elif urllib.request.proxy_bypass(hostport):  # check system settings
-            return
-
-    return traverse_obj(proxies, url_components.scheme or 'http', 'all')
-
-
 def get_redirect_method(method, status):
     """Unified redirect method handling"""
 

yt_dlp/networking/_requests.py

@@ -10,7 +10,7 @@ import warnings
 
 from ..dependencies import brotli, requests, urllib3
 from ..utils import bug_reports_message, int_or_none, variadic
-from ..utils.networking import normalize_url
+from ..utils.networking import normalize_url, select_proxy
 
 if requests is None:
     raise ImportError('requests module is not installed')
@@ -41,7 +41,6 @@ from ._helper import (
     create_socks_proxy_socket,
     get_redirect_method,
     make_socks_proxy_opts,
-    select_proxy,
 )
 from .common import (
     Features,

yt_dlp/networking/_urllib.py

@@ -26,7 +26,6 @@ from ._helper import (
     create_socks_proxy_socket,
     get_redirect_method,
     make_socks_proxy_opts,
-    select_proxy,
 )
 from .common import Features, RequestHandler, Response, register_rh
 from .exceptions import (
@@ -41,7 +40,7 @@ from .exceptions import (
 from ..dependencies import brotli
 from ..socks import ProxyError as SocksProxyError
 from ..utils import update_url_query
-from ..utils.networking import normalize_url
+from ..utils.networking import normalize_url, select_proxy
 
 SUPPORTED_ENCODINGS = ['gzip', 'deflate']
 CONTENT_DECODE_ERRORS = [zlib.error, OSError]

yt_dlp/networking/_websockets.py

@@ -11,8 +11,8 @@ from ._helper import (
     create_connection,
     create_socks_proxy_socket,
     make_socks_proxy_opts,
-    select_proxy,
 )
+from ..utils.networking import select_proxy
 from .common import Features, Response, register_rh
 from .exceptions import (
     CertificateVerifyError,

yt_dlp/options.py

@@ -230,6 +230,9 @@ class _YoutubeDLOptionParser(optparse.OptionParser):
         formatter.indent()
         heading = formatter.format_heading('Preset Aliases')
         formatter.indent()
+        description = formatter.format_description(
+            'Predefined aliases for convenience and ease of use. Note that future versions of yt-dlp '
+            'may add or adjust presets, but the existing preset names will not be changed or removed')
         result = []
         for name, args in _PRESET_ALIASES.items():
             option = optparse.Option('-t', help=shlex.join(args))
@@ -238,7 +241,7 @@ class _YoutubeDLOptionParser(optparse.OptionParser):
         formatter.dedent()
         formatter.dedent()
         help_lines = '\n'.join(result)
-        return f'{formatted_help}\n{heading}{help_lines}'
+        return f'{formatted_help}\n{heading}{description}\n{help_lines}'
 
 
 def create_parser():
@@ -470,7 +473,7 @@ def create_parser():
     general.add_option(
         '--live-from-start',
         action='store_true', dest='live_from_start',
-        help='Download livestreams from the start. Currently only supported for YouTube (Experimental)')
+        help='Download livestreams from the start. Currently experimental and only supported for YouTube and Twitch')
     general.add_option(
         '--no-live-from-start',
         action='store_false', dest='live_from_start',
@@ -545,9 +548,9 @@ def create_parser():
         help=(
             'Create aliases for an option string. Unless an alias starts with a dash "-", it is prefixed with "--". '
             'Arguments are parsed according to the Python string formatting mini-language. '
-            'E.g. --alias get-audio,-X "-S=aext:{0},abr -x --audio-format {0}" creates options '
+            '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 '
-            '"-S=aext:ARG0,abr -x --audio-format ARG0". All defined aliases are listed in the --help output. '
+            '"-S aext:ARG0,abr -x --audio-format ARG0". All defined aliases are listed in the --help output. '
             'Alias options can trigger more aliases; so be careful to avoid defining recursive options. '
             f'As a safety measure, each alias may be triggered a maximum of {_YoutubeDLOptionParser.ALIAS_TRIGGER_LIMIT} times. '
             'This option can be used multiple times'))

yt_dlp/utils/networking.py

@@ -10,7 +10,8 @@ import urllib.request
 if typing.TYPE_CHECKING:
     T = typing.TypeVar('T')
 
-from ._utils import NO_DEFAULT, remove_start
+from ._utils import NO_DEFAULT, remove_start, format_field
+from .traversal import traverse_obj
 
 
 def random_user_agent():
@@ -278,3 +279,16 @@ def normalize_url(url):
         query=escape_rfc3986(url_parsed.query),
         fragment=escape_rfc3986(url_parsed.fragment),
     ).geturl()
+
+
+def select_proxy(url, proxies):
+    """Unified proxy selector for all backends"""
+    url_components = urllib.parse.urlparse(url)
+    if 'no' in proxies:
+        hostport = url_components.hostname + format_field(url_components.port, None, ':%s')
+        if urllib.request.proxy_bypass_environment(hostport, {'no': proxies['no']}):
+            return
+        elif urllib.request.proxy_bypass(hostport):  # check system settings
+            return
+
+    return traverse_obj(proxies, url_components.scheme or 'http', 'all')

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2025.04.30'
+__version__ = '2025.05.22'
 
-RELEASE_GIT_HEAD = '505b400795af557bdcfd9d4fa7e9133b26ef431c'
+RELEASE_GIT_HEAD = '7977b329ed97b216e37bd402f4935f28c00eac9e'
 
 VARIANT = None
 
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
 
 ORIGIN = 'yt-dlp/yt-dlp'
 
-_pkg_version = '2025.04.30'
+_pkg_version = '2025.05.22'