minor logging improvements

Authored by: doe1080

CONTRIBUTORS

@@ -757,3 +757,6 @@ rysson
 somini
 thedenv
 vallovic
+arabcoders
+mireq
+mlabeeb03

Changelog.md

@@ -4,6 +4,69 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2025.03.31
+
+#### Core changes
+- [Add `--compat-options 2024`](https://github.com/yt-dlp/yt-dlp/commit/22e34adbd741e1c7072015debd615dc3fb71c401) ([#12789](https://github.com/yt-dlp/yt-dlp/issues/12789)) by [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **francaisfacile**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb321cfdc3fd4400598ddb12a15862bc2ac8fc10) ([#12787](https://github.com/yt-dlp/yt-dlp/issues/12787)) by [mlabeeb03](https://github.com/mlabeeb03)
+- **generic**: [Validate response before checking m3u8 live status](https://github.com/yt-dlp/yt-dlp/commit/9a1ec1d36e172d252714cef712a6d091e0a0c4f2) ([#12784](https://github.com/yt-dlp/yt-dlp/issues/12784)) by [bashonly](https://github.com/bashonly)
+- **microsoftlearnepisode**: [Extract more formats](https://github.com/yt-dlp/yt-dlp/commit/d63696f23a341ee36a3237ccb5d5e14b34c2c579) ([#12799](https://github.com/yt-dlp/yt-dlp/issues/12799)) by [bashonly](https://github.com/bashonly)
+- **mlbtv**: [Fix radio-only extraction](https://github.com/yt-dlp/yt-dlp/commit/f033d86b96b36f8c5289dd7c3304f42d4d9f6ff4) ([#12792](https://github.com/yt-dlp/yt-dlp/issues/12792)) by [bashonly](https://github.com/bashonly)
+- **on24**: [Support `mainEvent` URLs](https://github.com/yt-dlp/yt-dlp/commit/e465b078ead75472fcb7b86f6ccaf2b5d3bc4c21) ([#12800](https://github.com/yt-dlp/yt-dlp/issues/12800)) by [bashonly](https://github.com/bashonly)
+- **sbs**: [Fix subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/29560359120f28adaaac67c86fa8442eb72daa0d) ([#12785](https://github.com/yt-dlp/yt-dlp/issues/12785)) by [bashonly](https://github.com/bashonly)
+- **stvr**: [Rename extractor from RTVS to STVR](https://github.com/yt-dlp/yt-dlp/commit/5fc521cbd0ce7b2410d0935369558838728e205d) ([#12788](https://github.com/yt-dlp/yt-dlp/issues/12788)) by [mireq](https://github.com/mireq)
+- **twitch**: clips: [Extract portrait formats](https://github.com/yt-dlp/yt-dlp/commit/61046c31612b30c749cbdae934b7fe26abe659d7) ([#12763](https://github.com/yt-dlp/yt-dlp/issues/12763)) by [DmitryScaletta](https://github.com/DmitryScaletta)
+- **youtube**
+    - [Add `player_js_variant` extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/07f04005e40ebdb368920c511e36e98af0077ed3) ([#12767](https://github.com/yt-dlp/yt-dlp/issues/12767)) by [bashonly](https://github.com/bashonly)
+    - tab: [Fix playlist continuation extraction](https://github.com/yt-dlp/yt-dlp/commit/6a6d97b2cbc78f818de05cc96edcdcfd52caa259) ([#12777](https://github.com/yt-dlp/yt-dlp/issues/12777)) by [coletdjnz](https://github.com/coletdjnz)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [5e457af](https://github.com/yt-dlp/yt-dlp/commit/5e457af57fae9645b1b8fa0ed689229c8fb9656b) by [bashonly](https://github.com/bashonly)
+
+### 2025.03.27
+
+#### Core changes
+- **jsinterp**: [Fix nested attributes and object extraction](https://github.com/yt-dlp/yt-dlp/commit/a8b9ff3c2a0ae25735e580173becc78545b92572) ([#12760](https://github.com/yt-dlp/yt-dlp/issues/12760)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- **youtube**: [Make signature and nsig extraction more robust](https://github.com/yt-dlp/yt-dlp/commit/48be862b32648bff5b3e553e40fca4dcc6e88b28) ([#12761](https://github.com/yt-dlp/yt-dlp/issues/12761)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
+
+### 2025.03.26
+
+#### Extractor changes
+- **youtube**
+    - [Fix signature and nsig extraction for player `4fcd6e4a`](https://github.com/yt-dlp/yt-dlp/commit/a550dfc904a02843a26369ae50dbb7c0febfb30e) ([#12748](https://github.com/yt-dlp/yt-dlp/issues/12748)) by [seproDev](https://github.com/seproDev)
+    - [Only cache nsig code on successful decoding](https://github.com/yt-dlp/yt-dlp/commit/ecee97b4fa90d51c48f9154c3a6d5a8ffe46cd5c) ([#12750](https://github.com/yt-dlp/yt-dlp/issues/12750)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
+
+### 2025.03.25
+
+#### Core changes
+- [Fix attribute error on failed VT init](https://github.com/yt-dlp/yt-dlp/commit/b872ffec50fd50f790a5a490e006a369a28a3df3) ([#12696](https://github.com/yt-dlp/yt-dlp/issues/12696)) by [Grub4K](https://github.com/Grub4K)
+- **utils**: `js_to_json`: [Make function less fatal](https://github.com/yt-dlp/yt-dlp/commit/9491b44032b330e05bd5eaa546187005d1e8538e) ([#12715](https://github.com/yt-dlp/yt-dlp/issues/12715)) by [seproDev](https://github.com/seproDev)
+
+#### Extractor changes
+- [Fix sorting of HLS audio formats by `GROUP-ID`](https://github.com/yt-dlp/yt-dlp/commit/86ab79e1a5182092321102adf6ca34195803b878) ([#12714](https://github.com/yt-dlp/yt-dlp/issues/12714)) by [bashonly](https://github.com/bashonly)
+- **17live**: vod: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/3396eb50dcd245b49c0f4aecd6e80ec914095d16) ([#12723](https://github.com/yt-dlp/yt-dlp/issues/12723)) by [subrat-lima](https://github.com/subrat-lima)
+- **9now.com.au**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/9d5e6de2e7a47226d1f72c713ad45c88ba01db68) ([#12702](https://github.com/yt-dlp/yt-dlp/issues/12702)) by [bashonly](https://github.com/bashonly)
+- **chzzk**: video: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/e2dfccaf808b406d5bcb7dd04ae9ce420752dd6f) ([#12692](https://github.com/yt-dlp/yt-dlp/issues/12692)) by [bashonly](https://github.com/bashonly), [dirkf](https://github.com/dirkf)
+- **deezer**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/be5af3f9e91747768c2b41157851bfbe14c663f7) ([#12704](https://github.com/yt-dlp/yt-dlp/issues/12704)) by [seproDev](https://github.com/seproDev)
+- **generic**: [Fix MPD base URL parsing](https://github.com/yt-dlp/yt-dlp/commit/5086d4aed6aeb3908c62f49e2d8f74cc0cb05110) ([#12718](https://github.com/yt-dlp/yt-dlp/issues/12718)) by [fireattack](https://github.com/fireattack)
+- **streaks**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/801afeac91f97dc0b58cd39cc7e8c50f619dc4e1) ([#12679](https://github.com/yt-dlp/yt-dlp/issues/12679)) by [doe1080](https://github.com/doe1080)
+- **tver**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/66e0bab814e4a52ef3e12d81123ad992a29df50e) ([#12659](https://github.com/yt-dlp/yt-dlp/issues/12659)) by [arabcoders](https://github.com/arabcoders), [bashonly](https://github.com/bashonly)
+- **viki**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/fe4f14b8369038e7c58f7de546d76de1ce3a91ce) ([#12703](https://github.com/yt-dlp/yt-dlp/issues/12703)) by [seproDev](https://github.com/seproDev)
+- **vrsquare**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/b7fbb5a0a16a8e8d3e29c29e26ebed677d0d6ea3) ([#12515](https://github.com/yt-dlp/yt-dlp/issues/12515)) by [doe1080](https://github.com/doe1080)
+- **youtube**
+    - [Fix PhantomJS nsig fallback](https://github.com/yt-dlp/yt-dlp/commit/4054a2b623bd1e277b49d2e9abc3d112a4b1c7be) ([#12728](https://github.com/yt-dlp/yt-dlp/issues/12728)) by [bashonly](https://github.com/bashonly)
+    - [Fix signature and nsig extraction for player `363db69b`](https://github.com/yt-dlp/yt-dlp/commit/b9c979461b244713bf42691a5bc02834e2ba4b2c) ([#12725](https://github.com/yt-dlp/yt-dlp/issues/12725)) by [bashonly](https://github.com/bashonly)
+
+#### Networking changes
+- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.10.x](https://github.com/yt-dlp/yt-dlp/commit/9bf23902ceb948b9685ce1dab575491571720fc6) ([#12670](https://github.com/yt-dlp/yt-dlp/issues/12670)) by [Grub4K](https://github.com/Grub4K)
+
+#### Misc. changes
+- **cleanup**: Miscellaneous: [9dde546](https://github.com/yt-dlp/yt-dlp/commit/9dde546e7ee3e1515d88ee3af08b099351455dc0) by [seproDev](https://github.com/seproDev)
+
 ### 2025.03.21
 
 #### Core changes

README.md

@@ -1770,7 +1770,7 @@ The following extractors use this feature:
 * `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_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
+* `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.
 * `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`
@@ -1782,6 +1782,15 @@ The following extractors use this feature:
 * `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 settings
+* `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)
+* `pot_log_level`: PO Token provider log level. One of `TRACE`, `DEBUG`, `INFO`, `WARNING`, `ERROR`. Default is `DEBUG` if `-v` is used, otherwise `INFO`
+* `fetch_pot`: Policy to use for fetching a PO Token from providers. `always` to always try fetch a PO Token regardless if the client requires one for the given context. `when_required` to only fetch a PO Token if the client requires one for the given context (default)
+
+###### youtubepot-webpo
+* `bind_to_visitor_id`: Whether to use the Visitor ID instead of Visitor Data for caching WebPO tokens. Either `true` or `false` (default `true`)
 
 #### 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)
@@ -1866,6 +1875,9 @@ The following extractors use this feature:
 #### sonylivseries
 * `sort_order`: Episode sort order for series extraction - one of `asc` (ascending, oldest first) or `desc` (descending, newest first). Default is `asc`
 
+#### tver
+* `backend`: Backend API to use for extraction - one of `streaks` (default) or `brightcove` (deprecated)
+
 **Note**: These options may be changed/removed in the future without concern for backward compatibility
 
 <!-- MANPAGE: MOVE "INSTALLATION" SECTION HERE -->
@@ -2215,7 +2227,7 @@ Some of yt-dlp's default options are different from that of youtube-dl and youtu
 * Live chats (if available) are considered as subtitles. Use `--sub-langs all,-live_chat` to download all subtitles except live chat. You can also use `--compat-options no-live-chat` to prevent any live chat/danmaku from downloading
 * YouTube channel URLs download all uploads of the channel. To download only the videos in a specific tab, pass the tab's URL. If the channel does not show the requested tab, an error will be raised. Also, `/live` URLs raise an error if there are no live videos instead of silently downloading the entire channel. You may use `--compat-options no-youtube-channel-redirect` to revert all these redirections
 * Unavailable videos are also listed for YouTube playlists. Use `--compat-options no-youtube-unavailable-videos` to remove this
-* The upload dates extracted from YouTube are in UTC [when available](https://github.com/yt-dlp/yt-dlp/blob/89e4d86171c7b7c997c77d4714542e0383bf0db0/yt_dlp/extractor/youtube.py#L3898-L3900). Use `--compat-options no-youtube-prefer-utc-upload-date` to prefer the non-UTC upload date.
+* The upload dates extracted from YouTube are in UTC.
 * If `ffmpeg` is used as the downloader, the downloading and merging of formats happen in a single step when possible. Use `--compat-options no-direct-merge` to revert this
 * Thumbnail embedding in `mp4` is done with mutagen if possible. Use `--compat-options embed-thumbnail-atomicparsley` to force the use of AtomicParsley instead
 * Some internal metadata such as filenames are removed by default from the infojson. Use `--no-clean-infojson` or `--compat-options no-clean-infojson` to revert this
@@ -2234,9 +2246,10 @@ For ease of use, a few more compat options are available:
 * `--compat-options all`: Use all compat options (**Do NOT use this!**)
 * `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort`
 * `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext,-prefer-vp9-sort`
-* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization,no-youtube-prefer-utc-upload-date`
+* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization`
 * `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
-* `--compat-options 2023`: Same as `--compat-options prefer-vp9-sort`. Use this to enable all future compat options
+* `--compat-options 2023`: Same as `--compat-options 2024,prefer-vp9-sort`
+* `--compat-options 2024`: Currently does nothing. Use this to enable all future compat options
 
 The following compat options restore vulnerable behavior from before security patches:
 

pyproject.toml

@@ -55,8 +55,7 @@ default = [
     "websockets>=13.0",
 ]
 curl-cffi = [
-    "curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
+    "curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.11; implementation_name=='cpython'",
-    "curl-cffi>=0.5.10,!=0.6.*,<0.7.2; os_name!='nt' and implementation_name=='cpython'",
 ]
 secretstorage = [
     "cffi",

supportedsites.md

@@ -7,6 +7,7 @@ The only reliable way to check if a site is supported is to try it.
 
  - **17live**
  - **17live:clip**
+ - **17live:vod**
  - **1News**: 1news.co.nz article videos
  - **1tv**: Первый канал
  - **20min**
@@ -200,7 +201,7 @@ The only reliable way to check if a site is supported is to try it.
  - **blogger.com**
  - **Bloomberg**
  - **Bluesky**
- - **BokeCC**
+ - **BokeCC**: CC视频
  - **BongaCams**
  - **Boosty**
  - **BostonGlobe**
@@ -347,8 +348,6 @@ The only reliable way to check if a site is supported is to try it.
  - **daystar:clip**
  - **DBTV**
  - **DctpTv**
- - **DeezerAlbum**
- - **DeezerPlaylist**
  - **democracynow**
  - **DestinationAmerica**
  - **DetikEmbed**
@@ -473,6 +472,7 @@ The only reliable way to check if a site is supported is to try it.
  - **FoxNewsVideo**
  - **FoxSports**
  - **fptplay**: fptplay.vn
+ - **FrancaisFacile**
  - **FranceCulture**
  - **FranceInter**
  - **francetv**
@@ -829,7 +829,7 @@ The only reliable way to check if a site is supported is to try it.
  - **MotherlessUploader**
  - **Motorsport**: motorsport.com (**Currently broken**)
  - **MovieFap**
- - **Moviepilot**
+ - **moviepilot**: Moviepilot trailer
  - **MoviewPlay**
  - **Moviezine**
  - **MovingImage**
@@ -1252,7 +1252,6 @@ The only reliable way to check if a site is supported is to try it.
  - **rtve.es:infantil**: RTVE infantil
  - **rtve.es:live**: RTVE.es live streams
  - **rtve.es:television**
- - **RTVS**
  - **rtvslo.si**
  - **rtvslo.si:show**
  - **RudoVideo**
@@ -1307,8 +1306,8 @@ The only reliable way to check if a site is supported is to try it.
  - **sejm**
  - **Sen**
  - **SenalColombiaLive**: (**Currently broken**)
- - **SenateGov**
+ - **senate.gov**
- - **SenateISVP**
+ - **senate.gov:isvp**
  - **SendtoNews**: (**Currently broken**)
  - **Servus**
  - **Sexu**: (**Currently broken**)
@@ -1401,12 +1400,14 @@ The only reliable way to check if a site is supported is to try it.
  - **StoryFire**
  - **StoryFireSeries**
  - **StoryFireUser**
+ - **Streaks**
  - **Streamable**
  - **StreamCZ**
  - **StreetVoice**
  - **StretchInternet**
  - **Stripchat**
  - **stv:player**
+ - **stvr**: Slovak Television and Radio (formerly RTVS)
  - **Subsplash**
  - **subsplash:playlist**
  - **Substack**
@@ -1643,8 +1644,6 @@ The only reliable way to check if a site is supported is to try it.
  - **viewlift**
  - **viewlift:embed**
  - **Viidea**
- - **viki**: [*viki*](## "netrc machine")
- - **viki:channel**: [*viki*](## "netrc machine")
  - **vimeo**: [*vimeo*](## "netrc machine")
  - **vimeo:album**: [*vimeo*](## "netrc machine")
  - **vimeo:channel**: [*vimeo*](## "netrc machine")
@@ -1682,6 +1681,10 @@ The only reliable way to check if a site is supported is to try it.
  - **vpro**: npo.nl, ntr.nl, omroepwnl.nl, zapp.nl and npo3.nl
  - **vqq:series**
  - **vqq:video**
+ - **vrsquare**: VR SQUARE
+ - **vrsquare:channel**
+ - **vrsquare:search**
+ - **vrsquare:section**
  - **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
  - **vrtmax**: [*vrtnu*](## "netrc machine") VRT MAX (formerly VRT NU)
  - **VTM**: (**Currently broken**)

test/helper.py

@@ -136,7 +136,7 @@ def _iter_differences(got, expected, field):
             return
 
         if op == 'startswith':
-            if not val.startswith(got):
+            if not got.startswith(val):
                 yield field, f'should start with {val!r}, got {got!r}'
             return
 

test/test_InfoExtractor.py

@@ -638,6 +638,7 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                 'img_bipbop_adv_example_fmp4',
                 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
                 [{
+                    # 60kbps (bitrate not provided in m3u8); sorted as worst because it's grouped with lowest bitrate video track
                     'format_id': 'aud1-English',
                     'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a1/prog_index.m3u8',
                     'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
@@ -645,15 +646,9 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'ext': 'mp4',
                     'protocol': 'm3u8_native',
                     'audio_ext': 'mp4',
+                    'source_preference': 0,
                 }, {
-                    'format_id': 'aud2-English',
+                    # 192kbps (bitrate not provided in m3u8)
-                    'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a2/prog_index.m3u8',
-                    'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
-                    'language': 'en',
-                    'ext': 'mp4',
-                    'protocol': 'm3u8_native',
-                    'audio_ext': 'mp4',
-                }, {
                     'format_id': 'aud3-English',
                     'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a3/prog_index.m3u8',
                     'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
@@ -661,6 +656,17 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'ext': 'mp4',
                     'protocol': 'm3u8_native',
                     'audio_ext': 'mp4',
+                    'source_preference': 1,
+                }, {
+                    # 384kbps (bitrate not provided in m3u8); sorted as best because it's grouped with the highest bitrate video track
+                    'format_id': 'aud2-English',
+                    'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/a2/prog_index.m3u8',
+                    'manifest_url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/master.m3u8',
+                    'language': 'en',
+                    'ext': 'mp4',
+                    'protocol': 'm3u8_native',
+                    'audio_ext': 'mp4',
+                    'source_preference': 2,
                 }, {
                     'format_id': '530',
                     'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/img_bipbop_adv_example_fmp4/v2/prog_index.m3u8',

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_jsinterp.py

@@ -118,6 +118,7 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){var x = 20; x = 30 + 1; return x;}', 31)
         self._test('function f(){var x = 20; x += 30 + 1; return x;}', 51)
         self._test('function f(){var x = 20; x -= 30 + 1; return x;}', -11)
+        self._test('function f(){var x = 2; var y = ["a", "b"]; y[x%y["length"]]="z"; return y}', ['z', 'b'])
 
     @unittest.skip('Not implemented')
     def test_comments(self):
@@ -403,6 +404,8 @@ class TestJSInterpreter(unittest.TestCase):
         test_result = list('test')
         tests = [
             'function f(a, b){return a.split(b)}',
+            'function f(a, b){return a["split"](b)}',
+            'function f(a, b){let x = ["split"]; return a[x[0]](b)}',
             'function f(a, b){return String.prototype.split.call(a, b)}',
             'function f(a, b){return String.prototype.split.apply(a, [b])}',
         ]
@@ -441,6 +444,9 @@ class TestJSInterpreter(unittest.TestCase):
         self._test('function f(){return "012345678".slice(-1, 1)}', '')
         self._test('function f(){return "012345678".slice(-3, -1)}', '67')
 
+    def test_splice(self):
+        self._test('function f(){var T = ["0", "1", "2"]; T["splice"](2, 1, "0")[0]; return T }', ['0', '1', '0'])
+
     def test_js_number_to_string(self):
         for test, radix, expected in [
             (0, None, '0'),

test/test_networking.py

@@ -39,6 +39,7 @@ from yt_dlp.cookies import YoutubeDLCookieJar
 from yt_dlp.dependencies import brotli, curl_cffi, requests, urllib3
 from yt_dlp.networking import (
     HEADRequest,
+    PATCHRequest,
     PUTRequest,
     Request,
     RequestDirector,
@@ -614,7 +615,6 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
                 rh, Request(f'http://127.0.0.1:{self.http_port}/source_address')).read().decode()
             assert source_address == data
 
-    # Not supported by CurlCFFI
     @pytest.mark.skip_handler('CurlCFFI', 'not supported by curl-cffi')
     def test_gzip_trailing_garbage(self, handler):
         with handler() as rh:
@@ -1857,6 +1857,7 @@ class TestRequest:
 
     def test_request_helpers(self):
         assert HEADRequest('http://example.com').method == 'HEAD'
+        assert PATCHRequest('http://example.com').method == 'PATCH'
         assert PUTRequest('http://example.com').method == 'PUT'
 
     def test_headers(self):

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 +1,74 @@
+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 = {}
+
+    def trace(self, message: str):
+        self.messages.setdefault('trace', []).append(message)
+        pass
+
+    def debug(self, message: str):
+        self.messages.setdefault('debug', []).append(message)
+        pass
+
+    def info(self, message: str):
+        self.messages.setdefault('info', []).append(message)
+        pass
+
+    def warning(self, message: str, *, once=False):
+        self.messages.setdefault('warning', []).append(message)
+        pass
+
+    def error(self, message: str):
+        self.messages.setdefault('error', []).append(message)
+        pass
+
+
+@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 +1,46 @@
+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.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_subtitles.py

@@ -23,7 +23,6 @@ from yt_dlp.extractor import (
     TedTalkIE,
     ThePlatformFeedIE,
     ThePlatformIE,
-    VikiIE,
     VimeoIE,
     WallaIE,
     YoutubeIE,
@@ -331,20 +330,6 @@ class TestRaiPlaySubtitles(BaseTestSubtitles):
         self.assertEqual(md5(subtitles['it']), '4b3264186fbb103508abe5311cfcb9cd')
 
 
-@is_download_test
-@unittest.skip('IE broken - DRM only')
-class TestVikiSubtitles(BaseTestSubtitles):
-    url = 'http://www.viki.com/videos/1060846v-punch-episode-18'
-    IE = VikiIE
-
-    def test_allsubtitles(self):
-        self.DL.params['writesubtitles'] = True
-        self.DL.params['allsubtitles'] = True
-        subtitles = self.getSubtitles()
-        self.assertEqual(set(subtitles.keys()), {'en'})
-        self.assertEqual(md5(subtitles['en']), '53cb083a5914b2d84ef1ab67b880d18a')
-
-
 @is_download_test
 class TestThePlatformSubtitles(BaseTestSubtitles):
     # from http://www.3playmedia.com/services-features/tools/integrations/theplatform/

test/test_utils.py

@@ -659,6 +659,8 @@ class TestUtil(unittest.TestCase):
         self.assertEqual(url_or_none('mms://foo.de'), 'mms://foo.de')
         self.assertEqual(url_or_none('rtspu://foo.de'), 'rtspu://foo.de')
         self.assertEqual(url_or_none('ftps://foo.de'), 'ftps://foo.de')
+        self.assertEqual(url_or_none('ws://foo.de'), 'ws://foo.de')
+        self.assertEqual(url_or_none('wss://foo.de'), 'wss://foo.de')
 
     def test_parse_age_limit(self):
         self.assertEqual(parse_age_limit(None), None)
@@ -1260,6 +1262,7 @@ class TestUtil(unittest.TestCase):
     def test_js_to_json_malformed(self):
         self.assertEqual(js_to_json('42a1'), '42"a1"')
         self.assertEqual(js_to_json('42a-1'), '42"a"-1')
+        self.assertEqual(js_to_json('{a: `${e("")}`}'), '{"a": "\\"e\\"(\\"\\")"}')
 
     def test_js_to_json_template_literal(self):
         self.assertEqual(js_to_json('`Hello ${name}`', {'name': '"world"'}), '"Hello world"')

test/test_youtube_signature.py

@@ -83,6 +83,56 @@ _SIG_TESTS = [
         '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
         'AAOAOq0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xx8j7vgpDL0QwbdV06sCIEzpWqMGkFR20CFOS21Tp-7vj_EMu-m37KtXJoOy1',
     ),
+    (
+        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+    ),
+    (
+        'https://www.youtube.com/s/player/363db69b/player_ias_tce.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpz2ICs6EVdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias_tce.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'wAOAOq0QJ8ARAIgXmPlOPSBkkUs1bYFYlJCfe29xx8q7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player_ias_tce.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '7AOq0QJ8wRAIgXmPlOPSBkkAs1bYFYlJCfe29xx8jOv1pDL0Q2bdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJoOySqa0qaw',
+    ),
+    (
+        'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
+    ),
+    (
+        'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
+    ),
 ]
 
 _NSIG_TESTS = [
@@ -234,6 +284,38 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/643afba4/tv-player-ias.vflset/tv-player-ias.js',
         'ir9-V6cdbCiyKxhr', '2PL7ZDYAALMfmA',
     ),
+    (
+        'https://www.youtube.com/s/player/363db69b/player_ias.vflset/en_US/base.js',
+        'eWYu5d5YeY_4LyEDc', 'XJQqf-N7Xra3gg',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias.vflset/en_US/base.js',
+        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+    ),
+    (
+        'https://www.youtube.com/s/player/4fcd6e4a/player_ias_tce.vflset/en_US/base.js',
+        'o_L251jm8yhZkWtBW', 'lXoxI3XvToqn6A',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/tv-player-ias.vflset/tv-player-ias.js',
+        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player-plasma-ias-phone-en_US.vflset/base.js',
+        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+    ),
+    (
+        'https://www.youtube.com/s/player/20830619/player-plasma-ias-tablet-en_US.vflset/base.js',
+        'ir9-V6cdbCiyKxhr', '9YE85kNjZiS4',
+    ),
+    (
+        'https://www.youtube.com/s/player/8a8ac953/player_ias_tce.vflset/en_US/base.js',
+        'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
+    ),
+    (
+        'https://www.youtube.com/s/player/8a8ac953/tv-player-es6.vflset/tv-player-es6.js',
+        'MiBYeXx_vRREbiCCmh', 'RtZYMVvmkE0JE',
+    ),
 ]
 
 
@@ -284,33 +366,33 @@ def t_factory(name, sig_func, url_pattern):
         test_id = re.sub(r'[/.-]', '_', m.group('id') or m.group('compat_id'))
 
         def test_func(self):
-            basename = f'player-{name}-{test_id}.js'
+            basename = f'player-{test_id}.js'
             fn = os.path.join(self.TESTDATA_DIR, basename)
 
             if not os.path.exists(fn):
                 urllib.request.urlretrieve(url, fn)
             with open(fn, encoding='utf-8') as testf:
                 jscode = testf.read()
-            self.assertEqual(sig_func(jscode, sig_input), expected_sig)
+            self.assertEqual(sig_func(jscode, sig_input, url), expected_sig)
 
         test_func.__name__ = f'test_{name}_js_{test_id}'
         setattr(TestSignature, test_func.__name__, test_func)
     return make_tfunc
 
 
-def signature(jscode, sig_input):
+def signature(jscode, sig_input, player_url):
-    func = YoutubeIE(FakeYDL())._parse_sig_js(jscode)
+    func = YoutubeIE(FakeYDL())._parse_sig_js(jscode, player_url)
     src_sig = (
         str(string.printable[:sig_input])
         if isinstance(sig_input, int) else sig_input)
     return func(src_sig)
 
 
-def n_sig(jscode, sig_input):
+def n_sig(jscode, sig_input, player_url):
     ie = YoutubeIE(FakeYDL())
-    funcname = ie._extract_n_function_name(jscode)
+    funcname = ie._extract_n_function_name(jscode, player_url=player_url)
     jsi = JSInterpreter(jscode)
-    func = jsi.extract_function_from_code(*ie._fixup_n_function_code(*jsi.extract_function_code(funcname), jscode))
+    func = jsi.extract_function_from_code(*ie._fixup_n_function_code(*jsi.extract_function_code(funcname), jscode, player_url))
     return func([sig_input])
 
 

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
@@ -654,19 +655,21 @@ class YoutubeDL:
         if not all_plugins_loaded.value:
             load_all_plugins()
 
-        try:
-            windows_enable_vt_mode()
-        except Exception as e:
-            self.write_debug(f'Failed to enable VT mode: {e}')
-
         stdout = sys.stderr if self.params.get('logtostderr') else sys.stdout
         self._out_files = Namespace(
             out=stdout,
             error=sys.stderr,
             screen=sys.stderr if self.params.get('quiet') else stdout,
-            console=next(filter(supports_terminal_sequences, (sys.stderr, sys.stdout)), None),
         )
 
+        try:
+            windows_enable_vt_mode()
+        except Exception as e:
+            self.write_debug(f'Failed to enable VT mode: {e}')
+
+        # hehe "immutable" namespace
+        self._out_files.console = next(filter(supports_terminal_sequences, (sys.stderr, sys.stdout)), None)
+
         if self.params.get('no_color'):
             if self.params.get('color') is not None:
                 self.params.setdefault('_warnings', []).append(
@@ -906,6 +909,10 @@ 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"""
+        self._close_hooks.append(ch)
+
     def add_progress_hook(self, ph):
         """Add the download progress hook"""
         self._progress_hooks.append(ph)
@@ -1014,6 +1021,9 @@ 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.
 
@@ -4150,7 +4160,7 @@ class YoutubeDL:
             (target, rh.RH_NAME)
             for rh in self._request_director.handlers.values()
             if isinstance(rh, ImpersonateRequestHandler)
-            for target in rh.supported_targets
+            for target in reversed(rh.supported_targets)
         ]
 
     def _impersonate_target_available(self, target):

yt_dlp/__init__.py

@@ -1021,8 +1021,9 @@ def _real_main(argv=None):
                 # List of simplified targets we know are supported,
                 # to help users know what dependencies may be required.
                 (ImpersonateTarget('chrome'), 'curl_cffi'),
-                (ImpersonateTarget('edge'), 'curl_cffi'),
                 (ImpersonateTarget('safari'), 'curl_cffi'),
+                (ImpersonateTarget('firefox'), 'curl_cffi>=0.10'),
+                (ImpersonateTarget('edge'), 'curl_cffi'),
             ]
 
             available_targets = ydl._get_available_impersonate_targets()
@@ -1038,12 +1039,12 @@ def _real_main(argv=None):
 
             for known_target, known_handler in known_targets:
                 if not any(
-                    known_target in target and handler == known_handler
+                    known_target in target and known_handler.startswith(handler)
                     for target, handler in available_targets
                 ):
-                    rows.append([
+                    rows.insert(0, [
                         ydl._format_out(text, ydl.Styles.SUPPRESS)
-                        for text in make_row(known_target, f'{known_handler} (not available)')
+                        for text in make_row(known_target, f'{known_handler} (unavailable)')
                     ])
 
             ydl.to_screen('[info] Available impersonate targets')

yt_dlp/downloader/niconico.py

@@ -85,6 +85,7 @@ class NiconicoLiveFD(FileDownloader):
                             'quality': live_quality,
                             'protocol': 'hls+fmp4',
                             'latency': live_latency,
+                            'accessRightMethod': 'single_cookie',
                             'chasePlay': False,
                         },
                         'room': {

yt_dlp/extractor/_extractors.py

@@ -496,10 +496,6 @@ from .daum import (
 from .daystar import DaystarClipIE
 from .dbtv import DBTVIE
 from .dctp import DctpTvIE
-from .deezer import (
-    DeezerAlbumIE,
-    DeezerPlaylistIE,
-)
 from .democracynow import DemocracynowIE
 from .detik import DetikEmbedIE
 from .deuxm import (
@@ -687,6 +683,7 @@ from .foxnews import (
 )
 from .foxsports import FoxSportsIE
 from .fptplay import FptplayIE
+from .francaisfacile import FrancaisFacileIE
 from .franceinter import FranceInterIE
 from .francetv import (
     FranceTVIE,
@@ -843,6 +840,7 @@ from .icareus import IcareusIE
 from .ichinanalive import (
     IchinanaLiveClipIE,
     IchinanaLiveIE,
+    IchinanaLiveVODIE,
 )
 from .idolplus import IdolPlusIE
 from .ign import (
@@ -905,6 +903,7 @@ from .ivi import (
     IviIE,
 )
 from .ivideon import IvideonIE
+from .ivoox import IvooxIE
 from .iwara import (
     IwaraIE,
     IwaraPlaylistIE,
@@ -962,7 +961,10 @@ from .kick import (
 )
 from .kicker import KickerIE
 from .kickstarter import KickStarterIE
-from .kika import KikaIE
+from .kika import (
+    KikaIE,
+    KikaPlaylistIE,
+)
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
 from .kommunetv import KommunetvIE
@@ -1063,6 +1065,7 @@ from .loom import (
 from .lovehomeporn import LoveHomePornIE
 from .lrt import (
     LRTVODIE,
+    LRTRadioIE,
     LRTStreamIE,
 )
 from .lsm import (
@@ -1495,6 +1498,10 @@ from .paramountplus import (
 )
 from .parler import ParlerIE
 from .parlview import ParlviewIE
+from .parti import (
+    PartiLivestreamIE,
+    PartiVideoIE,
+)
 from .patreon import (
     PatreonCampaignIE,
     PatreonIE,
@@ -1741,6 +1748,7 @@ from .roosterteeth import (
     RoosterTeethSeriesIE,
 )
 from .rottentomatoes import RottenTomatoesIE
+from .roya import RoyaLiveIE
 from .rozhlas import (
     MujRozhlasIE,
     RozhlasIE,
@@ -1989,6 +1997,7 @@ from .storyfire import (
     StoryFireSeriesIE,
     StoryFireUserIE,
 )
+from .streaks import StreaksIE
 from .streamable import StreamableIE
 from .streamcz import StreamCZIE
 from .streetvoice import StreetVoiceIE
@@ -2352,10 +2361,6 @@ from .viewlift import (
     ViewLiftIE,
 )
 from .viidea import ViideaIE
-from .viki import (
-    VikiChannelIE,
-    VikiIE,
-)
 from .vimeo import (
     VHXEmbedIE,
     VimeoAlbumIE,
@@ -2400,6 +2405,12 @@ from .voxmedia import (
     VoxMediaIE,
     VoxMediaVolumeIE,
 )
+from .vrsquare import (
+    VrSquareChannelIE,
+    VrSquareIE,
+    VrSquareSearchIE,
+    VrSquareSectionIE,
+)
 from .vrt import (
     VRTIE,
     DagelijkseKostIE,

yt_dlp/extractor/agora.py

@@ -146,7 +146,7 @@ class TokFMPodcastIE(InfoExtractor):
         'url': 'https://audycje.tokfm.pl/podcast/91275,-Systemowy-rasizm-Czy-zamieszki-w-USA-po-morderstwie-w-Minneapolis-doprowadza-do-zmian-w-sluzbach-panstwowych',
         'info_dict': {
             'id': '91275',
-            'ext': 'aac',
+            'ext': 'mp3',
             'title': 'md5:a9b15488009065556900169fb8061cce',
             'episode': 'md5:a9b15488009065556900169fb8061cce',
             'series': 'Analizy',
@@ -164,23 +164,20 @@ class TokFMPodcastIE(InfoExtractor):
             raise ExtractorError('No such podcast', expected=True)
         metadata = metadata[0]
 
-        formats = []
+        mp3_url = self._download_json(
-        for ext in ('aac', 'mp3'):
+            'https://api.podcast.radioagora.pl/api4/getSongUrl',
-            url_data = self._download_json(
+            media_id, 'Downloading podcast mp3 URL', query={
-                f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
+                'podcast_id': media_id,
-                media_id, f'Downloading podcast {ext} URL')
+                'device_id': str(uuid.uuid4()),
-            # prevents inserting the mp3 (default) multiple times
+                'ppre': 'false',
-            if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
+                'audio': 'mp3',
-                formats.append({
+            })['link_ssl']
-                    'url': url_data['link_ssl'],
-                    'ext': ext,
-                    'vcodec': 'none',
-                    'acodec': ext,
-                })
 
         return {
             'id': media_id,
-            'formats': formats,
+            'url': mp3_url,
+            'vcodec': 'none',
+            'ext': 'mp3',
             'title': metadata.get('podcast_name'),
             'series': metadata.get('series_name'),
             'episode': metadata.get('podcast_name'),

yt_dlp/extractor/bokecc.py

@@ -24,7 +24,7 @@ class BokeCCBaseIE(InfoExtractor):
 
 
 class BokeCCIE(BokeCCBaseIE):
-    _IE_DESC = 'CC视频'
+    IE_DESC = 'CC视频'
     _VALID_URL = r'https?://union\.bokecc\.com/playvideo\.bo\?(?P<query>.*)'
 
     _TESTS = [{

yt_dlp/extractor/chzzk.py

@@ -21,7 +21,7 @@ class CHZZKLiveIE(InfoExtractor):
             'channel': '진짜도현',
             'channel_id': 'c68b8ef525fb3d2fa146344d84991753',
             'channel_is_verified': False,
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'timestamp': 1705510344,
             'upload_date': '20240117',
             'live_status': 'is_live',
@@ -98,7 +98,7 @@ class CHZZKVideoIE(InfoExtractor):
             'channel': '침착맨',
             'channel_id': 'bb382c2c0cc9fa7c86ab3b037fb5799c',
             'channel_is_verified': False,
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'duration': 15577,
             'timestamp': 1702970505.417,
             'upload_date': '20231219',
@@ -115,7 +115,7 @@ class CHZZKVideoIE(InfoExtractor):
             'channel': '라디유radiyu',
             'channel_id': '68f895c59a1043bc5019b5e08c83a5c5',
             'channel_is_verified': False,
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'duration': 95,
             'timestamp': 1703102631.722,
             'upload_date': '20231220',
@@ -131,12 +131,30 @@ class CHZZKVideoIE(InfoExtractor):
             'channel': '강지',
             'channel_id': 'b5ed5db484d04faf4d150aedd362f34b',
             'channel_is_verified': True,
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg',
             'duration': 4433,
             'timestamp': 1703307460.214,
             'upload_date': '20231223',
             'view_count': int,
         },
+    }, {
+        # video_status == 'NONE' but is downloadable
+        'url': 'https://chzzk.naver.com/video/6325166',
+        'info_dict': {
+            'id': '6325166',
+            'ext': 'mp4',
+            'title': '와이프 숙제빼주기',
+            'channel': '이 다',
+            'channel_id': '0076a519f147ee9fd0959bf02f9571ca',
+            'channel_is_verified': False,
+            'view_count': int,
+            'duration': 28167,
+            'thumbnail': r're:https?://.+/.+\.jpg',
+            'timestamp': 1742139216.86,
+            'upload_date': '20250316',
+            'live_status': 'was_live',
+        },
+        'params': {'skip_download': 'm3u8'},
     }]
 
     def _real_extract(self, url):
@@ -147,11 +165,7 @@ class CHZZKVideoIE(InfoExtractor):
 
         live_status = 'was_live' if video_meta.get('liveOpenDate') else 'not_live'
         video_status = video_meta.get('vodStatus')
-        if video_status == 'UPLOAD':
+        if video_status == 'ABR_HLS':
-            playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id)
-            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-                playback['media'][0]['path'], video_id, 'mp4', m3u8_id='hls')
-        elif video_status == 'ABR_HLS':
             formats, subtitles = self._extract_mpd_formats_and_subtitles(
                 f'https://apis.naver.com/neonplayer/vodplay/v1/playback/{video_meta["videoId"]}',
                 video_id, query={
@@ -161,10 +175,17 @@ class CHZZKVideoIE(InfoExtractor):
                     'cpl': 'en_US',
                 })
         else:
-            self.raise_no_formats(
+            fatal = video_status == 'UPLOAD'
-                f'Unknown video status detected: "{video_status}"', expected=True, video_id=video_id)
+            playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id, fatal=fatal)
-            formats, subtitles = [], {}
+            formats, subtitles = self._extract_m3u8_formats_and_subtitles(
-            live_status = 'post_live' if live_status == 'was_live' else None
+                traverse_obj(playback, ('media', 0, 'path')), video_id, 'mp4', m3u8_id='hls', fatal=fatal)
+            if formats and video_status != 'UPLOAD':
+                self.write_debug(f'Video found with status: "{video_status}"')
+            elif not formats:
+                self.raise_no_formats(
+                    f'Unknown video status detected: "{video_status}"', expected=True, video_id=video_id)
+                formats, subtitles = [], {}
+                live_status = 'post_live' if live_status == 'was_live' else None
 
         return {
             'id': video_id,

yt_dlp/extractor/common.py

@@ -78,6 +78,7 @@ from ..utils import (
     parse_iso8601,
     parse_m3u8_attributes,
     parse_resolution,
+    qualities,
     sanitize_url,
     smuggle_url,
     str_or_none,
@@ -1569,6 +1570,8 @@ class InfoExtractor:
         """Yield all json ld objects in the html"""
         if default is not NO_DEFAULT:
             fatal = False
+        if not fatal and not isinstance(html, str):
+            return
         for mobj in re.finditer(JSON_LD_RE, html):
             json_ld_item = self._parse_json(
                 mobj.group('json_ld'), video_id, fatal=fatal,
@@ -2177,6 +2180,8 @@ class InfoExtractor:
             media_url = media.get('URI')
             if media_url:
                 manifest_url = format_url(media_url)
+                is_audio = media_type == 'AUDIO'
+                is_alternate = media.get('DEFAULT') == 'NO' or media.get('AUTOSELECT') == 'NO'
                 formats.extend({
                     'format_id': join_nonempty(m3u8_id, group_id, name, idx),
                     'format_note': name,
@@ -2189,7 +2194,11 @@ class InfoExtractor:
                     'preference': preference,
                     'quality': quality,
                     'has_drm': has_drm,
-                    'vcodec': 'none' if media_type == 'AUDIO' else None,
+                    'vcodec': 'none' if is_audio else None,
+                    # Alternate audio formats (e.g. audio description) should be deprioritized
+                    'source_preference': -2 if is_audio and is_alternate else None,
+                    # Save this to assign source_preference based on associated video stream
+                    '_audio_group_id': group_id if is_audio and not is_alternate else None,
                 } for idx in _extract_m3u8_playlist_indices(manifest_url))
 
         def build_stream_name():
@@ -2284,6 +2293,8 @@ class InfoExtractor:
                     # ignore references to rendition groups and treat them
                     # as complete formats.
                     if audio_group_id and codecs and f.get('vcodec') != 'none':
+                        # Save this to determine quality of audio formats that only have a GROUP-ID
+                        f['_audio_group_id'] = audio_group_id
                         audio_group = groups.get(audio_group_id)
                         if audio_group and audio_group[0].get('URI'):
                             # TODO: update acodec for audio only formats with
@@ -2306,6 +2317,28 @@ class InfoExtractor:
                         formats.append(http_f)
 
                 last_stream_inf = {}
+
+        # Some audio-only formats only have a GROUP-ID without any other quality/bitrate/codec info
+        # Each audio GROUP-ID corresponds with one or more video formats' AUDIO attribute
+        # For sorting purposes, set source_preference based on the quality of the video formats they are grouped with
+        # See https://github.com/yt-dlp/yt-dlp/issues/11178
+        audio_groups_by_quality = orderedSet(f['_audio_group_id'] for f in sorted(
+            traverse_obj(formats, lambda _, v: v.get('vcodec') != 'none' and v['_audio_group_id']),
+            key=lambda x: (x.get('tbr') or 0, x.get('width') or 0)))
+        audio_quality_map = {
+            audio_groups_by_quality[0]: 'low',
+            audio_groups_by_quality[-1]: 'high',
+        } if len(audio_groups_by_quality) > 1 else None
+        audio_preference = qualities(audio_groups_by_quality)
+        for fmt in formats:
+            audio_group_id = fmt.pop('_audio_group_id', None)
+            if not audio_quality_map or not audio_group_id or fmt.get('vcodec') != 'none':
+                continue
+            # Use source_preference since quality and preference are set by params
+            fmt['source_preference'] = audio_preference(audio_group_id)
+            fmt['format_note'] = join_nonempty(
+                fmt.get('format_note'), audio_quality_map.get(audio_group_id), delim=', ')
+
         return formats, subtitles
 
     def _extract_m3u8_vod_duration(

yt_dlp/extractor/crowdbunker.py

@@ -5,7 +5,9 @@ from ..utils import (
     int_or_none,
     try_get,
     unified_strdate,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class CrowdBunkerIE(InfoExtractor):
@@ -44,16 +46,15 @@ class CrowdBunkerIE(InfoExtractor):
                 'url': sub_url,
             })
 
-        mpd_url = try_get(video_json, lambda x: x['dashManifest']['url'])
+        if mpd_url := traverse_obj(video_json, ('dashManifest', 'url', {url_or_none})):
-        if mpd_url:
+            fmts, subs = self._extract_mpd_formats_and_subtitles(mpd_url, video_id, mpd_id='dash', fatal=False)
-            fmts, subs = self._extract_mpd_formats_and_subtitles(mpd_url, video_id)
             formats.extend(fmts)
-            subtitles = self._merge_subtitles(subtitles, subs)
+            self._merge_subtitles(subs, target=subtitles)
-        m3u8_url = try_get(video_json, lambda x: x['hlsManifest']['url'])
+
-        if m3u8_url:
+        if m3u8_url := traverse_obj(video_json, ('hlsManifest', 'url', {url_or_none})):
-            fmts, subs = self._extract_m3u8_formats_and_subtitles(mpd_url, video_id)
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls', fatal=False)
             formats.extend(fmts)
-            subtitles = self._merge_subtitles(subtitles, subs)
+            self._merge_subtitles(subs, target=subtitles)
 
         thumbnails = [{
             'url': image['url'],

yt_dlp/extractor/deezer.py

@@ -1,142 +0,0 @@
-import json
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    orderedSet,
-)
-
-
-class DeezerBaseInfoExtractor(InfoExtractor):
-    def get_data(self, url):
-        if not self.get_param('test'):
-            self.report_warning('For now, this extractor only supports the 30 second previews. Patches welcome!')
-
-        mobj = self._match_valid_url(url)
-        data_id = mobj.group('id')
-
-        webpage = self._download_webpage(url, data_id)
-        geoblocking_msg = self._html_search_regex(
-            r'<p class="soon-txt">(.*?)</p>', webpage, 'geoblocking message',
-            default=None)
-        if geoblocking_msg is not None:
-            raise ExtractorError(
-                f'Deezer said: {geoblocking_msg}', expected=True)
-
-        data_json = self._search_regex(
-            (r'__DZR_APP_STATE__\s*=\s*({.+?})\s*</script>',
-             r'naboo\.display\(\'[^\']+\',\s*(.*?)\);\n'),
-            webpage, 'data JSON')
-        data = json.loads(data_json)
-        return data_id, webpage, data
-
-
-class DeezerPlaylistIE(DeezerBaseInfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?playlist/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'http://www.deezer.com/playlist/176747451',
-        'info_dict': {
-            'id': '176747451',
-            'title': 'Best!',
-            'uploader': 'anonymous',
-            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
-        },
-        'playlist_count': 29,
-    }
-
-    def _real_extract(self, url):
-        playlist_id, webpage, data = self.get_data(url)
-
-        playlist_title = data.get('DATA', {}).get('TITLE')
-        playlist_uploader = data.get('DATA', {}).get('PARENT_USERNAME')
-        playlist_thumbnail = self._search_regex(
-            r'<img id="naboo_playlist_image".*?src="([^"]+)"', webpage,
-            'playlist thumbnail')
-
-        entries = []
-        for s in data.get('SONGS', {}).get('data'):
-            formats = [{
-                'format_id': 'preview',
-                'url': s.get('MEDIA', [{}])[0].get('HREF'),
-                'preference': -100,  # Only the first 30 seconds
-                'ext': 'mp3',
-            }]
-            artists = ', '.join(
-                orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
-            entries.append({
-                'id': s.get('SNG_ID'),
-                'duration': int_or_none(s.get('DURATION')),
-                'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
-                'uploader': s.get('ART_NAME'),
-                'uploader_id': s.get('ART_ID'),
-                'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
-                'formats': formats,
-            })
-
-        return {
-            '_type': 'playlist',
-            'id': playlist_id,
-            'title': playlist_title,
-            'uploader': playlist_uploader,
-            'thumbnail': playlist_thumbnail,
-            'entries': entries,
-        }
-
-
-class DeezerAlbumIE(DeezerBaseInfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?deezer\.com/(../)?album/(?P<id>[0-9]+)'
-    _TEST = {
-        'url': 'https://www.deezer.com/fr/album/67505622',
-        'info_dict': {
-            'id': '67505622',
-            'title': 'Last Week',
-            'uploader': 'Home Brew',
-            'thumbnail': r're:^https?://(e-)?cdns-images\.dzcdn\.net/images/cover/.*\.jpg$',
-        },
-        'playlist_count': 7,
-    }
-
-    def _real_extract(self, url):
-        album_id, webpage, data = self.get_data(url)
-
-        album_title = data.get('DATA', {}).get('ALB_TITLE')
-        album_uploader = data.get('DATA', {}).get('ART_NAME')
-        album_thumbnail = self._search_regex(
-            r'<img id="naboo_album_image".*?src="([^"]+)"', webpage,
-            'album thumbnail')
-
-        entries = []
-        for s in data.get('SONGS', {}).get('data'):
-            formats = [{
-                'format_id': 'preview',
-                'url': s.get('MEDIA', [{}])[0].get('HREF'),
-                'preference': -100,  # Only the first 30 seconds
-                'ext': 'mp3',
-            }]
-            artists = ', '.join(
-                orderedSet(a.get('ART_NAME') for a in s.get('ARTISTS')))
-            entries.append({
-                'id': s.get('SNG_ID'),
-                'duration': int_or_none(s.get('DURATION')),
-                'title': '{} - {}'.format(artists, s.get('SNG_TITLE')),
-                'uploader': s.get('ART_NAME'),
-                'uploader_id': s.get('ART_ID'),
-                'age_limit': 16 if s.get('EXPLICIT_LYRICS') == '1' else 0,
-                'formats': formats,
-                'track': s.get('SNG_TITLE'),
-                'track_number': int_or_none(s.get('TRACK_NUMBER')),
-                'track_id': s.get('SNG_ID'),
-                'artist': album_uploader,
-                'album': album_title,
-                'album_artist': album_uploader,
-            })
-
-        return {
-            '_type': 'playlist',
-            'id': album_id,
-            'title': album_title,
-            'uploader': album_uploader,
-            'thumbnail': album_thumbnail,
-            'entries': entries,
-        }

yt_dlp/extractor/francaisfacile.py

@@ -0,0 +1,87 @@
+import urllib.parse
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    float_or_none,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class FrancaisFacileIE(InfoExtractor):
+    _VALID_URL = r'https?://francaisfacile\.rfi\.fr/[a-z]{2}/(?:actualit%C3%A9|podcasts/[^/#?]+)/(?P<id>[^/#?]+)'
+    _TESTS = [{
+        'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250305-r%C3%A9concilier-les-jeunes-avec-la-lecture-gr%C3%A2ce-aux-r%C3%A9seaux-sociaux',
+        'md5': '4f33674cb205744345cc835991100afa',
+        'info_dict': {
+            'id': 'WBMZ58952-FLE-FR-20250305',
+            'display_id': '20250305-réconcilier-les-jeunes-avec-la-lecture-grâce-aux-réseaux-sociaux',
+            'title': 'Réconcilier les jeunes avec la lecture grâce aux réseaux sociaux',
+            'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/05/6b6af52a-f9ba-11ef-a1f8-005056a97652.mp3',
+            'ext': 'mp3',
+            'description': 'md5:b903c63d8585bd59e8cc4d5f80c4272d',
+            'duration': 103.15,
+            'timestamp': 1741177984,
+            'upload_date': '20250305',
+        },
+    }, {
+        'url': 'https://francaisfacile.rfi.fr/fr/actualit%C3%A9/20250307-argentine-le-sac-d-un-alpiniste-retrouv%C3%A9-40-ans-apr%C3%A8s-sa-mort',
+        'md5': 'b8c3a63652d4ae8e8092dda5700c1cd9',
+        'info_dict': {
+            'id': 'WBMZ59102-FLE-FR-20250307',
+            'display_id': '20250307-argentine-le-sac-d-un-alpiniste-retrouvé-40-ans-après-sa-mort',
+            'title': 'Argentine: le sac d\'un alpiniste retrouvé 40 ans après sa mort',
+            'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/07/8edf4082-fb46-11ef-8a37-005056bf762b.mp3',
+            'ext': 'mp3',
+            'description': 'md5:7fd088fbdf4a943bb68cf82462160dca',
+            'duration': 117.74,
+            'timestamp': 1741352789,
+            'upload_date': '20250307',
+        },
+    }, {
+        'url': 'https://francaisfacile.rfi.fr/fr/podcasts/un-mot-une-histoire/20250317-le-mot-de-david-foenkinos-peut-%C3%AAtre',
+        'md5': 'db83c2cc2589b4c24571c6b6cf14f5f1',
+        'info_dict': {
+            'id': 'WBMZ59441-FLE-FR-20250317',
+            'display_id': '20250317-le-mot-de-david-foenkinos-peut-être',
+            'title': 'Le mot de David Foenkinos: «peut-être» - Un mot, une histoire',
+            'url': 'https://aod-fle.akamaized.net/fle/sounds/fr/2025/03/17/4ca6cbbe-0315-11f0-a85b-005056a97652.mp3',
+            'ext': 'mp3',
+            'description': 'md5:3fe35fae035803df696bfa7af2496e49',
+            'duration': 198.96,
+            'timestamp': 1742210897,
+            'upload_date': '20250317',
+        },
+    }]
+
+    def _real_extract(self, url):
+        display_id = urllib.parse.unquote(self._match_id(url))
+
+        try:  # yt-dlp's default user-agents are too old and blocked by the site
+            webpage = self._download_webpage(url, display_id, headers={
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
+            })
+        except ExtractorError as e:
+            if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
+                raise
+            # Retry with impersonation if hardcoded UA is insufficient
+            webpage = self._download_webpage(url, display_id, impersonate=True)
+
+        data = self._search_json(
+            r'<script[^>]+\bdata-media-id=[^>]+\btype="application/json"[^>]*>',
+            webpage, 'audio data', display_id)
+
+        return {
+            'id': data['mediaId'],
+            'display_id': display_id,
+            'vcodec': 'none',
+            'title': self._html_extract_title(webpage),
+            **self._search_json_ld(webpage, display_id, fatal=False),
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'url': ('sources', ..., 'url', {url_or_none}, any),
+                'duration': ('sources', ..., 'duration', {float_or_none}, any),
+            }),
+        }

yt_dlp/extractor/generic.py

@@ -16,6 +16,7 @@ from ..utils import (
     MEDIA_EXTENSIONS,
     ExtractorError,
     UnsupportedError,
+    base_url,
     determine_ext,
     determine_protocol,
     dict_get,
@@ -2213,10 +2214,21 @@ class GenericIE(InfoExtractor):
             if is_live is not None:
                 info['live_status'] = 'not_live' if is_live == 'false' else 'is_live'
                 return
-            headers = m3u8_format.get('http_headers') or info.get('http_headers')
+            headers = m3u8_format.get('http_headers') or info.get('http_headers') or {}
-            duration = self._extract_m3u8_vod_duration(
+            display_id = info.get('id')
-                m3u8_format['url'], info.get('id'), note='Checking m3u8 live status',
+            urlh = self._request_webpage(
-                errnote='Failed to download m3u8 media playlist', headers=headers)
+                m3u8_format['url'], display_id, 'Checking m3u8 live status', errnote=False,
+                headers={**headers, 'Accept-Encoding': 'identity'}, fatal=False)
+            if urlh is False:
+                return
+            first_bytes = urlh.read(512)
+            if not first_bytes.startswith(b'#EXTM3U'):
+                return
+            m3u8_doc = self._webpage_read_content(
+                urlh, urlh.url, display_id, prefix=first_bytes, fatal=False, errnote=False)
+            if not m3u8_doc:
+                return
+            duration = self._parse_m3u8_vod_duration(m3u8_doc, display_id)
             if not duration:
                 info['live_status'] = 'is_live'
             info['duration'] = info.get('duration') or duration
@@ -2531,7 +2543,7 @@ class GenericIE(InfoExtractor):
             elif re.match(r'(?i)^(?:{[^}]+})?MPD$', doc.tag):
                 info_dict['formats'], info_dict['subtitles'] = self._parse_mpd_formats_and_subtitles(
                     doc,
-                    mpd_base_url=full_response.url.rpartition('/')[0],
+                    mpd_base_url=base_url(full_response.url),
                     mpd_url=url)
                 info_dict['live_status'] = 'is_live' if doc.get('type') == 'dynamic' else None
                 self._extra_manifest_info(info_dict, url)

yt_dlp/extractor/hse.py

@@ -6,7 +6,7 @@ from ..utils import (
 )
 
 
-class HSEShowBaseInfoExtractor(InfoExtractor):
+class HSEShowBaseIE(InfoExtractor):
     _GEO_COUNTRIES = ['DE']
 
     def _extract_redux_data(self, url, video_id):
@@ -28,7 +28,7 @@ class HSEShowBaseInfoExtractor(InfoExtractor):
         return formats, subtitles
 
 
-class HSEShowIE(HSEShowBaseInfoExtractor):
+class HSEShowIE(HSEShowBaseIE):
     _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/c/tv-shows/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://www.hse.de/dpl/c/tv-shows/505350',
@@ -64,7 +64,7 @@ class HSEShowIE(HSEShowBaseInfoExtractor):
         }
 
 
-class HSEProductIE(HSEShowBaseInfoExtractor):
+class HSEProductIE(HSEShowBaseIE):
     _VALID_URL = r'https?://(?:www\.)?hse\.de/dpl/p/product/(?P<id>[0-9]+)'
     _TESTS = [{
         'url': 'https://www.hse.de/dpl/p/product/408630',

yt_dlp/extractor/ichinanalive.py

@@ -1,5 +1,13 @@
+
 from .common import InfoExtractor
-from ..utils import ExtractorError, str_or_none, traverse_obj, unified_strdate
+from ..utils import (
+    ExtractorError,
+    int_or_none,
+    str_or_none,
+    traverse_obj,
+    unified_strdate,
+    url_or_none,
+)
 
 
 class IchinanaLiveIE(InfoExtractor):
@@ -157,3 +165,51 @@ class IchinanaLiveClipIE(InfoExtractor):
             'description': view_data.get('caption'),
             'upload_date': unified_strdate(str_or_none(view_data.get('createdAt'))),
         }
+
+
+class IchinanaLiveVODIE(InfoExtractor):
+    IE_NAME = '17live:vod'
+    _VALID_URL = r'https?://(?:www\.)?17\.live/ja/vod/[^/?#]+/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://17.live/ja/vod/27323042/2cf84520-e65e-4b22-891e-1d3a00b0f068',
+        'md5': '3299b930d7457b069639486998a89580',
+        'info_dict': {
+            'id': '2cf84520-e65e-4b22-891e-1d3a00b0f068',
+            'ext': 'mp4',
+            'title': 'md5:b5f8cbf497d54cc6a60eb3b480182f01',
+            'uploader': 'md5:29fb12122ab94b5a8495586e7c3085a5',
+            'uploader_id': '27323042',
+            'channel': '🌟オールナイトニッポン アーカイブ🌟',
+            'channel_id': '2b4f85f1-d61e-429d-a901-68d32bdd8645',
+            'like_count': int,
+            'view_count': int,
+            'thumbnail': r're:https?://.+/.+\.(?:jpe?g|png)',
+            'duration': 549,
+            'description': 'md5:116f326579700f00eaaf5581aae1192e',
+            'timestamp': 1741058645,
+            'upload_date': '20250304',
+        },
+    }, {
+        'url': 'https://17.live/ja/vod/27323042/0de11bac-9bea-40b8-9eab-0239a7d88079',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        json_data = self._download_json(f'https://wap-api.17app.co/api/v1/vods/{video_id}', video_id)
+
+        return traverse_obj(json_data, {
+            'id': ('vodID', {str}),
+            'title': ('title', {str}),
+            'formats': ('vodURL', {lambda x: self._extract_m3u8_formats(x, video_id)}),
+            'uploader': ('userInfo', 'displayName', {str}),
+            'uploader_id': ('userInfo', 'roomID', {int}, {str_or_none}),
+            'channel': ('userInfo', 'name', {str}),
+            'channel_id': ('userInfo', 'userID', {str}),
+            'like_count': ('likeCount', {int_or_none}),
+            'view_count': ('viewCount', {int_or_none}),
+            'thumbnail': ('imageURL', {url_or_none}),
+            'duration': ('duration', {int_or_none}),
+            'description': ('description', {str}),
+            'timestamp': ('createdAt', {int_or_none}),
+        })

yt_dlp/extractor/ivoox.py

@@ -0,0 +1,78 @@
+from .common import InfoExtractor
+from ..utils import int_or_none, parse_iso8601, url_or_none, urljoin
+from ..utils.traversal import traverse_obj
+
+
+class IvooxIE(InfoExtractor):
+    _VALID_URL = (
+        r'https?://(?:www\.)?ivoox\.com/(?:\w{2}/)?[^/?#]+_rf_(?P<id>[0-9]+)_1\.html',
+        r'https?://go\.ivoox\.com/rf/(?P<id>[0-9]+)',
+    )
+    _TESTS = [{
+        'url': 'https://www.ivoox.com/dex-08x30-rostros-del-mal-los-asesinos-en-audios-mp3_rf_143594959_1.html',
+        'md5': '993f712de5b7d552459fc66aa3726885',
+        'info_dict': {
+            'id': '143594959',
+            'ext': 'mp3',
+            'timestamp': 1742731200,
+            'channel': 'DIAS EXTRAÑOS con Santiago Camacho',
+            'title': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+            'description': 'md5:eae8b4b9740d0216d3871390b056bb08',
+            'uploader': 'Santiago Camacho',
+            'thumbnail': 'https://static-1.ivoox.com/audios/c/d/5/2/cd52f46783fe735000c33a803dce2554_XXL.jpg',
+            'upload_date': '20250323',
+            'episode': 'DEx 08x30 Rostros del mal: Los asesinos en serie que aterrorizaron España',
+            'duration': 11837,
+            'tags': ['españa', 'asesinos en serie', 'arropiero', 'historia criminal', 'mataviejas'],
+        },
+    }, {
+        'url': 'https://go.ivoox.com/rf/143594959',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.ivoox.com/en/campodelgas-28-03-2025-audios-mp3_rf_144036942_1.html',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+        webpage = self._download_webpage(url, media_id, fatal=False)
+
+        data = self._search_nuxt_data(
+            webpage, media_id, fatal=False, traverse=('data', 0, 'data', 'audio'))
+
+        direct_download = self._download_json(
+            f'https://vcore-web.ivoox.com/v1/public/audios/{media_id}/download-url', media_id, fatal=False,
+            note='Fetching direct download link', headers={'Referer': url})
+
+        download_paths = {
+            *traverse_obj(direct_download, ('data', 'downloadUrl', {str}, filter, all)),
+            *traverse_obj(data, (('downloadUrl', 'mediaUrl'), {str}, filter)),
+        }
+
+        formats = []
+        for path in download_paths:
+            formats.append({
+                'url': urljoin('https://ivoox.com', path),
+                'http_headers': {'Referer': url},
+            })
+
+        return {
+            'id': media_id,
+            'formats': formats,
+            'uploader': self._html_search_regex(r'data-prm-author="([^"]+)"', webpage, 'author', default=None),
+            'timestamp': parse_iso8601(
+                self._html_search_regex(r'data-prm-pubdate="([^"]+)"', webpage, 'timestamp', default=None)),
+            'channel': self._html_search_regex(r'data-prm-podname="([^"]+)"', webpage, 'channel', default=None),
+            'title': self._html_search_regex(r'data-prm-title="([^"]+)"', webpage, 'title', default=None),
+            'thumbnail': self._og_search_thumbnail(webpage, default=None),
+            'description': self._og_search_description(webpage, default=None),
+            **self._search_json_ld(webpage, media_id, default={}),
+            **traverse_obj(data, {
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('image', {url_or_none}),
+                'timestamp': ('uploadDate', {parse_iso8601(delimiter=' ')}),
+                'duration': ('duration', {int_or_none}),
+                'tags': ('tags', ..., 'name', {str}),
+            }),
+        }

yt_dlp/extractor/kika.py

@@ -1,3 +1,5 @@
+import itertools
+
 from .common import InfoExtractor
 from ..utils import (
     determine_ext,
@@ -124,3 +126,43 @@ class KikaIE(InfoExtractor):
                         'vbr': ('bitrateVideo', {int_or_none}, {lambda x: None if x == -1 else x}),
                     }),
                 }
+
+
+class KikaPlaylistIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?kika\.de/[\w-]+/(?P<id>[a-z-]+\d+)'
+
+    _TESTS = [{
+        'url': 'https://www.kika.de/logo/logo-die-welt-und-ich-562',
+        'info_dict': {
+            'id': 'logo-die-welt-und-ich-562',
+            'title': 'logo!',
+            'description': 'md5:7b9d7f65561b82fa512f2cfb553c397d',
+        },
+        'playlist_count': 100,
+    }]
+
+    def _entries(self, playlist_url, playlist_id):
+        for page in itertools.count(1):
+            data = self._download_json(playlist_url, playlist_id, note=f'Downloading page {page}')
+            for item in traverse_obj(data, ('content', lambda _, v: url_or_none(v['api']['url']))):
+                yield self.url_result(
+                    item['api']['url'], ie=KikaIE,
+                    **traverse_obj(item, {
+                        'id': ('id', {str}),
+                        'title': ('title', {str}),
+                        'duration': ('duration', {int_or_none}),
+                        'timestamp': ('date', {parse_iso8601}),
+                    }))
+
+            playlist_url = traverse_obj(data, ('links', 'next', {url_or_none}))
+            if not playlist_url:
+                break
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        brand_data = self._download_json(
+            f'https://www.kika.de/_next-api/proxy/v1/brands/{playlist_id}', playlist_id)
+
+        return self.playlist_result(
+            self._entries(brand_data['videoSubchannel']['videosPageUrl'], playlist_id),
+            playlist_id, title=brand_data.get('title'), description=brand_data.get('description'))

yt_dlp/extractor/lrt.py

@@ -2,8 +2,11 @@ from .common import InfoExtractor
 from ..utils import (
     clean_html,
     merge_dicts,
+    str_or_none,
     traverse_obj,
+    unified_timestamp,
     url_or_none,
+    urljoin,
 )
 
 
@@ -80,7 +83,7 @@ class LRTVODIE(LRTBaseIE):
     }]
 
     def _real_extract(self, url):
-        path, video_id = self._match_valid_url(url).groups()
+        path, video_id = self._match_valid_url(url).group('path', 'id')
         webpage = self._download_webpage(url, video_id)
 
         media_url = self._extract_js_var(webpage, 'main_url', path)
@@ -106,3 +109,42 @@ class LRTVODIE(LRTBaseIE):
         }
 
         return merge_dicts(clean_info, jw_data, json_ld_data)
+
+
+class LRTRadioIE(LRTBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?lrt\.lt/radioteka/irasas/(?P<id>\d+)/(?P<path>[^?#/]+)'
+    _TESTS = [{
+        # m3u8 download
+        'url': 'https://www.lrt.lt/radioteka/irasas/2000359728/nemarios-eiles-apie-pragarus-ir-skaistyklas-su-aiste-kiltinaviciute',
+        'info_dict': {
+            'id': '2000359728',
+            'ext': 'm4a',
+            'title': 'Nemarios eilės: apie pragarus ir skaistyklas su Aiste Kiltinavičiūte',
+            'description': 'md5:5eee9a0e86a55bf547bd67596204625d',
+            'timestamp': 1726143120,
+            'upload_date': '20240912',
+            'tags': 'count:5',
+            'thumbnail': r're:https?://.+/.+\.jpe?g',
+            'categories': ['Daiktiniai įrodymai'],
+        },
+    }, {
+        'url': 'https://www.lrt.lt/radioteka/irasas/2000304654/vakaras-su-knyga-svetlana-aleksijevic-cernobylio-malda-v-dalis?season=%2Fmediateka%2Faudio%2Fvakaras-su-knyga%2F2023',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id, path = self._match_valid_url(url).group('id', 'path')
+        media = self._download_json(
+            '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)}),
+        })

yt_dlp/extractor/microsoftembed.py

@@ -4,6 +4,7 @@ from .common import InfoExtractor
 from ..utils import (
     int_or_none,
     parse_iso8601,
+    parse_resolution,
     traverse_obj,
     unified_timestamp,
     url_basename,
@@ -83,8 +84,8 @@ class MicrosoftMediusBaseIE(InfoExtractor):
             subtitles.setdefault(sub.pop('tag', 'und'), []).append(sub)
         return subtitles
 
-    def _extract_ism(self, ism_url, video_id):
+    def _extract_ism(self, ism_url, video_id, fatal=True):
-        formats = self._extract_ism_formats(ism_url, video_id)
+        formats = self._extract_ism_formats(ism_url, video_id, fatal=fatal)
         for fmt in formats:
             if fmt['language'] != 'eng' and 'English' not in fmt['format_id']:
                 fmt['language_preference'] = -10
@@ -218,9 +219,21 @@ class MicrosoftLearnEpisodeIE(MicrosoftMediusBaseIE):
             'description': 'md5:7bbbfb593d21c2cf2babc3715ade6b88',
             'timestamp': 1676339547,
             'upload_date': '20230214',
-            'thumbnail': r're:https://learn\.microsoft\.com/video/media/.*\.png',
+            'thumbnail': r're:https://learn\.microsoft\.com/video/media/.+\.png',
             'subtitles': 'count:14',
         },
+    }, {
+        'url': 'https://learn.microsoft.com/en-gb/shows/on-demand-instructor-led-training-series/az-900-module-1',
+        'info_dict': {
+            'id': '4fe10f7c-d83c-463b-ac0e-c30a8195e01b',
+            'ext': 'mp4',
+            'title': 'AZ-900 Cloud fundamentals (1 of 6)',
+            'description': 'md5:3c2212ce865e9142f402c766441bd5c9',
+            'thumbnail': r're:https://.+/.+\.jpg',
+            'timestamp': 1706605184,
+            'upload_date': '20240130',
+        },
+        'params': {'format': 'bv[protocol=https]'},
     }]
 
     def _real_extract(self, url):
@@ -230,9 +243,32 @@ class MicrosoftLearnEpisodeIE(MicrosoftMediusBaseIE):
         entry_id = self._html_search_meta('entryId', webpage, 'entryId', fatal=True)
         video_info = self._download_json(
             f'https://learn.microsoft.com/api/video/public/v1/entries/{entry_id}', video_id)
+
+        formats = []
+        if ism_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoUrl', {url_or_none})):
+            formats.extend(self._extract_ism(ism_url, video_id, fatal=False))
+        if hls_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoHLSUrl', {url_or_none})):
+            formats.extend(self._extract_m3u8_formats(hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False))
+        if mpd_url := traverse_obj(video_info, ('publicVideo', 'adaptiveVideoDashUrl', {url_or_none})):
+            formats.extend(self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash', fatal=False))
+        for key in ('low', 'medium', 'high'):
+            if video_url := traverse_obj(video_info, ('publicVideo', f'{key}QualityVideoUrl', {url_or_none})):
+                formats.append({
+                    'url': video_url,
+                    'format_id': f'video-http-{key}',
+                    'acodec': 'none',
+                    **parse_resolution(video_url),
+                })
+        if audio_url := traverse_obj(video_info, ('publicVideo', 'audioUrl', {url_or_none})):
+            formats.append({
+                'url': audio_url,
+                'format_id': 'audio-http',
+                'vcodec': 'none',
+            })
+
         return {
             'id': entry_id,
-            'formats': self._extract_ism(video_info['publicVideo']['adaptiveVideoUrl'], video_id),
+            'formats': formats,
             'subtitles': self._sub_to_dict(traverse_obj(video_info, (
                 'publicVideo', 'captions', lambda _, v: url_or_none(v['url']), {
                     'tag': ('language', {str}),

yt_dlp/extractor/mixcloud.py

@@ -10,7 +10,9 @@ from ..utils import (
     parse_iso8601,
     strip_or_none,
     try_get,
+    url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class MixcloudBaseIE(InfoExtractor):
@@ -37,7 +39,7 @@ class MixcloudIE(MixcloudBaseIE):
             'ext': 'm4a',
             'title': 'Cryptkeeper',
             'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
-            'uploader': 'Daniel Holbach',
+            'uploader': 'dholbach',
             'uploader_id': 'dholbach',
             'thumbnail': r're:https?://.*\.jpg',
             'view_count': int,
@@ -46,10 +48,11 @@ class MixcloudIE(MixcloudBaseIE):
             'uploader_url': 'https://www.mixcloud.com/dholbach/',
             'artist': 'Submorphics & Chino , Telekinesis, Porter Robinson, Enei, Breakage ft Jess Mills',
             'duration': 3723,
-            'tags': [],
+            'tags': ['liquid drum and bass', 'drum and bass'],
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
+            'artists': list,
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -67,7 +70,7 @@ class MixcloudIE(MixcloudBaseIE):
             'upload_date': '20150203',
             'uploader_url': 'https://www.mixcloud.com/gillespeterson/',
             'duration': 2992,
-            'tags': [],
+            'tags': ['jazz', 'soul', 'world music', 'funk'],
             'comment_count': int,
             'repost_count': int,
             'like_count': int,
@@ -149,8 +152,6 @@ class MixcloudIE(MixcloudBaseIE):
         elif reason:
             raise ExtractorError('Track is restricted', expected=True)
 
-        title = cloudcast['name']
-
         stream_info = cloudcast['streamInfo']
         formats = []
 
@@ -182,47 +183,39 @@ class MixcloudIE(MixcloudBaseIE):
             self.raise_login_required(metadata_available=True)
 
         comments = []
-        for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []):
+        for node in traverse_obj(cloudcast, ('comments', 'edges', ..., 'node', {dict})):
-            node = edge.get('node') or {}
             text = strip_or_none(node.get('comment'))
             if not text:
                 continue
-            user = node.get('user') or {}
             comments.append({
-                'author': user.get('displayName'),
-                'author_id': user.get('username'),
                 'text': text,
-                'timestamp': parse_iso8601(node.get('created')),
+                **traverse_obj(node, {
+                    'author': ('user', 'displayName', {str}),
+                    'author_id': ('user', 'username', {str}),
+                    'timestamp': ('created', {parse_iso8601}),
+                }),
             })
 
-        tags = []
-        for t in cloudcast.get('tags'):
-            tag = try_get(t, lambda x: x['tag']['name'], str)
-            if not tag:
-                tags.append(tag)
-
-        get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount']))
-
-        owner = cloudcast.get('owner') or {}
-
         return {
             'id': track_id,
-            'title': title,
             'formats': formats,
-            'description': cloudcast.get('description'),
-            'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], str),
-            'uploader': owner.get('displayName'),
-            'timestamp': parse_iso8601(cloudcast.get('publishDate')),
-            'uploader_id': owner.get('username'),
-            'uploader_url': owner.get('url'),
-            'duration': int_or_none(cloudcast.get('audioLength')),
-            'view_count': int_or_none(cloudcast.get('plays')),
-            'like_count': get_count('favorites'),
-            'repost_count': get_count('reposts'),
-            'comment_count': get_count('comments'),
             'comments': comments,
-            'tags': tags,
+            **traverse_obj(cloudcast, {
-            'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None,
+                'title': ('name', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('picture', 'url', {url_or_none}),
+                'timestamp': ('publishDate', {parse_iso8601}),
+                'duration': ('audioLength', {int_or_none}),
+                'uploader': ('owner', 'displayName', {str}),
+                'uploader_id': ('owner', 'username', {str}),
+                'uploader_url': ('owner', 'url', {url_or_none}),
+                'view_count': ('plays', {int_or_none}),
+                'like_count': ('favorites', 'totalCount', {int_or_none}),
+                'repost_count': ('reposts', 'totalCount', {int_or_none}),
+                'comment_count': ('comments', 'totalCount', {int_or_none}),
+                'tags': ('tags', ..., 'tag', 'name', {str}, filter, all, filter),
+                'artists': ('featuringArtistList', ..., {str}, filter, all, filter),
+            }),
         }
 
 
@@ -295,7 +288,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'url': 'http://www.mixcloud.com/dholbach/',
         'info_dict': {
             'id': 'dholbach_uploads',
-            'title': 'Daniel Holbach (uploads)',
+            'title': 'dholbach (uploads)',
             'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
         },
         'playlist_mincount': 36,
@@ -303,7 +296,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'url': 'http://www.mixcloud.com/dholbach/uploads/',
         'info_dict': {
             'id': 'dholbach_uploads',
-            'title': 'Daniel Holbach (uploads)',
+            'title': 'dholbach (uploads)',
             'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
         },
         'playlist_mincount': 36,
@@ -311,7 +304,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
         'url': 'http://www.mixcloud.com/dholbach/favorites/',
         'info_dict': {
             'id': 'dholbach_favorites',
-            'title': 'Daniel Holbach (favorites)',
+            'title': 'dholbach (favorites)',
             'description': 'md5:a3f468a60ac8c3e1f8616380fc469b2b',
         },
         # 'params': {
@@ -337,7 +330,7 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
             'title': 'First Ear (stream)',
             'description': 'we maraud for ears',
         },
-        'playlist_mincount': 269,
+        'playlist_mincount': 267,
     }]
 
     _TITLE_KEY = 'displayName'
@@ -361,7 +354,7 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
             'id': 'maxvibes_jazzcat-on-ness-radio',
             'title': 'Ness Radio sessions',
         },
-        'playlist_mincount': 59,
+        'playlist_mincount': 58,
     }]
     _TITLE_KEY = 'name'
     _DESCRIPTION_KEY = 'description'

yt_dlp/extractor/mlb.py

@@ -449,9 +449,7 @@ mutation initPlaybackSession(
 
         if not (m3u8_url and token):
             errors = '; '.join(traverse_obj(response, ('errors', ..., 'message', {str})))
-            if 'not entitled' in errors:
+            if errors:  # Only warn when 'blacked out' or 'not entitled'; radio formats may be available
-                raise ExtractorError(errors, expected=True)
-            elif errors:  # Only warn when 'blacked out' since radio formats are available
                 self.report_warning(f'API returned errors for {format_id}: {errors}')
             else:
                 self.report_warning(f'No formats available for {format_id} broadcast; skipping')

yt_dlp/extractor/moviepilot.py

@@ -3,8 +3,8 @@ from .dailymotion import DailymotionIE
 
 
 class MoviepilotIE(InfoExtractor):
-    _IE_NAME = 'moviepilot'
+    IE_NAME = 'moviepilot'
-    _IE_DESC = 'Moviepilot trailer'
+    IE_DESC = 'Moviepilot trailer'
     _VALID_URL = r'https?://(?:www\.)?moviepilot\.de/movies/(?P<id>[^/]+)'
 
     _TESTS = [{

yt_dlp/extractor/niconico.py

@@ -27,6 +27,7 @@ from ..utils import (
     traverse_obj,
     try_get,
     unescapeHTML,
+    unified_timestamp,
     update_url_query,
     url_basename,
     url_or_none,
@@ -985,6 +986,7 @@ class NiconicoLiveIE(InfoExtractor):
                     'quality': 'abr',
                     'protocol': 'hls+fmp4',
                     'latency': latency,
+                    'accessRightMethod': 'single_cookie',
                     'chasePlay': False,
                 },
                 'room': {
@@ -1005,6 +1007,7 @@ class NiconicoLiveIE(InfoExtractor):
             if data.get('type') == 'stream':
                 m3u8_url = data['data']['uri']
                 qualities = data['data']['availableQualities']
+                cookies = data['data']['cookies']
                 break
             elif data.get('type') == 'disconnect':
                 self.write_debug(recv)
@@ -1043,6 +1046,11 @@ class NiconicoLiveIE(InfoExtractor):
                     **res,
                 })
 
+        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'])
+
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
         for fmt, q in zip(formats, reversed(qualities[1:])):
             fmt.update({

yt_dlp/extractor/ninenow.py

@@ -1,34 +1,46 @@
+import json
+import re
+
+from .brightcove import BrightcoveNewIE
 from .common import InfoExtractor
 from ..utils import (
-    ExtractorError,
     float_or_none,
     int_or_none,
-    smuggle_url,
+    parse_iso8601,
+    parse_resolution,
     str_or_none,
-    try_get,
+    url_or_none,
-    unified_strdate,
-    unified_timestamp,
 )
+from ..utils.traversal import require, traverse_obj, value
 
 
 class NineNowIE(InfoExtractor):
     IE_NAME = '9now.com.au'
-    _VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/]+/){2}(?P<id>[^/?#]+)'
+    _VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/?#]+/){2}(?P<id>(?P<type>clip|episode)-[^/?#]+)'
-    _GEO_COUNTRIES = ['AU']
+    _GEO_BYPASS = False
     _TESTS = [{
         # clip
-        'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
+        'url': 'https://www.9now.com.au/today/season-2025/clip-cm8hw9h5z00080hquqa5hszq7',
-        'md5': '17cf47d63ec9323e562c9957a968b565',
         'info_dict': {
-            'id': '16801',
+            'id': '6370295582112',
             'ext': 'mp4',
-            'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
+            'title': 'Would Karl Stefanovic be able to land a plane?',
-            'description': 'Is a boycott of the NAB Cup "on the table"?',
+            'description': 'The Today host\'s skills are put to the test with the latest simulation tech.',
             'uploader_id': '4460760524001',
-            'upload_date': '20160713',
+            'duration': 197.376,
-            'timestamp': 1468421266,
+            'tags': ['flights', 'technology', 'Karl Stefanovic'],
+            'season': 'Season 2025',
+            'season_number': 2025,
+            'series': 'TODAY',
+            'timestamp': 1742507988,
+            'upload_date': '20250320',
+            'release_timestamp': 1742507983,
+            'release_date': '20250320',
+            'thumbnail': r're:https?://.+/1920x0/.+\.jpg',
+        },
+        'params': {
+            'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
         },
-        'skip': 'Only available in Australia',
     }, {
         # episode
         'url': 'https://www.9now.com.au/afl-footy-show/2016/episode-19',
@@ -41,7 +53,7 @@ class NineNowIE(InfoExtractor):
         # episode of series
         'url': 'https://www.9now.com.au/lego-masters/season-3/episode-3',
         'info_dict': {
-            'id': '6249614030001',
+            'id': '6308830406112',
             'title': 'Episode 3',
             'ext': 'mp4',
             'season_number': 3,
@@ -50,72 +62,87 @@ class NineNowIE(InfoExtractor):
             'uploader_id': '4460760524001',
             'timestamp': 1619002200,
             'upload_date': '20210421',
+            'duration': 3574.085,
+            'thumbnail': r're:https?://.+/1920x0/.+\.jpg',
+            'tags': ['episode'],
+            'series': 'Lego Masters',
+            'season': 'Season 3',
+            'episode': 'Episode 3',
+            'release_timestamp': 1619002200,
+            'release_date': '20210421',
         },
-        'expected_warnings': ['Ignoring subtitle tracks'],
         'params': {
-            'skip_download': True,
+            'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
+        },
+    }, {
+        'url': 'https://www.9now.com.au/married-at-first-sight/season-12/episode-1',
+        'info_dict': {
+            'id': '6367798770112',
+            'ext': 'mp4',
+            'title': 'Episode 1',
+            'description': r're:The cultural sensation of Married At First Sight returns with our first weddings! .{90}$',
+            'uploader_id': '4460760524001',
+            'duration': 5415.079,
+            'thumbnail': r're:https?://.+/1920x0/.+\.png',
+            'tags': ['episode'],
+            'season': 'Season 12',
+            'season_number': 12,
+            'episode': 'Episode 1',
+            'episode_number': 1,
+            'series': 'Married at First Sight',
+            'timestamp': 1737973800,
+            'upload_date': '20250127',
+            'release_timestamp': 1737973800,
+            'release_date': '20250127',
+        },
+        'params': {
+            'skip_download': 'HLS/DASH fragments and mp4 URLs are geo-restricted; only available in AU',
         },
     }]
-    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId=%s'
+    BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/4460760524001/default_default/index.html?videoId={}'
+
+    # XXX: For parsing next.js v15+ data; see also yt_dlp.extractor.francetv and yt_dlp.extractor.goplay
+    def _find_json(self, s):
+        return self._search_json(
+            r'\w+\s*:\s*', s, 'next js data', None, contains_pattern=r'\[(?s:.+)\]', default=None)
 
     def _real_extract(self, url):
-        display_id = self._match_id(url)
+        display_id, video_type = self._match_valid_url(url).group('id', 'type')
         webpage = self._download_webpage(url, display_id)
-        page_data = self._parse_json(self._search_regex(
-            r'window\.__data\s*=\s*({.*?});', webpage,
-            'page data', default='{}'), display_id, fatal=False)
-        if not page_data:
-            page_data = self._parse_json(self._parse_json(self._search_regex(
-                r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
-                webpage, 'page data'), display_id), display_id)
 
-        for kind in ('episode', 'clip'):
+        common_data = traverse_obj(
-            current_key = page_data.get(kind, {}).get(
+            re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
-                f'current{kind.capitalize()}Key')
+            (..., {json.loads}, ..., {self._find_json},
-            if not current_key:
+             lambda _, v: v['payload'][video_type]['slug'] == display_id,
-                continue
+             'payload', any, {require('video data')}))
-            cache = page_data.get(kind, {}).get(f'{kind}Cache', {})
-            if not cache:
-                continue
-            common_data = {
-                'episode': (cache.get(current_key) or next(iter(cache.values())))[kind],
-                'season': (cache.get(current_key) or next(iter(cache.values()))).get('season', None),
-            }
-            break
-        else:
-            raise ExtractorError('Unable to find video data')
 
-        if not self.get_param('allow_unplayable_formats') and try_get(common_data, lambda x: x['episode']['video']['drm'], bool):
+        if traverse_obj(common_data, (video_type, 'video', 'drm', {bool})):
             self.report_drm(display_id)
-        brightcove_id = try_get(
+        brightcove_id = traverse_obj(common_data, (
-            common_data, lambda x: x['episode']['video']['brightcoveId'], str) or 'ref:{}'.format(common_data['episode']['video']['referenceId'])
+            video_type, 'video', (
-        video_id = str_or_none(try_get(common_data, lambda x: x['episode']['video']['id'])) or brightcove_id
+                ('brightcoveId', {str}),
-
+                ('referenceId', {str}, {lambda x: f'ref:{x}' if x else None}),
-        title = try_get(common_data, lambda x: x['episode']['name'], str)
+            ), any, {require('brightcove ID')}))
-        season_number = try_get(common_data, lambda x: x['season']['seasonNumber'], int)
-        episode_number = try_get(common_data, lambda x: x['episode']['episodeNumber'], int)
-        timestamp = unified_timestamp(try_get(common_data, lambda x: x['episode']['airDate'], str))
-        release_date = unified_strdate(try_get(common_data, lambda x: x['episode']['availability'], str))
-        thumbnails_data = try_get(common_data, lambda x: x['episode']['image']['sizes'], dict) or {}
-        thumbnails = [{
-            'id': thumbnail_id,
-            'url': thumbnail_url,
-            'width': int_or_none(thumbnail_id[1:]),
-        } for thumbnail_id, thumbnail_url in thumbnails_data.items()]
 
         return {
             '_type': 'url_transparent',
-            'url': smuggle_url(
+            'ie_key': BrightcoveNewIE.ie_key(),
-                self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+            'url': self.BRIGHTCOVE_URL_TEMPLATE.format(brightcove_id),
-                {'geo_countries': self._GEO_COUNTRIES}),
+            **traverse_obj(common_data, {
-            'id': video_id,
+                'id': (video_type, 'video', 'id', {int}, ({str_or_none}, {value(brightcove_id)}), any),
-            'title': title,
+                'title': (video_type, 'name', {str}),
-            'description': try_get(common_data, lambda x: x['episode']['description'], str),
+                'description': (video_type, 'description', {str}),
-            'duration': float_or_none(try_get(common_data, lambda x: x['episode']['video']['duration'], float), 1000),
+                'duration': (video_type, 'video', 'duration', {float_or_none(scale=1000)}),
-            'thumbnails': thumbnails,
+                'tags': (video_type, 'tags', ..., 'name', {str}, all, filter),
-            'ie_key': 'BrightcoveNew',
+                'series': ('tvSeries', 'name', {str}),
-            'season_number': season_number,
+                'season_number': ('season', 'seasonNumber', {int_or_none}),
-            'episode_number': episode_number,
+                'episode_number': ('episode', 'episodeNumber', {int_or_none}),
-            'timestamp': timestamp,
+                'timestamp': ('episode', 'airDate', {parse_iso8601}),
-            'release_date': release_date,
+                'release_timestamp': (video_type, 'availability', {parse_iso8601}),
+                'thumbnails': (video_type, 'image', 'sizes', {dict.items}, lambda _, v: url_or_none(v[1]), {
+                    'id': 0,
+                    'url': 1,
+                    'width': (1, {parse_resolution}, 'width'),
+                }),
+            }),
         }

yt_dlp/extractor/on24.py

@@ -11,12 +11,15 @@ class On24IE(InfoExtractor):
     IE_NAME = 'on24'
     IE_DESC = 'ON24'
 
-    _VALID_URL = r'''(?x)
+    _ID_RE = r'(?P<id>\d{7})'
-                    https?://event\.on24\.com/(?:
+    _KEY_RE = r'(?P<key>[0-9A-F]{32})'
-                        wcc/r/(?P<id_1>\d{7})/(?P<key_1>[0-9A-F]{32})|
+    _URL_BASE_RE = r'https?://event\.on24\.com'
-                        eventRegistration/(?:console/EventConsoleApollo|EventLobbyServlet\?target=lobby30)
+    _URL_QUERY_RE = rf'(?:[^#]*&)?eventid={_ID_RE}&(?:[^#]+&)?key={_KEY_RE}'
-                            \.jsp\?(?:[^/#?]*&)?eventid=(?P<id_2>\d{7})[^/#?]*&key=(?P<key_2>[0-9A-F]{32})
+    _VALID_URL = [
-                    )'''
+        rf'{_URL_BASE_RE}/wcc/r/{_ID_RE}/{_KEY_RE}',
+        rf'{_URL_BASE_RE}/eventRegistration/console/(?:EventConsoleApollo\.jsp|apollox/mainEvent/?)\?{_URL_QUERY_RE}',
+        rf'{_URL_BASE_RE}/eventRegistration/EventLobbyServlet/?\?{_URL_QUERY_RE}',
+    ]
 
     _TESTS = [{
         'url': 'https://event.on24.com/eventRegistration/console/EventConsoleApollo.jsp?uimode=nextgeneration&eventid=2197467&sessionid=1&key=5DF57BE53237F36A43B478DD36277A84&contenttype=A&eventuserid=305999&playerwidth=1000&playerheight=650&caller=previewLobby&text_language_id=en&format=fhaudio&newConsole=false',
@@ -34,12 +37,16 @@ class On24IE(InfoExtractor):
     }, {
         'url': 'https://event.on24.com/eventRegistration/console/EventConsoleApollo.jsp?&eventid=2639291&sessionid=1&username=&partnerref=&format=fhvideo1&mobile=&flashsupportedmobiledevice=&helpcenter=&key=82829018E813065A122363877975752E&newConsole=true&nxChe=true&newTabCon=true&text_language_id=en&playerwidth=748&playerheight=526&eventuserid=338788762&contenttype=A&mediametricsessionid=384764716&mediametricid=3558192&usercd=369267058&mode=launch',
         'only_matching': True,
+    }, {
+        'url': 'https://event.on24.com/eventRegistration/EventLobbyServlet?target=reg20.jsp&eventid=3543176&key=BC0F6B968B67C34B50D461D40FDB3E18&groupId=3143628',
+        'only_matching': True,
+    }, {
+        'url': 'https://event.on24.com/eventRegistration/console/apollox/mainEvent?&eventid=4843671&sessionid=1&username=&partnerref=&format=fhvideo1&mobile=&flashsupportedmobiledevice=&helpcenter=&key=4EAC9B5C564CC98FF29E619B06A2F743&newConsole=true&nxChe=true&newTabCon=true&consoleEarEventConsole=false&consoleEarCloudApi=false&text_language_id=en&playerwidth=748&playerheight=526&referrer=https%3A%2F%2Fevent.on24.com%2Finterface%2Fregistration%2Fautoreg%2Findex.html%3Fsessionid%3D1%26eventid%3D4843671%26key%3D4EAC9B5C564CC98FF29E619B06A2F743%26email%3D000a3e42-7952-4dd6-8f8a-34c38ea3cf02%2540platform%26firstname%3Ds%26lastname%3Ds%26deletecookie%3Dtrue%26event_email%3DN%26marketing_email%3DN%26std1%3D0642572014177%26std2%3D0642572014179%26std3%3D550165f7-a44e-4725-9fe6-716f89908c2b%26std4%3D0&eventuserid=745776448&contenttype=A&mediametricsessionid=640613707&mediametricid=6810717&usercd=745776448&mode=launch',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
-        mobj = self._match_valid_url(url)
+        event_id, event_key = self._match_valid_url(url).group('id', 'key')
-        event_id = mobj.group('id_1') or mobj.group('id_2')
-        event_key = mobj.group('key_1') or mobj.group('key_2')
 
         event_data = self._download_json(
             'https://event.on24.com/apic/utilApp/EventConsoleCachedServlet',

yt_dlp/extractor/parti.py

@@ -0,0 +1,101 @@
+from .common import InfoExtractor
+from ..utils import UserNotLive, int_or_none, parse_iso8601, url_or_none, urljoin
+from ..utils.traversal import traverse_obj
+
+
+class PartiBaseIE(InfoExtractor):
+    def _call_api(self, path, video_id, note=None):
+        return self._download_json(
+            f'https://api-backend.parti.com/parti_v2/profile/{path}', video_id, note)
+
+
+class PartiVideoIE(PartiBaseIE):
+    IE_NAME = 'parti:video'
+    _VALID_URL = r'https?://(?:www\.)?parti\.com/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://parti.com/video/66284',
+        'info_dict': {
+            'id': '66284',
+            'ext': 'mp4',
+            'title': 'NOW LIVE ',
+            'upload_date': '20250327',
+            'categories': ['Gaming'],
+            'thumbnail': 'https://assets.parti.com/351424_eb9e5250-2821-484a-9c5f-ca99aa666c87.png',
+            'channel': 'ItZTMGG',
+            'timestamp': 1743044379,
+        },
+        'params': {'skip_download': 'm3u8'},
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        data = self._call_api(f'get_livestream_channel_info/recent/{video_id}', video_id)
+
+        return {
+            'id': video_id,
+            'formats': self._extract_m3u8_formats(
+                urljoin('https://watch.parti.com', data['livestream_recording']), video_id, 'mp4'),
+            **traverse_obj(data, {
+                'title': ('event_title', {str}),
+                'channel': ('user_name', {str}),
+                'thumbnail': ('event_file', {url_or_none}),
+                'categories': ('category_name', {str}, filter, all),
+                'timestamp': ('event_start_ts', {int_or_none}),
+            }),
+        }
+
+
+class PartiLivestreamIE(PartiBaseIE):
+    IE_NAME = 'parti:livestream'
+    _VALID_URL = r'https?://(?:www\.)?parti\.com/creator/(?P<service>[\w]+)/(?P<id>[\w/-]+)'
+    _TESTS = [{
+        'url': 'https://parti.com/creator/parti/Capt_Robs_Adventures',
+        'info_dict': {
+            'id': 'Capt_Robs_Adventures',
+            'ext': 'mp4',
+            'title': r"re:I'm Live on Parti \d{4}-\d{2}-\d{2} \d{2}:\d{2}",
+            'view_count': int,
+            'thumbnail': r're:https://assets\.parti\.com/.+\.png',
+            'timestamp': 1743879776,
+            'upload_date': '20250405',
+            'live_status': 'is_live',
+        },
+        'params': {'skip_download': 'm3u8'},
+    }, {
+        'url': 'https://parti.com/creator/discord/sazboxgaming/0',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        service, creator_slug = self._match_valid_url(url).group('service', 'id')
+
+        encoded_creator_slug = creator_slug.replace('/', '%23')
+        creator_id = self._call_api(
+            f'get_user_by_social_media/{service}/{encoded_creator_slug}',
+            creator_slug, note='Fetching user ID')
+
+        data = self._call_api(
+            f'get_livestream_channel_info/{creator_id}', creator_id,
+            note='Fetching user profile feed')['channel_info']
+
+        if not traverse_obj(data, ('channel', 'is_live', {bool})):
+            raise UserNotLive(video_id=creator_id)
+
+        channel_info = data['channel']
+
+        return {
+            'id': creator_slug,
+            'formats': self._extract_m3u8_formats(
+                channel_info['playback_url'], creator_slug, live=True, query={
+                    'token': channel_info['playback_auth_token'],
+                    'player_version': '1.17.0',
+                }),
+            'is_live': True,
+            **traverse_obj(data, {
+                'title': ('livestream_event_info', 'event_name', {str}),
+                'description': ('livestream_event_info', 'event_description', {str}),
+                'thumbnail': ('livestream_event_info', 'livestream_preview_file', {url_or_none}),
+                'timestamp': ('stream', 'start_time', {parse_iso8601}),
+                'view_count': ('stream', 'viewer_count', {int_or_none}),
+            }),
+        }

yt_dlp/extractor/polskieradio.py

@@ -22,7 +22,7 @@ from ..utils import (
 )
 
 
-class PolskieRadioBaseExtractor(InfoExtractor):
+class PolskieRadioBaseIE(InfoExtractor):
     def _extract_webpage_player_entries(self, webpage, playlist_id, base_data):
         media_urls = set()
 
@@ -47,7 +47,7 @@ class PolskieRadioBaseExtractor(InfoExtractor):
             yield entry
 
 
-class PolskieRadioLegacyIE(PolskieRadioBaseExtractor):
+class PolskieRadioLegacyIE(PolskieRadioBaseIE):
     # legacy sites
     IE_NAME = 'polskieradio:legacy'
     _VALID_URL = r'https?://(?:www\.)?polskieradio(?:24)?\.pl/\d+/\d+/[Aa]rtykul/(?P<id>\d+)'
@@ -127,7 +127,7 @@ class PolskieRadioLegacyIE(PolskieRadioBaseExtractor):
         return self.playlist_result(entries, playlist_id, title, description)
 
 
-class PolskieRadioIE(PolskieRadioBaseExtractor):
+class PolskieRadioIE(PolskieRadioBaseIE):
     # new next.js sites
     _VALID_URL = r'https?://(?:[^/]+\.)?(?:polskieradio(?:24)?|radiokierowcow)\.pl/artykul/(?P<id>\d+)'
     _TESTS = [{
@@ -519,7 +519,7 @@ class PolskieRadioPlayerIE(InfoExtractor):
         }
 
 
-class PolskieRadioPodcastBaseExtractor(InfoExtractor):
+class PolskieRadioPodcastBaseIE(InfoExtractor):
     _API_BASE = 'https://apipodcasts.polskieradio.pl/api'
 
     def _parse_episode(self, data):
@@ -539,7 +539,7 @@ class PolskieRadioPodcastBaseExtractor(InfoExtractor):
         }
 
 
-class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseExtractor):
+class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseIE):
     IE_NAME = 'polskieradio:podcast:list'
     _VALID_URL = r'https?://podcasty\.polskieradio\.pl/podcast/(?P<id>\d+)'
     _TESTS = [{
@@ -578,7 +578,7 @@ class PolskieRadioPodcastListIE(PolskieRadioPodcastBaseExtractor):
         }
 
 
-class PolskieRadioPodcastIE(PolskieRadioPodcastBaseExtractor):
+class PolskieRadioPodcastIE(PolskieRadioPodcastBaseIE):
     IE_NAME = 'polskieradio:podcast'
     _VALID_URL = r'https?://podcasty\.polskieradio\.pl/track/(?P<id>[a-f\d]{8}(?:-[a-f\d]{4}){4}[a-f\d]{8})'
     _TESTS = [{

yt_dlp/extractor/redgifs.py

@@ -12,7 +12,7 @@ from ..utils import (
 )
 
 
-class RedGifsBaseInfoExtractor(InfoExtractor):
+class RedGifsBaseIE(InfoExtractor):
     _FORMATS = {
         'gif': 250,
         'sd': 480,
@@ -113,7 +113,7 @@ class RedGifsBaseInfoExtractor(InfoExtractor):
         return page_fetcher(page) if page else OnDemandPagedList(page_fetcher, self._PAGE_SIZE)
 
 
-class RedGifsIE(RedGifsBaseInfoExtractor):
+class RedGifsIE(RedGifsBaseIE):
     _VALID_URL = r'https?://(?:(?:www\.)?redgifs\.com/(?:watch|ifr)/|thumbs2\.redgifs\.com/)(?P<id>[^-/?#\.]+)'
     _TESTS = [{
         'url': 'https://www.redgifs.com/watch/squeakyhelplesswisent',
@@ -172,7 +172,7 @@ class RedGifsIE(RedGifsBaseInfoExtractor):
         return self._parse_gif_data(video_info['gif'])
 
 
-class RedGifsSearchIE(RedGifsBaseInfoExtractor):
+class RedGifsSearchIE(RedGifsBaseIE):
     IE_DESC = 'Redgifs search'
     _VALID_URL = r'https?://(?:www\.)?redgifs\.com/browse\?(?P<query>[^#]+)'
     _PAGE_SIZE = 80
@@ -226,7 +226,7 @@ class RedGifsSearchIE(RedGifsBaseInfoExtractor):
             entries, query_str, tags, f'RedGifs search for {tags}, ordered by {order}')
 
 
-class RedGifsUserIE(RedGifsBaseInfoExtractor):
+class RedGifsUserIE(RedGifsBaseIE):
     IE_DESC = 'Redgifs user'
     _VALID_URL = r'https?://(?:www\.)?redgifs\.com/users/(?P<username>[^/?#]+)(?:\?(?P<query>[^#]+))?'
     _PAGE_SIZE = 80

yt_dlp/extractor/roya.py

@@ -0,0 +1,43 @@
+from .common import InfoExtractor
+from ..utils.traversal import traverse_obj
+
+
+class RoyaLiveIE(InfoExtractor):
+    _VALID_URL = r'https?://roya\.tv/live-stream/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://roya.tv/live-stream/1',
+        'info_dict': {
+            'id': '1',
+            'title': r're:Roya TV \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'ext': 'mp4',
+            'live_status': 'is_live',
+        },
+    }, {
+        'url': 'https://roya.tv/live-stream/21',
+        'info_dict': {
+            'id': '21',
+            'title': r're:Roya News \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
+            'ext': 'mp4',
+            'live_status': 'is_live',
+        },
+    }, {
+        'url': 'https://roya.tv/live-stream/10000',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        media_id = self._match_id(url)
+
+        stream_url = self._download_json(
+            f'https://ticket.roya-tv.com/api/v5/fastchannel/{media_id}', media_id)['data']['secured_url']
+
+        title = traverse_obj(
+            self._download_json('https://backend.roya.tv/api/v01/channels/schedule-pagination', media_id, fatal=False),
+            ('data', 0, 'channel', lambda _, v: str(v['id']) == media_id, 'title', {str}, any))
+
+        return {
+            'id': media_id,
+            'formats': self._extract_m3u8_formats(stream_url, media_id, 'mp4', m3u8_id='hls', live=True),
+            'title': title,
+            'is_live': True,
+        }

yt_dlp/extractor/rtvs.py

@@ -9,7 +9,9 @@ from ..utils import (
 
 
 class RTVSIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
+    IE_NAME = 'stvr'
+    IE_DESC = 'Slovak Television and Radio (formerly RTVS)'
+    _VALID_URL = r'https?://(?:www\.)?(?:rtvs|stvr)\.sk/(?:radio|televizia)/archiv(?:/\d+)?/(?P<id>\d+)/?(?:[#?]|$)'
     _TESTS = [{
         # radio archive
         'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
@@ -19,7 +21,7 @@ class RTVSIE(InfoExtractor):
             'ext': 'mp3',
             'title': 'Ostrov pokladov 1 časť.mp3',
             'duration': 2854,
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0000/b1R8.rtvs.jpg',
+            'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0000/rtvs-00009383.png',
             'display_id': '135331',
         },
     }, {
@@ -30,7 +32,7 @@ class RTVSIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'Amaro Džives - Náš deň',
             'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.',
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
+            'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0031/L7Qm.amaro_dzives_png.jpg',
             'timestamp': 1428555900,
             'upload_date': '20150409',
             'duration': 4986,
@@ -47,8 +49,11 @@ class RTVSIE(InfoExtractor):
             'display_id': '307655',
             'duration': 831,
             'upload_date': '20211111',
-            'thumbnail': 'https://www.rtvs.sk/media/a501/image/file/2/0916/robin.jpg',
+            'thumbnail': 'https://www.stvr.sk/media/a501/image/file/2/0916/robin.jpg',
         },
+    }, {
+        'url': 'https://www.stvr.sk/radio/archiv/11224/414872',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/rumble.py

@@ -7,7 +7,6 @@ from ..utils import (
     ExtractorError,
     UnsupportedError,
     clean_html,
-    determine_ext,
     extract_attributes,
     format_field,
     get_element_by_class,
@@ -36,7 +35,7 @@ class RumbleEmbedIE(InfoExtractor):
             'upload_date': '20191020',
             'channel_url': 'https://rumble.com/c/WMAR',
             'channel': 'WMAR',
-            'thumbnail': 'https://sp.rmbl.ws/s8/1/5/M/z/1/5Mz1a.qR4e-small-WMAR-2-News-Latest-Headline.jpg',
+            'thumbnail': r're:https://.+\.jpg',
             'duration': 234,
             'uploader': 'WMAR',
             'live_status': 'not_live',
@@ -52,7 +51,7 @@ class RumbleEmbedIE(InfoExtractor):
             'upload_date': '20220217',
             'channel_url': 'https://rumble.com/c/CyberTechNews',
             'channel': 'CTNews',
-            'thumbnail': 'https://sp.rmbl.ws/s8/6/7/i/9/h/7i9hd.OvCc.jpg',
+            'thumbnail': r're:https://.+\.jpg',
             'duration': 901,
             'uploader': 'CTNews',
             'live_status': 'not_live',
@@ -114,6 +113,22 @@ class RumbleEmbedIE(InfoExtractor):
             'live_status': 'was_live',
         },
         'params': {'skip_download': True},
+    }, {
+        'url': 'https://rumble.com/embed/v6pezdb',
+        'info_dict': {
+            'id': 'v6pezdb',
+            'ext': 'mp4',
+            'title': '"Es war einmal ein Mädchen" – Ein filmisches Zeitzeugnis aus Leningrad 1944',
+            'uploader': 'RT DE',
+            'channel': 'RT DE',
+            'channel_url': 'https://rumble.com/c/RTDE',
+            'duration': 309,
+            'thumbnail': 'https://1a-1791.com/video/fww1/dc/s8/1/n/z/2/y/nz2yy.qR4e-small-Es-war-einmal-ein-Mdchen-Ei.jpg',
+            'timestamp': 1743703500,
+            'upload_date': '20250403',
+            'live_status': 'not_live',
+        },
+        'params': {'skip_download': True},
     }, {
         'url': 'https://rumble.com/embed/ufe9n.v5pv5f',
         'only_matching': True,
@@ -168,40 +183,42 @@ class RumbleEmbedIE(InfoExtractor):
             live_status = None
 
         formats = []
-        for ext, ext_info in (video.get('ua') or {}).items():
+        for format_type, format_info in (video.get('ua') or {}).items():
-            if isinstance(ext_info, dict):
+            if isinstance(format_info, dict):
-                for height, video_info in ext_info.items():
+                for height, video_info in format_info.items():
                     if not traverse_obj(video_info, ('meta', 'h', {int_or_none})):
                         video_info.setdefault('meta', {})['h'] = height
-                ext_info = ext_info.values()
+                format_info = format_info.values()
 
-            for video_info in ext_info:
+            for video_info in format_info:
                 meta = video_info.get('meta') or {}
                 if not video_info.get('url'):
                     continue
-                if ext == 'hls':
+                # With default query params returns m3u8 variants which are duplicates, without returns tar files
+                if format_type == 'tar':
+                    continue
+                if format_type == 'hls':
                     if meta.get('live') is True and video.get('live') == 1:
                         live_status = 'post_live'
                     formats.extend(self._extract_m3u8_formats(
                         video_info['url'], video_id,
                         ext='mp4', m3u8_id='hls', fatal=False, live=live_status == 'is_live'))
                     continue
-                timeline = ext == 'timeline'
+                is_timeline = format_type == 'timeline'
-                if timeline:
+                is_audio = format_type == 'audio'
-                    ext = determine_ext(video_info['url'])
                 formats.append({
-                    'ext': ext,
+                    'acodec': 'none' if is_timeline else None,
-                    'acodec': 'none' if timeline else None,
+                    'vcodec': 'none' if is_audio else None,
                     'url': video_info['url'],
-                    'format_id': join_nonempty(ext, format_field(meta, 'h', '%sp')),
+                    'format_id': join_nonempty(format_type, format_field(meta, 'h', '%sp')),
-                    'format_note': 'Timeline' if timeline else None,
+                    'format_note': 'Timeline' if is_timeline else None,
-                    'fps': None if timeline else video.get('fps'),
+                    'fps': None if is_timeline or is_audio else video.get('fps'),
                     **traverse_obj(meta, {
-                        'tbr': 'bitrate',
+                        'tbr': ('bitrate', {int_or_none}),
-                        'filesize': 'size',
+                        'filesize': ('size', {int_or_none}),
-                        'width': 'w',
+                        'width': ('w', {int_or_none}),
-                        'height': 'h',
+                        'height': ('h', {int_or_none}),
-                    }, expected_type=lambda x: int(x) or None),
+                    }),
                 })
 
         subtitles = {

yt_dlp/extractor/sbs.py

@@ -122,6 +122,15 @@ class SBSIE(InfoExtractor):
         if traverse_obj(media, ('partOfSeries', {dict})):
             media['epName'] = traverse_obj(media, ('title', {str}))
 
+        # Need to set different language for forced subs or else they have priority over full subs
+        fixed_subtitles = {}
+        for lang, subs in subtitles.items():
+            for sub in subs:
+                fixed_lang = lang
+                if sub['url'].lower().endswith('_fe.vtt'):
+                    fixed_lang += '-forced'
+                fixed_subtitles.setdefault(fixed_lang, []).append(sub)
+
         return {
             'id': video_id,
             **traverse_obj(media, {
@@ -151,6 +160,6 @@ class SBSIE(InfoExtractor):
                 }),
             }),
             'formats': formats,
-            'subtitles': subtitles,
+            'subtitles': fixed_subtitles,
             'uploader': 'SBSC',
         }

yt_dlp/extractor/senategov.py

@@ -13,7 +13,7 @@ from ..utils.traversal import traverse_obj
 
 
 class SenateISVPIE(InfoExtractor):
-    _IE_NAME = 'senate.gov:isvp'
+    IE_NAME = 'senate.gov:isvp'
     _VALID_URL = r'https?://(?:www\.)?senate\.gov/isvp/?\?(?P<qs>.+)'
     _EMBED_REGEX = [r"<iframe[^>]+src=['\"](?P<url>https?://www\.senate\.gov/isvp/?\?[^'\"]+)['\"]"]
 
@@ -137,7 +137,7 @@ class SenateISVPIE(InfoExtractor):
 
 
 class SenateGovIE(InfoExtractor):
-    _IE_NAME = 'senate.gov'
+    IE_NAME = 'senate.gov'
     _SUBDOMAIN_RE = '|'.join(map(re.escape, (
         'agriculture', 'aging', 'appropriations', 'armed-services', 'banking',
         'budget', 'commerce', 'energy', 'epw', 'finance', 'foreign', 'help',

yt_dlp/extractor/streaks.py

@@ -0,0 +1,236 @@
+import json
+import urllib.parse
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    filter_dict,
+    float_or_none,
+    join_nonempty,
+    mimetype2ext,
+    parse_iso8601,
+    unsmuggle_url,
+    update_url_query,
+    url_or_none,
+)
+from ..utils.traversal import traverse_obj
+
+
+class StreaksBaseIE(InfoExtractor):
+    _API_URL_TEMPLATE = 'https://{}.api.streaks.jp/v1/projects/{}/medias/{}{}'
+    _GEO_BYPASS = False
+    _GEO_COUNTRIES = ['JP']
+
+    def _extract_from_streaks_api(self, project_id, media_id, headers=None, query=None, ssai=False):
+        try:
+            response = self._download_json(
+                self._API_URL_TEMPLATE.format('playback', project_id, media_id, ''),
+                media_id, 'Downloading STREAKS playback API JSON', headers={
+                    'Accept': 'application/json',
+                    'Origin': 'https://players.streaks.jp',
+                    **self.geo_verification_headers(),
+                    **(headers or {}),
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status in {403, 404}:
+                error = self._parse_json(e.cause.response.read().decode(), media_id, fatal=False)
+                message = traverse_obj(error, ('message', {str}))
+                code = traverse_obj(error, ('code', {str}))
+                if code == 'REQUEST_FAILED':
+                    self.raise_geo_restricted(message, countries=self._GEO_COUNTRIES)
+                elif code == 'MEDIA_NOT_FOUND':
+                    raise ExtractorError(message, expected=True)
+                elif code or message:
+                    raise ExtractorError(join_nonempty(code, message, delim=': '))
+            raise
+
+        streaks_id = response['id']
+        live_status = {
+            'clip': 'was_live',
+            'file': 'not_live',
+            'linear': 'is_live',
+            'live': 'is_live',
+        }.get(response.get('type'))
+
+        formats, subtitles = [], {}
+        drm_formats = False
+
+        for source in traverse_obj(response, ('sources', lambda _, v: v['src'])):
+            if source.get('key_systems'):
+                drm_formats = True
+                continue
+
+            src_url = source['src']
+            is_live = live_status == 'is_live'
+            ext = mimetype2ext(source.get('type'))
+            if ext != 'm3u8':
+                self.report_warning(f'Unsupported stream type: {ext}')
+                continue
+
+            if is_live and ssai:
+                session_params = traverse_obj(self._download_json(
+                    self._API_URL_TEMPLATE.format('ssai', project_id, streaks_id, '/ssai/session'),
+                    media_id, 'Downloading session parameters',
+                    headers={'Content-Type': 'application/json', 'Accept': 'application/json'},
+                    data=json.dumps({'id': source['id']}).encode(),
+                ), (0, 'query', {urllib.parse.parse_qs}))
+                src_url = update_url_query(src_url, session_params)
+
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                src_url, media_id, 'mp4', m3u8_id='hls', fatal=False, live=is_live, query=query)
+            formats.extend(fmts)
+            self._merge_subtitles(subs, target=subtitles)
+
+        if not formats and drm_formats:
+            self.report_drm(media_id)
+        self._remove_duplicate_formats(formats)
+
+        for subs in traverse_obj(response, (
+            'tracks', lambda _, v: v['kind'] in ('captions', 'subtitles') and url_or_none(v['src']),
+        )):
+            lang = traverse_obj(subs, ('srclang', {str.lower})) or 'ja'
+            subtitles.setdefault(lang, []).append({'url': subs['src']})
+
+        return {
+            'id': streaks_id,
+            'display_id': media_id,
+            'formats': formats,
+            'live_status': live_status,
+            'subtitles': subtitles,
+            'uploader_id': project_id,
+            **traverse_obj(response, {
+                'title': ('name', {str}),
+                'description': ('description', {str}, filter),
+                'duration': ('duration', {float_or_none}),
+                'modified_timestamp': ('updated_at', {parse_iso8601}),
+                'tags': ('tags', ..., {str}),
+                'thumbnails': (('poster', 'thumbnail'), 'src', {'url': {url_or_none}}),
+                'timestamp': ('created_at', {parse_iso8601}),
+            }),
+        }
+
+
+class StreaksIE(StreaksBaseIE):
+    _VALID_URL = [
+        r'https?://players\.streaks\.jp/(?P<project_id>[\w-]+)/[\da-f]+/index\.html\?(?:[^#]+&)?m=(?P<id>(?:ref:)?[\w-]+)',
+        r'https?://playback\.api\.streaks\.jp/v1/projects/(?P<project_id>[\w-]+)/medias/(?P<id>(?:ref:)?[\w-]+)',
+    ]
+    _EMBED_REGEX = [rf'<iframe\s+[^>]*\bsrc\s*=\s*["\'](?P<url>{_VALID_URL[0]})']
+    _TESTS = [{
+        'url': 'https://players.streaks.jp/tipness/08155cd19dc14c12bebefb69b92eafcc/index.html?m=dbdf2df35b4d483ebaeeaeb38c594647',
+        'info_dict': {
+            'id': 'dbdf2df35b4d483ebaeeaeb38c594647',
+            'ext': 'mp4',
+            'title': '3shunenCM_edit.mp4',
+            'display_id': 'dbdf2df35b4d483ebaeeaeb38c594647',
+            'duration': 47.533,
+            'live_status': 'not_live',
+            'modified_date': '20230726',
+            'modified_timestamp': 1690356180,
+            'timestamp': 1690355996,
+            'upload_date': '20230726',
+            'uploader_id': 'tipness',
+        },
+    }, {
+        'url': 'https://players.streaks.jp/ktv-web/0298e8964c164ab384c07ef6e08c444b/index.html?m=ref:mycoffeetime_250317',
+        'info_dict': {
+            'id': 'dccdc079e3fd41f88b0c8435e2d453ab',
+            'ext': 'mp4',
+            'title': 'わたしの珈琲時間_250317',
+            'display_id': 'ref:mycoffeetime_250317',
+            'duration': 122.99,
+            'live_status': 'not_live',
+            'modified_date': '20250310',
+            'modified_timestamp': 1741586302,
+            'thumbnail': r're:https?://.+\.jpg',
+            'timestamp': 1741585839,
+            'upload_date': '20250310',
+            'uploader_id': 'ktv-web',
+        },
+    }, {
+        'url': 'https://playback.api.streaks.jp/v1/projects/ktv-web/medias/b5411938e1e5435dac71edf829dd4813',
+        'info_dict': {
+            'id': 'b5411938e1e5435dac71edf829dd4813',
+            'ext': 'mp4',
+            'title': 'KANTELE_SYUSEi_0630',
+            'display_id': 'b5411938e1e5435dac71edf829dd4813',
+            'live_status': 'not_live',
+            'modified_date': '20250122',
+            'modified_timestamp': 1737522999,
+            'thumbnail': r're:https?://.+\.jpg',
+            'timestamp': 1735205137,
+            'upload_date': '20241226',
+            'uploader_id': 'ktv-web',
+        },
+    }, {
+        # TVer Olympics: website already down, but api remains accessible
+        'url': 'https://playback.api.streaks.jp/v1/projects/tver-olympic/medias/ref:sp_240806_1748_dvr',
+        'info_dict': {
+            'id': 'c10f7345adb648cf804d7578ab93b2e3',
+            'ext': 'mp4',
+            'title': 'サッカー 男子 準決勝_dvr',
+            'display_id': 'ref:sp_240806_1748_dvr',
+            'duration': 12960.0,
+            'live_status': 'was_live',
+            'modified_date': '20240805',
+            'modified_timestamp': 1722896263,
+            'timestamp': 1722777618,
+            'upload_date': '20240804',
+            'uploader_id': 'tver-olympic',
+        },
+    }, {
+        # TBS FREE: 24-hour stream
+        'url': 'https://playback.api.streaks.jp/v1/projects/tbs/medias/ref:simul-02',
+        'info_dict': {
+            'id': 'c4e83a7b48f4409a96adacec674b4e22',
+            'ext': 'mp4',
+            'title': str,
+            'display_id': 'ref:simul-02',
+            'live_status': 'is_live',
+            'modified_date': '20241031',
+            'modified_timestamp': 1730339858,
+            'timestamp': 1705466840,
+            'upload_date': '20240117',
+            'uploader_id': 'tbs',
+        },
+    }, {
+        # DRM protected
+        'url': 'https://players.streaks.jp/sp-jbc/a12d7ee0f40c49d6a0a2bff520639677/index.html?m=5f89c62f37ee4a68be8e6e3b1396c7d8',
+        'only_matching': True,
+    }]
+    _WEBPAGE_TESTS = [{
+        'url': 'https://event.play.jp/playnext2023/',
+        'info_dict': {
+            'id': '2d975178293140dc8074a7fc536a7604',
+            'ext': 'mp4',
+            'title': 'PLAY NEXTキームービー（本番）',
+            'uploader_id': 'play',
+            'duration': 17.05,
+            'thumbnail': r're:https?://.+\.jpg',
+            'timestamp': 1668387517,
+            'upload_date': '20221114',
+            'modified_timestamp': 1739411523,
+            'modified_date': '20250213',
+            'live_status': 'not_live',
+        },
+    }, {
+        'url': 'https://wowshop.jp/Page/special/cooking_goods/?bid=wowshop&srsltid=AfmBOor_phUNoPEE_UCPiGGSCMrJE5T2US397smvsbrSdLqUxwON0el4',
+        'playlist_mincount': 2,
+        'info_dict': {
+            'id': '?bid=wowshop&srsltid=AfmBOor_phUNoPEE_UCPiGGSCMrJE5T2US397smvsbrSdLqUxwON0el4',
+            'title': 'ワンランク上の料理道具でとびきりの“おいしい”を食卓へ｜wowshop',
+            'description': 'md5:914b5cb8624fc69274c7fb7b2342958f',
+            'age_limit': 0,
+            'thumbnail': 'https://wowshop.jp/Page/special/cooking_goods/images/ogp.jpg',
+        },
+    }]
+
+    def _real_extract(self, url):
+        url, smuggled_data = unsmuggle_url(url, {})
+        project_id, media_id = self._match_valid_url(url).group('project_id', 'id')
+
+        return self._extract_from_streaks_api(
+            project_id, media_id, headers=filter_dict({
+                'X-Streaks-Api-Key': smuggled_data.get('api_key'),
+            }))

yt_dlp/extractor/taptap.py

@@ -191,12 +191,12 @@ class TapTapAppIE(TapTapBaseIE):
     }]
 
 
-class TapTapIntlBase(TapTapBaseIE):
+class TapTapIntlBaseIE(TapTapBaseIE):
     _X_UA = 'V=1&PN=WebAppIntl2&LANG=zh_TW&VN_CODE=115&VN=0.1.0&LOC=CN&PLT=PC&DS=Android&UID={uuid}&CURR=&DT=PC&OS=Windows&OSV=NT%208.0.0'
     _VIDEO_API = 'https://www.taptap.io/webapiv2/video-resource/v1/multi-get'
 
 
-class TapTapAppIntlIE(TapTapIntlBase):
+class TapTapAppIntlIE(TapTapIntlBaseIE):
     _VALID_URL = r'https?://www\.taptap\.io/app/(?P<id>\d+)'
     _INFO_API = 'https://www.taptap.io/webapiv2/i/app/v5/detail'
     _DATA_PATH = 'app'
@@ -227,7 +227,7 @@ class TapTapAppIntlIE(TapTapIntlBase):
     }]
 
 
-class TapTapPostIntlIE(TapTapIntlBase):
+class TapTapPostIntlIE(TapTapIntlBaseIE):
     _VALID_URL = r'https?://www\.taptap\.io/post/(?P<id>\d+)'
     _INFO_API = 'https://www.taptap.io/webapiv2/creation/post/v1/detail'
     _INFO_QUERY_KEY = 'id_str'

yt_dlp/extractor/tver.py

@@ -1,31 +1,70 @@
-from .common import InfoExtractor
+from .streaks import StreaksBaseIE
 from ..utils import (
     ExtractorError,
+    int_or_none,
     join_nonempty,
+    make_archive_id,
     smuggle_url,
     str_or_none,
     strip_or_none,
-    traverse_obj,
     update_url_query,
 )
+from ..utils.traversal import require, traverse_obj
 
 
-class TVerIE(InfoExtractor):
+class TVerIE(StreaksBaseIE):
     _VALID_URL = r'https?://(?:www\.)?tver\.jp/(?:(?P<type>lp|corner|series|episodes?|feature)/)+(?P<id>[a-zA-Z0-9]+)'
+    _GEO_COUNTRIES = ['JP']
+    _GEO_BYPASS = False
     _TESTS = [{
-        'skip': 'videos are only available for 7 days',
+        # via Streaks backend
-        'url': 'https://tver.jp/episodes/ep83nf3w4p',
+        'url': 'https://tver.jp/episodes/epc1hdugbk',
         'info_dict': {
-            'title': '家事ヤロウ!!! 売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
+            'id': 'epc1hdugbk',
-            'description': 'md5:dc2c06b6acc23f1e7c730c513737719b',
-            'series': '家事ヤロウ!!!',
-            'episode': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
-            'alt_title': '売り場席巻のチーズSP＆財前直見×森泉親子の脱東京暮らし密着！',
-            'channel': 'テレビ朝日',
-            'id': 'ep83nf3w4p',
             'ext': 'mp4',
+            'display_id': 'ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068',
+            'title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル）',
+            'alt_title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル） 日テレ',
+            'description': 'md5:2726f742d5e3886edeaf72fb6d740fef',
+            'uploader_id': 'tver-ntv',
+            'channel': '日テレ',
+            'duration': 1158.024,
+            'thumbnail': 'https://statics.tver.jp/images/content/thumbnail/episode/xlarge/epc1hdugbk.jpg?v=16',
+            'series': '神回だけ見せます！',
+            'episode': '#2 壮烈！車大騎馬戦（木曜スペシャル）',
+            'episode_number': 2,
+            'timestamp': 1736486036,
+            'upload_date': '20250110',
+            'modified_timestamp': 1736870264,
+            'modified_date': '20250114',
+            'live_status': 'not_live',
+            'release_timestamp': 1651453200,
+            'release_date': '20220502',
+            '_old_archive_ids': ['brightcovenew ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068'],
         },
-        'add_ie': ['BrightcoveNew'],
+    }, {
+        # via Brightcove backend (deprecated)
+        'url': 'https://tver.jp/episodes/epc1hdugbk',
+        'info_dict': {
+            'id': 'ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068',
+            'ext': 'mp4',
+            'title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル）',
+            'alt_title': '神回だけ見せます！ #2 壮烈！車大騎馬戦（木曜スペシャル） 日テレ',
+            'description': 'md5:2726f742d5e3886edeaf72fb6d740fef',
+            'uploader_id': '4394098882001',
+            'channel': '日テレ',
+            'duration': 1158.101,
+            'thumbnail': 'https://statics.tver.jp/images/content/thumbnail/episode/xlarge/epc1hdugbk.jpg?v=16',
+            'tags': [],
+            'series': '神回だけ見せます！',
+            'episode': '#2 壮烈！車大騎馬戦（木曜スペシャル）',
+            'episode_number': 2,
+            'timestamp': 1651388531,
+            'upload_date': '20220501',
+            'release_timestamp': 1651453200,
+            'release_date': '20220502',
+        },
+        'params': {'extractor_args': {'tver': {'backend': ['brightcove']}}},
     }, {
         'url': 'https://tver.jp/corner/f0103888',
         'only_matching': True,
@@ -38,26 +77,7 @@ class TVerIE(InfoExtractor):
             'id': 'srtxft431v',
             'title': '名探偵コナン',
         },
-        'playlist': [
+        'playlist_mincount': 21,
-            {
-                'md5': '779ffd97493ed59b0a6277ea726b389e',
-                'info_dict': {
-                    'id': 'ref:conan-1137-241005',
-                    'ext': 'mp4',
-                    'title': '名探偵コナン #1137「行列店、味変の秘密」',
-                    'uploader_id': '5330942432001',
-                    'tags': [],
-                    'channel': '読売テレビ',
-                    'series': '名探偵コナン',
-                    'description': 'md5:601fccc1d2430d942a2c8068c4b33eb5',
-                    'episode': '#1137「行列店、味変の秘密」',
-                    'duration': 1469.077,
-                    'timestamp': 1728030405,
-                    'upload_date': '20241004',
-                    'alt_title': '名探偵コナン #1137「行列店、味変の秘密」 読売テレビ 10月5日(土)放送分',
-                    'thumbnail': r're:https://.+\.jpg',
-                },
-            }],
     }, {
         'url': 'https://tver.jp/series/sru35hwdd2',
         'info_dict': {
@@ -70,7 +90,11 @@ class TVerIE(InfoExtractor):
         'only_matching': True,
     }]
     BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
-    _HEADERS = {'x-tver-platform-type': 'web'}
+    _HEADERS = {
+        'x-tver-platform-type': 'web',
+        'Origin': 'https://tver.jp',
+        'Referer': 'https://tver.jp/',
+    }
     _PLATFORM_QUERY = {}
 
     def _real_initialize(self):
@@ -103,6 +127,9 @@ class TVerIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id, video_type = self._match_valid_url(url).group('id', 'type')
+        backend = self._configuration_arg('backend', ['streaks'])[0]
+        if backend not in ('brightcove', 'streaks'):
+            raise ExtractorError(f'Invalid backend value: {backend}', expected=True)
 
         if video_type == 'series':
             series_info = self._call_platform_api(
@@ -129,12 +156,6 @@ class TVerIE(InfoExtractor):
         video_info = self._download_json(
             f'https://statics.tver.jp/content/episode/{video_id}.json', video_id, 'Downloading video info',
             query={'v': version}, headers={'Referer': 'https://tver.jp/'})
-        p_id = video_info['video']['accountID']
-        r_id = traverse_obj(video_info, ('video', ('videoRefID', 'videoID')), get_all=False)
-        if not r_id:
-            raise ExtractorError('Failed to extract reference ID for Brightcove')
-        if not r_id.isdigit():
-            r_id = f'ref:{r_id}'
 
         episode = strip_or_none(episode_content.get('title'))
         series = str_or_none(episode_content.get('seriesTitle'))
@@ -161,17 +182,53 @@ class TVerIE(InfoExtractor):
             ]
         ]
 
-        return {
+        metadata = {
-            '_type': 'url_transparent',
             'title': title,
             'series': series,
             'episode': episode,
             # an another title which is considered "full title" for some viewers
             'alt_title': join_nonempty(title, provider, onair_label, delim=' '),
             'channel': provider,
-            'description': str_or_none(video_info.get('description')),
             'thumbnails': thumbnails,
-            'url': smuggle_url(
+            **traverse_obj(video_info, {
-                self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id), {'geo_countries': ['JP']}),
+                'description': ('description', {str}),
-            'ie_key': 'BrightcoveNew',
+                'release_timestamp': ('viewStatus', 'startAt', {int_or_none}),
+                'episode_number': ('no', {int_or_none}),
+            }),
+        }
+
+        brightcove_id = traverse_obj(video_info, ('video', ('videoRefID', 'videoID'), {str}, any))
+        if brightcove_id and not brightcove_id.isdecimal():
+            brightcove_id = f'ref:{brightcove_id}'
+
+        streaks_id = traverse_obj(video_info, ('streaks', 'videoRefID', {str}))
+        if streaks_id and not streaks_id.startswith('ref:'):
+            streaks_id = f'ref:{streaks_id}'
+
+        # Deprecated Brightcove extraction reachable w/extractor-arg or fallback; errors are expected
+        if backend == 'brightcove' or not streaks_id:
+            if backend != 'brightcove':
+                self.report_warning(
+                    'No STREAKS ID found; falling back to Brightcove extraction', video_id=video_id)
+            if not brightcove_id:
+                raise ExtractorError('Unable to extract brightcove reference ID', expected=True)
+            account_id = traverse_obj(video_info, (
+                'video', 'accountID', {str}, {require('brightcove account ID', expected=True)}))
+            return {
+                **metadata,
+                '_type': 'url_transparent',
+                'url': smuggle_url(
+                    self.BRIGHTCOVE_URL_TEMPLATE % (account_id, brightcove_id),
+                    {'geo_countries': ['JP']}),
+                'ie_key': 'BrightcoveNew',
+            }
+
+        return {
+            **self._extract_from_streaks_api(video_info['streaks']['projectID'], streaks_id, {
+                'Origin': 'https://tver.jp',
+                'Referer': 'https://tver.jp/',
+            }),
+            **metadata,
+            'id': video_id,
+            '_old_archive_ids': [make_archive_id('BrightcoveNew', brightcove_id)] if brightcove_id else None,
         }

yt_dlp/extractor/twitch.py

@@ -14,19 +14,20 @@ from ..utils import (
     dict_get,
     float_or_none,
     int_or_none,
+    join_nonempty,
     make_archive_id,
     parse_duration,
     parse_iso8601,
     parse_qs,
     qualities,
     str_or_none,
-    traverse_obj,
     try_get,
     unified_timestamp,
     update_url_query,
     url_or_none,
     urljoin,
 )
+from ..utils.traversal import traverse_obj, value
 
 
 class TwitchBaseIE(InfoExtractor):
@@ -42,10 +43,10 @@ class TwitchBaseIE(InfoExtractor):
         'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
         'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
         'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
+        'ShareClipRenderStatus': 'f130048a462a0ac86bb54d653c968c514e9ab9ca94db52368c1179e97b0f16eb',
         'ChannelCollectionsContent': '447aec6a0cc1e8d0a8d7732d47eb0762c336a2294fdb009e9c9d854e49d484b9',
         'StreamMetadata': 'a647c2a13599e5991e175155f798ca7f1ecddde73f7f341f39009c14dbf59962',
         'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
-        'VideoAccessToken_Clip': '36b89d2507fce29e5ca551df756d27c1cfe079e2609642b4390aa4c35796eb11',
         'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
         'VideoMetadata': '49b5b8f268cdeb259d75b58dcb0c1a748e3b575003448a2333dc5cdafd49adad',
         'VideoPlayer_ChapterSelectButtonVideo': '8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41',
@@ -1083,16 +1084,44 @@ class TwitchClipsIE(TwitchBaseIE):
         'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat',
         'md5': '761769e1eafce0ffebfb4089cb3847cd',
         'info_dict': {
-            'id': '42850523',
+            'id': '396245304',
             'display_id': 'FaintLightGullWholeWheat',
             'ext': 'mp4',
             'title': 'EA Play 2016 Live from the Novo Theatre',
+            'duration': 32,
+            'view_count': int,
             'thumbnail': r're:^https?://.*\.jpg',
             'timestamp': 1465767393,
             'upload_date': '20160612',
-            'creator': 'EA',
+            'creators': ['EA'],
-            'uploader': 'stereotype_',
+            'channel': 'EA',
-            'uploader_id': '43566419',
+            'channel_id': '25163635',
+            'channel_is_verified': False,
+            'channel_follower_count': int,
+            'uploader': 'EA',
+            'uploader_id': '25163635',
+        },
+    }, {
+        'url': 'https://www.twitch.tv/xqc/clip/CulturedAmazingKuduDatSheffy-TiZ_-ixAGYR3y2Uy',
+        'md5': 'e90fe616b36e722a8cfa562547c543f0',
+        'info_dict': {
+            'id': '3207364882',
+            'display_id': 'CulturedAmazingKuduDatSheffy-TiZ_-ixAGYR3y2Uy',
+            'ext': 'mp4',
+            'title': 'A day in the life of xQc',
+            'duration': 60,
+            'view_count': int,
+            'thumbnail': r're:^https?://.*\.jpg',
+            'timestamp': 1742869615,
+            'upload_date': '20250325',
+            'creators': ['xQc'],
+            'channel': 'xQc',
+            'channel_id': '71092938',
+            'channel_is_verified': True,
+            'channel_follower_count': int,
+            'uploader': 'xQc',
+            'uploader_id': '71092938',
+            'categories': ['Just Chatting'],
         },
     }, {
         # multiple formats
@@ -1116,16 +1145,14 @@ class TwitchClipsIE(TwitchBaseIE):
     }]
 
     def _real_extract(self, url):
-        video_id = self._match_id(url)
+        slug = self._match_id(url)
 
         clip = self._download_gql(
-            video_id, [{
+            slug, [{
-                'operationName': 'VideoAccessToken_Clip',
+                'operationName': 'ShareClipRenderStatus',
-                'variables': {
+                'variables': {'slug': slug},
-                    'slug': video_id,
-                },
             }],
-            'Downloading clip access token GraphQL')[0]['data']['clip']
+            'Downloading clip GraphQL')[0]['data']['clip']
 
         if not clip:
             raise ExtractorError(
@@ -1135,81 +1162,71 @@ class TwitchClipsIE(TwitchBaseIE):
             'sig': clip['playbackAccessToken']['signature'],
             'token': clip['playbackAccessToken']['value'],
         }
-
+        asset_default = traverse_obj(clip, ('assets', 0, {dict})) or {}
-        data = self._download_base_gql(
+        asset_portrait = traverse_obj(clip, ('assets', 1, {dict})) or {}
-            video_id, {
-                'query': '''{
-  clip(slug: "%s") {
-    broadcaster {
-      displayName
-    }
-    createdAt
-    curator {
-      displayName
-      id
-    }
-    durationSeconds
-    id
-    tiny: thumbnailURL(width: 86, height: 45)
-    small: thumbnailURL(width: 260, height: 147)
-    medium: thumbnailURL(width: 480, height: 272)
-    title
-    videoQualities {
-      frameRate
-      quality
-      sourceURL
-    }
-    viewCount
-  }
-}''' % video_id}, 'Downloading clip GraphQL', fatal=False)  # noqa: UP031
-
-        if data:
-            clip = try_get(data, lambda x: x['data']['clip'], dict) or clip
 
         formats = []
-        for option in clip.get('videoQualities', []):
+        default_aspect_ratio = float_or_none(asset_default.get('aspectRatio'))
-            if not isinstance(option, dict):
+        formats.extend(traverse_obj(asset_default, ('videoQualities', lambda _, v: url_or_none(v['sourceURL']), {
-                continue
+            'url': ('sourceURL', {update_url_query(query=access_query)}),
-            source = url_or_none(option.get('sourceURL'))
+            'format_id': ('quality', {str}),
-            if not source:
+            'height': ('quality', {int_or_none}),
-                continue
+            'fps': ('frameRate', {float_or_none}),
+            'aspect_ratio': {value(default_aspect_ratio)},
+        })))
+        portrait_aspect_ratio = float_or_none(asset_portrait.get('aspectRatio'))
+        for source in traverse_obj(asset_portrait, ('videoQualities', lambda _, v: url_or_none(v['sourceURL']))):
             formats.append({
-                'url': update_url_query(source, access_query),
+                'url': update_url_query(source['sourceURL'], access_query),
-                'format_id': option.get('quality'),
+                'format_id': join_nonempty('portrait', source.get('quality')),
-                'height': int_or_none(option.get('quality')),
+                'height': int_or_none(source.get('quality')),
-                'fps': int_or_none(option.get('frameRate')),
+                'fps': float_or_none(source.get('frameRate')),
+                'aspect_ratio': portrait_aspect_ratio,
+                'quality': -2,
             })
 
         thumbnails = []
-        for thumbnail_id in ('tiny', 'small', 'medium'):
+        thumb_asset_default_url = url_or_none(asset_default.get('thumbnailURL'))
-            thumbnail_url = clip.get(thumbnail_id)
+        if thumb_asset_default_url:
-            if not thumbnail_url:
+            thumbnails.append({
-                continue
+                'id': 'default',
-            thumb = {
+                'url': thumb_asset_default_url,
-                'id': thumbnail_id,
+                'preference': 0,
-                'url': thumbnail_url,
+            })
-            }
+        if thumb_asset_portrait_url := url_or_none(asset_portrait.get('thumbnailURL')):
-            mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url)
+            thumbnails.append({
-            if mobj:
+                'id': 'portrait',
-                thumb.update({
+                'url': thumb_asset_portrait_url,
-                    'height': int(mobj.group(2)),
+                'preference': -1,
-                    'width': int(mobj.group(1)),
+            })
-                })
+        thumb_default_url = url_or_none(clip.get('thumbnailURL'))
-            thumbnails.append(thumb)
+        if thumb_default_url and thumb_default_url != thumb_asset_default_url:
+            thumbnails.append({
+                'id': 'small',
+                'url': thumb_default_url,
+                'preference': -2,
+            })
 
         old_id = self._search_regex(r'%7C(\d+)(?:-\d+)?.mp4', formats[-1]['url'], 'old id', default=None)
 
         return {
-            'id': clip.get('id') or video_id,
+            'id': clip.get('id') or slug,
             '_old_archive_ids': [make_archive_id(self, old_id)] if old_id else None,
-            'display_id': video_id,
+            'display_id': slug,
-            'title': clip.get('title'),
             'formats': formats,
-            'duration': int_or_none(clip.get('durationSeconds')),
-            'view_count': int_or_none(clip.get('viewCount')),
-            'timestamp': unified_timestamp(clip.get('createdAt')),
             'thumbnails': thumbnails,
-            'creator': try_get(clip, lambda x: x['broadcaster']['displayName'], str),
+            **traverse_obj(clip, {
-            'uploader': try_get(clip, lambda x: x['curator']['displayName'], str),
+                'title': ('title', {str}),
-            'uploader_id': try_get(clip, lambda x: x['curator']['id'], str),
+                'duration': ('durationSeconds', {int_or_none}),
+                'view_count': ('viewCount', {int_or_none}),
+                'timestamp': ('createdAt', {parse_iso8601}),
+                'creators': ('broadcaster', 'displayName', {str}, filter, all),
+                'channel': ('broadcaster', 'displayName', {str}),
+                'channel_id': ('broadcaster', 'id', {str}),
+                'channel_follower_count': ('broadcaster', 'followers', 'totalCount', {int_or_none}),
+                'channel_is_verified': ('broadcaster', 'isPartner', {bool}),
+                'uploader': ('broadcaster', 'displayName', {str}),
+                'uploader_id': ('broadcaster', 'id', {str}),
+                'categories': ('game', 'displayName', {str}, filter, all, filter),
+            }),
         }

yt_dlp/extractor/unsupported.py

@@ -51,6 +51,8 @@ class KnownDRMIE(UnsupportedInfoExtractor):
         r'(?:watch|front)\.njpwworld\.com',
         r'qub\.ca/vrai',
         r'(?:beta\.)?crunchyroll\.com',
+        r'viki\.com',
+        r'deezer\.com',
     )
 
     _TESTS = [{
@@ -160,6 +162,12 @@ class KnownDRMIE(UnsupportedInfoExtractor):
     }, {
         'url': 'https://beta.crunchyroll.com/pt-br/watch/G8WUN8VKP/the-ruler-of-conspiracy',
         'only_matching': True,
+    }, {
+        'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.deezer.com/playlist/176747451',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/viki.py

@@ -1,346 +0,0 @@
-import hashlib
-import hmac
-import json
-import time
-
-from .common import InfoExtractor
-from ..utils import (
-    ExtractorError,
-    int_or_none,
-    parse_age_limit,
-    parse_iso8601,
-    try_get,
-)
-
-
-class VikiBaseIE(InfoExtractor):
-    _VALID_URL_BASE = r'https?://(?:www\.)?viki\.(?:com|net|mx|jp|fr)/'
-    _API_URL_TEMPLATE = 'https://api.viki.io%s'
-
-    _DEVICE_ID = '112395910d'
-    _APP = '100005a'
-    _APP_VERSION = '6.11.3'
-    _APP_SECRET = 'd96704b180208dbb2efa30fe44c48bd8690441af9f567ba8fd710a72badc85198f7472'
-
-    _GEO_BYPASS = False
-    _NETRC_MACHINE = 'viki'
-
-    _token = None
-
-    _ERRORS = {
-        'geo': 'Sorry, this content is not available in your region.',
-        'upcoming': 'Sorry, this content is not yet available.',
-        'paywall': 'Sorry, this content is only available to Viki Pass Plus subscribers',
-    }
-
-    def _stream_headers(self, timestamp, sig):
-        return {
-            'X-Viki-manufacturer': 'vivo',
-            'X-Viki-device-model': 'vivo 1606',
-            'X-Viki-device-os-ver': '6.0.1',
-            'X-Viki-connection-type': 'WIFI',
-            'X-Viki-carrier': '',
-            'X-Viki-as-id': '100005a-1625321982-3932',
-            'timestamp': str(timestamp),
-            'signature': str(sig),
-            'x-viki-app-ver': self._APP_VERSION,
-        }
-
-    def _api_query(self, path, version=4, **kwargs):
-        path += '?' if '?' not in path else '&'
-        query = f'/v{version}/{path}app={self._APP}'
-        if self._token:
-            query += f'&token={self._token}'
-        return query + ''.join(f'&{name}={val}' for name, val in kwargs.items())
-
-    def _sign_query(self, path):
-        timestamp = int(time.time())
-        query = self._api_query(path, version=5)
-        sig = hmac.new(
-            self._APP_SECRET.encode('ascii'), f'{query}&t={timestamp}'.encode('ascii'), hashlib.sha1).hexdigest()
-        return timestamp, sig, self._API_URL_TEMPLATE % query
-
-    def _call_api(
-            self, path, video_id, note='Downloading JSON metadata', data=None, query=None, fatal=True):
-        if query is None:
-            timestamp, sig, url = self._sign_query(path)
-        else:
-            url = self._API_URL_TEMPLATE % self._api_query(path, version=4)
-        resp = self._download_json(
-            url, video_id, note, fatal=fatal, query=query,
-            data=json.dumps(data).encode() if data else None,
-            headers=({'x-viki-app-ver': self._APP_VERSION} if data
-                     else self._stream_headers(timestamp, sig) if query is None
-                     else None), expected_status=400) or {}
-
-        self._raise_error(resp.get('error'), fatal)
-        return resp
-
-    def _raise_error(self, error, fatal=True):
-        if error is None:
-            return
-        msg = f'{self.IE_NAME} said: {error}'
-        if fatal:
-            raise ExtractorError(msg, expected=True)
-        else:
-            self.report_warning(msg)
-
-    def _check_errors(self, data):
-        for reason, status in (data.get('blocking') or {}).items():
-            if status and reason in self._ERRORS:
-                message = self._ERRORS[reason]
-                if reason == 'geo':
-                    self.raise_geo_restricted(msg=message)
-                elif reason == 'paywall':
-                    if try_get(data, lambda x: x['paywallable']['tvod']):
-                        self._raise_error('This video is for rent only or TVOD (Transactional Video On demand)')
-                    self.raise_login_required(message)
-                self._raise_error(message)
-
-    def _perform_login(self, username, password):
-        self._token = self._call_api(
-            'sessions.json', None, 'Logging in', fatal=False,
-            data={'username': username, 'password': password}).get('token')
-        if not self._token:
-            self.report_warning('Login Failed: Unable to get session token')
-
-    @staticmethod
-    def dict_selection(dict_obj, preferred_key):
-        if preferred_key in dict_obj:
-            return dict_obj[preferred_key]
-        return (list(filter(None, dict_obj.values())) or [None])[0]
-
-
-class VikiIE(VikiBaseIE):
-    IE_NAME = 'viki'
-    _VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:videos|player)/(?P<id>[0-9]+v)'
-    _TESTS = [{
-        'note': 'Free non-DRM video with storyboards in MPD',
-        'url': 'https://www.viki.com/videos/1175236v-choosing-spouse-by-lottery-episode-1',
-        'info_dict': {
-            'id': '1175236v',
-            'ext': 'mp4',
-            'title': 'Choosing Spouse by Lottery - Episode 1',
-            'timestamp': 1606463239,
-            'age_limit': 13,
-            'uploader': 'FCC',
-            'upload_date': '20201127',
-        },
-    }, {
-        'url': 'http://www.viki.com/videos/1023585v-heirs-episode-14',
-        'info_dict': {
-            'id': '1023585v',
-            'ext': 'mp4',
-            'title': 'Heirs - Episode 14',
-            'uploader': 'SBS Contents Hub',
-            'timestamp': 1385047627,
-            'upload_date': '20131121',
-            'age_limit': 13,
-            'duration': 3570,
-            'episode_number': 14,
-        },
-        'skip': 'Blocked in the US',
-    }, {
-        # clip
-        'url': 'http://www.viki.com/videos/1067139v-the-avengers-age-of-ultron-press-conference',
-        'md5': '86c0b5dbd4d83a6611a79987cc7a1989',
-        'info_dict': {
-            'id': '1067139v',
-            'ext': 'mp4',
-            'title': "'The Avengers: Age of Ultron' Press Conference",
-            'description': 'md5:d70b2f9428f5488321bfe1db10d612ea',
-            'duration': 352,
-            'timestamp': 1430380829,
-            'upload_date': '20150430',
-            'uploader': 'Arirang TV',
-            'like_count': int,
-            'age_limit': 0,
-        },
-        'skip': 'Sorry. There was an error loading this video',
-    }, {
-        'url': 'http://www.viki.com/videos/1048879v-ankhon-dekhi',
-        'info_dict': {
-            'id': '1048879v',
-            'ext': 'mp4',
-            'title': 'Ankhon Dekhi',
-            'duration': 6512,
-            'timestamp': 1408532356,
-            'upload_date': '20140820',
-            'uploader': 'Spuul',
-            'like_count': int,
-            'age_limit': 13,
-        },
-        'skip': 'Blocked in the US',
-    }, {
-        # episode
-        'url': 'http://www.viki.com/videos/44699v-boys-over-flowers-episode-1',
-        'md5': '0a53dc252e6e690feccd756861495a8c',
-        'info_dict': {
-            'id': '44699v',
-            'ext': 'mp4',
-            'title': 'Boys Over Flowers - Episode 1',
-            'description': 'md5:b89cf50038b480b88b5b3c93589a9076',
-            'duration': 4172,
-            'timestamp': 1270496524,
-            'upload_date': '20100405',
-            'uploader': 'group8',
-            'like_count': int,
-            'age_limit': 13,
-            'episode_number': 1,
-        },
-    }, {
-        # youtube external
-        'url': 'http://www.viki.com/videos/50562v-poor-nastya-complete-episode-1',
-        'md5': '63f8600c1da6f01b7640eee7eca4f1da',
-        'info_dict': {
-            'id': '50562v',
-            'ext': 'webm',
-            'title': 'Poor Nastya [COMPLETE] - Episode 1',
-            'description': '',
-            'duration': 606,
-            'timestamp': 1274949505,
-            'upload_date': '20101213',
-            'uploader': 'ad14065n',
-            'uploader_id': 'ad14065n',
-            'like_count': int,
-            'age_limit': 13,
-        },
-        'skip': 'Page not found!',
-    }, {
-        'url': 'http://www.viki.com/player/44699v',
-        'only_matching': True,
-    }, {
-        # non-English description
-        'url': 'http://www.viki.com/videos/158036v-love-in-magic',
-        'md5': '41faaba0de90483fb4848952af7c7d0d',
-        'info_dict': {
-            'id': '158036v',
-            'ext': 'mp4',
-            'uploader': 'I Planet Entertainment',
-            'upload_date': '20111122',
-            'timestamp': 1321985454,
-            'description': 'md5:44b1e46619df3a072294645c770cef36',
-            'title': 'Love In Magic',
-            'age_limit': 13,
-        },
-    }]
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-        video = self._call_api(f'videos/{video_id}.json', video_id, 'Downloading video JSON', query={})
-        self._check_errors(video)
-
-        title = try_get(video, lambda x: x['titles']['en'], str)
-        episode_number = int_or_none(video.get('number'))
-        if not title:
-            title = f'Episode {episode_number}' if video.get('type') == 'episode' else video.get('id') or video_id
-            container_titles = try_get(video, lambda x: x['container']['titles'], dict) or {}
-            container_title = self.dict_selection(container_titles, 'en')
-            title = f'{container_title} - {title}'
-
-        thumbnails = [{
-            'id': thumbnail_id,
-            'url': thumbnail['url'],
-        } for thumbnail_id, thumbnail in (video.get('images') or {}).items() if thumbnail.get('url')]
-
-        resp = self._call_api(
-            f'playback_streams/{video_id}.json?drms=dt3&device_id={self._DEVICE_ID}',
-            video_id, 'Downloading video streams JSON')['main'][0]
-
-        stream_id = try_get(resp, lambda x: x['properties']['track']['stream_id'])
-        subtitles = dict((lang, [{
-            'ext': ext,
-            'url': self._API_URL_TEMPLATE % self._api_query(
-                f'videos/{video_id}/auth_subtitles/{lang}.{ext}', stream_id=stream_id),
-        } for ext in ('srt', 'vtt')]) for lang in (video.get('subtitle_completions') or {}))
-
-        mpd_url = resp['url']
-        # 720p is hidden in another MPD which can be found in the current manifest content
-        mpd_content = self._download_webpage(mpd_url, video_id, note='Downloading initial MPD manifest')
-        mpd_url = self._search_regex(
-            r'(?mi)<BaseURL>(http.+.mpd)', mpd_content, 'new manifest', default=mpd_url)
-        if 'mpdhd_high' not in mpd_url and 'sig=' not in mpd_url:
-            # Modify the URL to get 1080p
-            mpd_url = mpd_url.replace('mpdhd', 'mpdhd_high')
-        formats = self._extract_mpd_formats(mpd_url, video_id)
-
-        return {
-            'id': video_id,
-            'formats': formats,
-            'title': title,
-            'description': self.dict_selection(video.get('descriptions', {}), 'en'),
-            'duration': int_or_none(video.get('duration')),
-            'timestamp': parse_iso8601(video.get('created_at')),
-            'uploader': video.get('author'),
-            'uploader_url': video.get('author_url'),
-            'like_count': int_or_none(try_get(video, lambda x: x['likes']['count'])),
-            'age_limit': parse_age_limit(video.get('rating')),
-            'thumbnails': thumbnails,
-            'subtitles': subtitles,
-            'episode_number': episode_number,
-        }
-
-
-class VikiChannelIE(VikiBaseIE):
-    IE_NAME = 'viki:channel'
-    _VALID_URL = rf'{VikiBaseIE._VALID_URL_BASE}(?:tv|news|movies|artists)/(?P<id>[0-9]+c)'
-    _TESTS = [{
-        'url': 'http://www.viki.com/tv/50c-boys-over-flowers',
-        'info_dict': {
-            'id': '50c',
-            'title': 'Boys Over Flowers',
-            'description': 'md5:804ce6e7837e1fd527ad2f25420f4d59',
-        },
-        'playlist_mincount': 51,
-    }, {
-        'url': 'http://www.viki.com/tv/1354c-poor-nastya-complete',
-        'info_dict': {
-            'id': '1354c',
-            'title': 'Poor Nastya [COMPLETE]',
-            'description': 'md5:05bf5471385aa8b21c18ad450e350525',
-        },
-        'playlist_count': 127,
-        'skip': 'Page not found',
-    }, {
-        'url': 'http://www.viki.com/news/24569c-showbiz-korea',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.viki.com/movies/22047c-pride-and-prejudice-2005',
-        'only_matching': True,
-    }, {
-        'url': 'http://www.viki.com/artists/2141c-shinee',
-        'only_matching': True,
-    }]
-
-    _video_types = ('episodes', 'movies', 'clips', 'trailers')
-
-    def _entries(self, channel_id):
-        params = {
-            'app': self._APP, 'token': self._token, 'only_ids': 'true',
-            'direction': 'asc', 'sort': 'number', 'per_page': 30,
-        }
-        video_types = self._configuration_arg('video_types') or self._video_types
-        for video_type in video_types:
-            if video_type not in self._video_types:
-                self.report_warning(f'Unknown video_type: {video_type}')
-            page_num = 0
-            while True:
-                page_num += 1
-                params['page'] = page_num
-                res = self._call_api(
-                    f'containers/{channel_id}/{video_type}.json', channel_id, query=params, fatal=False,
-                    note=f'Downloading {video_type.title()} JSON page {page_num}')
-
-                for video_id in res.get('response') or []:
-                    yield self.url_result(f'https://www.viki.com/videos/{video_id}', VikiIE.ie_key(), video_id)
-                if not res.get('more'):
-                    break
-
-    def _real_extract(self, url):
-        channel_id = self._match_id(url)
-        channel = self._call_api(f'containers/{channel_id}.json', channel_id, 'Downloading channel JSON')
-        self._check_errors(channel)
-        return self.playlist_result(
-            self._entries(channel_id), channel_id,
-            self.dict_selection(channel['titles'], 'en'),
-            self.dict_selection(channel['descriptions'], 'en'))

yt_dlp/extractor/vk.py

@@ -544,7 +544,7 @@ class VKIE(VKBaseIE):
                 'uploader_id': (('author_id', 'authorId'), {str_or_none}, any),
                 'duration': ('duration', {int_or_none}),
                 'chapters': ('time_codes', lambda _, v: isinstance(v['time'], int), {
-                    'title': ('text', {str}),
+                    'title': ('text', {unescapeHTML}),
                     'start_time': 'time',
                 }),
             }),

yt_dlp/extractor/vrsquare.py

@@ -0,0 +1,185 @@
+import itertools
+
+from .common import InfoExtractor
+from ..networking.exceptions import HTTPError
+from ..utils import (
+    ExtractorError,
+    clean_html,
+    extract_attributes,
+    parse_duration,
+    parse_qs,
+)
+from ..utils.traversal import (
+    find_element,
+    find_elements,
+    traverse_obj,
+)
+
+
+class VrSquareIE(InfoExtractor):
+    IE_NAME = 'vrsquare'
+    IE_DESC = 'VR SQUARE'
+
+    _BASE_URL = 'https://livr.jp'
+    _VALID_URL = r'https?://livr\.jp/contents/(?P<id>[\w-]+)'
+    _TESTS = [{
+        'url': 'https://livr.jp/contents/P470896661',
+        'info_dict': {
+            'id': 'P470896661',
+            'ext': 'mp4',
+            'title': 'そこ曲がったら、櫻坂？ ７年間お疲れ様！菅井友香の卒業を祝う会！前半 2022年11月6日放送分',
+            'description': 'md5:523726dc835aa8014dfe1e2b38d36cd1',
+            'duration': 1515.0,
+            'tags': 'count:2',
+            'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
+        },
+    }, {
+        'url': 'https://livr.jp/contents/P589523973',
+        'info_dict': {
+            'id': 'P589523973',
+            'ext': 'mp4',
+            'title': '薄闇に仰ぐ しだれ桜の妖艶',
+            'description': 'md5:a042f517b2cbb4ed6746707afec4d306',
+            'duration': 1084.0,
+            'tags': list,
+            'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
+        },
+        'skip': 'Paid video',
+    }, {
+        'url': 'https://livr.jp/contents/P316939908',
+        'info_dict': {
+            'id': 'P316939908',
+            'ext': 'mp4',
+            'title': '2024年5月16日（木） 「今日は誰に恋をする？」公演 小栗有以 生誕祭',
+            'description': 'md5:2110bdcf947f28bd7d06ec420e51b619',
+            'duration': 8559.0,
+            'tags': list,
+            'thumbnail': r're:https?://media\.livr\.jp/vod/img/.+\.jpg',
+        },
+        'skip': 'Premium channel subscribers only',
+    }, {
+        # Accessible only in the VR SQUARE app
+        'url': 'https://livr.jp/contents/P126481458',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        status = self._download_json(
+            f'{self._BASE_URL}/webApi/contentsStatus/{video_id}',
+            video_id, 'Checking contents status', fatal=False)
+        if traverse_obj(status, 'result_code') == '40407':
+            self.raise_login_required('Unable to access this video')
+
+        try:
+            web_api = self._download_json(
+                f'{self._BASE_URL}/webApi/play/url/{video_id}', video_id)
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 500:
+                raise ExtractorError('VR SQUARE app-only videos are not supported', expected=True)
+            raise
+
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'description': self._html_search_meta('description', webpage),
+            'formats': self._extract_m3u8_formats(traverse_obj(web_api, (
+                'urls', ..., 'url', any)), video_id, 'mp4', fatal=False),
+            'thumbnail': self._html_search_meta('og:image', webpage),
+            **traverse_obj(webpage, {
+                'duration': ({find_element(cls='layout-product-data-time')}, {parse_duration}),
+                'tags': ({find_elements(cls='search-tag')}, ..., {clean_html}),
+            }),
+        }
+
+
+class VrSquarePlaylistBaseIE(InfoExtractor):
+    _BASE_URL = 'https://livr.jp'
+
+    def _fetch_vids(self, source, keys=()):
+        for url_path in traverse_obj(source, (
+            *keys, {find_elements(cls='video', html=True)}, ...,
+            {extract_attributes}, 'data-url', {str}, filter),
+        ):
+            yield self.url_result(
+                f'{self._BASE_URL}/contents/{url_path.removeprefix("/contents/")}', VrSquareIE)
+
+    def _entries(self, path, display_id, query=None):
+        for page in itertools.count(1):
+            ajax = self._download_json(
+                f'{self._BASE_URL}{path}', display_id,
+                f'Downloading playlist JSON page {page}',
+                query={'p': page, **(query or {})})
+            yield from self._fetch_vids(ajax, ('contents_render_list', ...))
+            if not traverse_obj(ajax, (('has_next', 'hasNext'), {bool}, any)):
+                break
+
+
+class VrSquareChannelIE(VrSquarePlaylistBaseIE):
+    IE_NAME = 'vrsquare:channel'
+
+    _VALID_URL = r'https?://livr\.jp/channel/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://livr.jp/channel/H372648599',
+        'info_dict': {
+            'id': 'H372648599',
+            'title': 'AKB48＋チャンネル',
+        },
+        'playlist_mincount': 502,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        return self.playlist_result(
+            self._entries(f'/ajax/channel/{playlist_id}', playlist_id),
+            playlist_id, self._html_search_meta('og:title', webpage))
+
+
+class VrSquareSearchIE(VrSquarePlaylistBaseIE):
+    IE_NAME = 'vrsquare:search'
+
+    _VALID_URL = r'https?://livr\.jp/web-search/?\?(?:[^#]+&)?w=[^#]+'
+    _TESTS = [{
+        'url': 'https://livr.jp/web-search?w=%23%E5%B0%8F%E6%A0%97%E6%9C%89%E4%BB%A5',
+        'info_dict': {
+            'id': '#小栗有以',
+        },
+        'playlist_mincount': 60,
+    }]
+
+    def _real_extract(self, url):
+        search_query = parse_qs(url)['w'][0]
+
+        return self.playlist_result(
+            self._entries('/ajax/web-search', search_query, {'w': search_query}), search_query)
+
+
+class VrSquareSectionIE(VrSquarePlaylistBaseIE):
+    IE_NAME = 'vrsquare:section'
+
+    _VALID_URL = r'https?://livr\.jp/(?:category|headline)/(?P<id>\w+)'
+    _TESTS = [{
+        'url': 'https://livr.jp/category/C133936275',
+        'info_dict': {
+            'id': 'C133936275',
+            'title': 'そこ曲がったら、櫻坂？VR',
+        },
+        'playlist_mincount': 308,
+    }, {
+        'url': 'https://livr.jp/headline/A296449604',
+        'info_dict': {
+            'id': 'A296449604',
+            'title': 'AKB48 アフターVR',
+        },
+        'playlist_mincount': 22,
+    }]
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+        webpage = self._download_webpage(url, playlist_id)
+
+        return self.playlist_result(
+            self._fetch_vids(webpage), playlist_id, self._html_search_meta('og:title', webpage))

yt_dlp/extractor/wykop.py

@@ -11,7 +11,7 @@ from ..utils import (
 )
 
 
-class WykopBaseExtractor(InfoExtractor):
+class WykopBaseIE(InfoExtractor):
     def _get_token(self, force_refresh=False):
         if not force_refresh:
             maybe_cached = self.cache.load('wykop', 'bearer')
@@ -72,7 +72,7 @@ class WykopBaseExtractor(InfoExtractor):
         }
 
 
-class WykopDigIE(WykopBaseExtractor):
+class WykopDigIE(WykopBaseIE):
     IE_NAME = 'wykop:dig'
     _VALID_URL = r'https?://(?:www\.)?wykop\.pl/link/(?P<id>\d+)'
 
@@ -128,7 +128,7 @@ class WykopDigIE(WykopBaseExtractor):
         }
 
 
-class WykopDigCommentIE(WykopBaseExtractor):
+class WykopDigCommentIE(WykopBaseIE):
     IE_NAME = 'wykop:dig:comment'
     _VALID_URL = r'https?://(?:www\.)?wykop\.pl/link/(?P<dig_id>\d+)/[^/]+/komentarz/(?P<id>\d+)'
 
@@ -177,7 +177,7 @@ class WykopDigCommentIE(WykopBaseExtractor):
         }
 
 
-class WykopPostIE(WykopBaseExtractor):
+class WykopPostIE(WykopBaseIE):
     IE_NAME = 'wykop:post'
     _VALID_URL = r'https?://(?:www\.)?wykop\.pl/wpis/(?P<id>\d+)'
 
@@ -228,7 +228,7 @@ class WykopPostIE(WykopBaseExtractor):
         }
 
 
-class WykopPostCommentIE(WykopBaseExtractor):
+class WykopPostCommentIE(WykopBaseIE):
     IE_NAME = 'wykop:post:comment'
     _VALID_URL = r'https?://(?:www\.)?wykop\.pl/wpis/(?P<post_id>\d+)/[^/#]+#(?P<id>\d+)'
 

yt_dlp/extractor/yandexvideo.py

@@ -2,15 +2,17 @@ import itertools
 
 from .common import InfoExtractor
 from ..utils import (
+    bug_reports_message,
     determine_ext,
-    extract_attributes,
     int_or_none,
     lowercase_escape,
     parse_qs,
-    traverse_obj,
+    qualities,
     try_get,
+    update_url_query,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class YandexVideoIE(InfoExtractor):
@@ -186,7 +188,22 @@ class YandexVideoPreviewIE(InfoExtractor):
         return self.url_result(data_json['video']['url'])
 
 
-class ZenYandexIE(InfoExtractor):
+class ZenYandexBaseIE(InfoExtractor):
+    def _fetch_ssr_data(self, url, video_id):
+        webpage = self._download_webpage(url, video_id)
+        redirect = self._search_json(
+            r'(?:var|let|const)\s+it\s*=', webpage, 'redirect', video_id, default={}).get('retpath')
+        if redirect:
+            video_id = self._match_id(redirect)
+            webpage = self._download_webpage(redirect, video_id, note='Redirecting')
+        return video_id, self._search_json(
+            r'(?:var|let|const)\s+_params\s*=\s*\(', webpage, 'metadata', video_id,
+            contains_pattern=r'{["\']ssrData.+}')['ssrData']
+
+
+class ZenYandexIE(ZenYandexBaseIE):
+    IE_NAME = 'dzen.ru'
+    IE_DESC = 'Дзен (dzen) formerly Яндекс.Дзен (Yandex Zen)'
     _VALID_URL = r'https?://(zen\.yandex|dzen)\.ru(?:/video)?/(media|watch)/(?:(?:id/[^/]+/|[^/]+/)(?:[a-z0-9-]+)-)?(?P<id>[a-z0-9-]+)'
     _TESTS = [{
         'url': 'https://zen.yandex.ru/media/id/606fd806cc13cb3c58c05cf5/vot-eto-focus-dedy-morozy-na-gidrociklah-60c7c443da18892ebfe85ed7',
@@ -216,6 +233,7 @@ class ZenYandexIE(InfoExtractor):
             'timestamp': 1573465585,
         },
         'params': {'skip_download': 'm3u8'},
+        'skip': 'The page does not exist',
     }, {
         'url': 'https://zen.yandex.ru/video/watch/6002240ff8b1af50bb2da5e3',
         'info_dict': {
@@ -227,6 +245,9 @@ class ZenYandexIE(InfoExtractor):
             'uploader': 'TechInsider',
             'timestamp': 1611378221,
             'upload_date': '20210123',
+            'view_count': int,
+            'duration': 243,
+            'tags': ['опыт', 'эксперимент', 'огонь'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -240,6 +261,9 @@ class ZenYandexIE(InfoExtractor):
             'uploader': 'TechInsider',
             'upload_date': '20210123',
             'timestamp': 1611378221,
+            'view_count': int,
+            'duration': 243,
+            'tags': ['опыт', 'эксперимент', 'огонь'],
         },
         'params': {'skip_download': 'm3u8'},
     }, {
@@ -252,44 +276,56 @@ class ZenYandexIE(InfoExtractor):
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(url, video_id)
+        video_id, ssr_data = self._fetch_ssr_data(url, video_id)
-        redirect = self._search_json(r'var it\s*=', webpage, 'redirect', id, default={}).get('retpath')
+        video_data = ssr_data['videoMetaResponse']
-        if redirect:
-            video_id = self._match_id(redirect)
-            webpage = self._download_webpage(redirect, video_id, note='Redirecting')
-        data_json = self._search_json(
-            r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
-        serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)', webpage, 'server state')
-        uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
-                                      webpage, 'uploader', default='<a>')
-        uploader_name = extract_attributes(uploader).get('aria-label')
-        item_id = traverse_obj(data_json, (serverstate, 'videoViewer', 'openedItemId', {str}))
-        video_json = traverse_obj(data_json, (serverstate, 'videoViewer', 'items', item_id, {dict})) or {}
 
         formats, subtitles = [], {}
-        for s_url in traverse_obj(video_json, ('video', 'streams', ..., {url_or_none})):
+        quality = qualities(('4', '0', '1', '2', '3', '5', '6', '7'))
+        # Deduplicate stream URLs. The "dzen_dash" query parameter is present in some URLs but can be omitted
+        stream_urls = set(traverse_obj(video_data, (
+            'video', ('id', ('streams', ...), ('mp4Streams', ..., 'url'), ('oneVideoStreams', ..., 'url')),
+            {url_or_none}, {update_url_query(query={'dzen_dash': []})})))
+        for s_url in stream_urls:
             ext = determine_ext(s_url)
-            if ext == 'mpd':
+            content_type = traverse_obj(parse_qs(s_url), ('ct', 0))
-                fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')
+            if ext == 'mpd' or content_type == '6':
-            elif ext == 'm3u8':
+                fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash', fatal=False)
-                fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4')
+            elif ext == 'm3u8' or content_type == '8':
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
+            elif content_type == '0':
+                format_type = traverse_obj(parse_qs(s_url), ('type', 0))
+                formats.append({
+                    'url': s_url,
+                    'format_id': format_type,
+                    'ext': 'mp4',
+                    'quality': quality(format_type),
+                })
+                continue
+            else:
+                self.report_warning(f'Unsupported stream URL: {s_url}{bug_reports_message()}')
+                continue
             formats.extend(fmts)
-            subtitles = self._merge_subtitles(subtitles, subs)
+            self._merge_subtitles(subs, target=subtitles)
+
         return {
             'id': video_id,
-            'title': video_json.get('title') or self._og_search_title(webpage),
             'formats': formats,
             'subtitles': subtitles,
-            'duration': int_or_none(video_json.get('duration')),
+            **traverse_obj(video_data, {
-            'view_count': int_or_none(video_json.get('views')),
+                'title': ('title', {str}),
-            'timestamp': int_or_none(video_json.get('publicationDate')),
+                'description': ('description', {str}),
-            'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']),
+                'thumbnail': ('image', {url_or_none}),
-            'description': video_json.get('description') or self._og_search_description(webpage),
+                'duration': ('video', 'duration', {int_or_none}),
-            'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']),
+                'view_count': ('video', 'views', {int_or_none}),
+                'timestamp': ('publicationDate', {int_or_none}),
+                'tags': ('tags', ..., {str}),
+                'uploader': ('source', 'title', {str}),
+            }),
         }
 
 
-class ZenYandexChannelIE(InfoExtractor):
+class ZenYandexChannelIE(ZenYandexBaseIE):
+    IE_NAME = 'dzen.ru:channel'
     _VALID_URL = r'https?://(zen\.yandex|dzen)\.ru/(?!media|video)(?:id/)?(?P<id>[a-z0-9-_]+)'
     _TESTS = [{
         'url': 'https://zen.yandex.ru/tok_media',
@@ -323,8 +359,8 @@ class ZenYandexChannelIE(InfoExtractor):
         'url': 'https://zen.yandex.ru/jony_me',
         'info_dict': {
             'id': 'jony_me',
-            'description': 'md5:ce0a5cad2752ab58701b5497835b2cc5',
+            'description': 'md5:7c30d11dc005faba8826feae99da3113',
-            'title': 'JONY ',
+            'title': 'JONY',
         },
         'playlist_count': 18,
     }, {
@@ -333,9 +369,8 @@ class ZenYandexChannelIE(InfoExtractor):
         'url': 'https://zen.yandex.ru/tatyanareva',
         'info_dict': {
             'id': 'tatyanareva',
-            'description': 'md5:40a1e51f174369ec3ba9d657734ac31f',
+            'description': 'md5:92e56fa730a932ca2483ba5c2186ad96',
             'title': 'Татьяна Рева',
-            'entries': 'maxcount:200',
         },
         'playlist_mincount': 46,
     }, {
@@ -348,43 +383,31 @@ class ZenYandexChannelIE(InfoExtractor):
         'playlist_mincount': 657,
     }]
 
-    def _entries(self, item_id, server_state_json, server_settings_json):
+    def _entries(self, feed_data, channel_id):
-        items = (traverse_obj(server_state_json, ('feed', 'items', ...))
-                 or traverse_obj(server_settings_json, ('exportData', 'items', ...)))
-
-        more = (traverse_obj(server_state_json, ('links', 'more'))
-                or traverse_obj(server_settings_json, ('exportData', 'more', 'link')))
-
         next_page_id = None
         for page in itertools.count(1):
-            for item in items or []:
+            for item in traverse_obj(feed_data, (
-                if item.get('type') != 'gif':
+                (None, ('items', lambda _, v: v['tab'] in ('shorts', 'longs'))),
-                    continue
+                'items', lambda _, v: url_or_none(v['link']),
-                video_id = traverse_obj(item, 'publication_id', 'publicationId') or ''
+            )):
-                yield self.url_result(item['link'], ZenYandexIE, video_id.split(':')[-1])
+                yield self.url_result(item['link'], ZenYandexIE, item.get('id'), title=item.get('title'))
 
+            more = traverse_obj(feed_data, ('more', 'link', {url_or_none}))
             current_page_id = next_page_id
             next_page_id = traverse_obj(parse_qs(more), ('next_page_id', -1))
-            if not all((more, items, next_page_id, next_page_id != current_page_id)):
+            if not all((more, next_page_id, next_page_id != current_page_id)):
                 break
 
-            data = self._download_json(more, item_id, note=f'Downloading Page {page}')
+            feed_data = self._download_json(more, channel_id, note=f'Downloading Page {page}')
-            items, more = data.get('items'), traverse_obj(data, ('more', 'link'))
 
     def _real_extract(self, url):
-        item_id = self._match_id(url)
+        channel_id = self._match_id(url)
-        webpage = self._download_webpage(url, item_id)
+        channel_id, ssr_data = self._fetch_ssr_data(url, channel_id)
-        redirect = self._search_json(
+        channel_data = ssr_data['exportResponse']
-            r'var it\s*=', webpage, 'redirect', item_id, default={}).get('retpath')
-        if redirect:
-            item_id = self._match_id(redirect)
-            webpage = self._download_webpage(redirect, item_id, note='Redirecting')
-        data = self._search_json(
-            r'("data"\s*:|data\s*=)', webpage, 'channel data', item_id, contains_pattern=r'{\"__serverState__.+}')
-        server_state_json = traverse_obj(data, lambda k, _: k.startswith('__serverState__'), get_all=False)
-        server_settings_json = traverse_obj(data, lambda k, _: k.startswith('__serverSettings__'), get_all=False)
 
         return self.playlist_result(
-            self._entries(item_id, server_state_json, server_settings_json),
+            self._entries(channel_data['feedData'], channel_id),
-            item_id, traverse_obj(server_state_json, ('channel', 'source', 'title')),
+            channel_id, **traverse_obj(channel_data, ('channel', 'source', {
-            traverse_obj(server_state_json, ('channel', 'source', 'description')))
+                'title': ('title', {str}),
+                'description': ('description', {str}),
+            })))

yt_dlp/extractor/youporn.py

@@ -227,7 +227,7 @@ class YouPornIE(InfoExtractor):
         return result
 
 
-class YouPornListBase(InfoExtractor):
+class YouPornListBaseIE(InfoExtractor):
     def _get_next_url(self, url, pl_id, html):
         return urljoin(url, self._search_regex(
             r'''<a [^>]*?\bhref\s*=\s*("|')(?P<url>(?:(?!\1)[^>])+)\1''',
@@ -284,7 +284,7 @@ class YouPornListBase(InfoExtractor):
             playlist_id=pl_id, playlist_title=title)
 
 
-class YouPornCategoryIE(YouPornListBase):
+class YouPornCategoryIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn category, with sorting, filtering and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/
@@ -319,7 +319,7 @@ class YouPornCategoryIE(YouPornListBase):
     }]
 
 
-class YouPornChannelIE(YouPornListBase):
+class YouPornChannelIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn channel, with sorting and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/
@@ -349,7 +349,7 @@ class YouPornChannelIE(YouPornListBase):
         return re.sub(r'_', ' ', title_slug).title()
 
 
-class YouPornCollectionIE(YouPornListBase):
+class YouPornCollectionIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn collection (user playlist), with sorting and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/
@@ -394,7 +394,7 @@ class YouPornCollectionIE(YouPornListBase):
         return playlist
 
 
-class YouPornTagIE(YouPornListBase):
+class YouPornTagIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn tag (porntags), with sorting, filtering and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/
@@ -442,7 +442,7 @@ class YouPornTagIE(YouPornListBase):
         return super()._real_extract(url)
 
 
-class YouPornStarIE(YouPornListBase):
+class YouPornStarIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn Pornstar, with description, sorting and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/
@@ -493,7 +493,7 @@ class YouPornStarIE(YouPornListBase):
         }
 
 
-class YouPornVideosIE(YouPornListBase):
+class YouPornVideosIE(YouPornListBaseIE):
     IE_DESC = 'YouPorn video (browse) playlists, with sorting, filtering and pagination'
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?youporn\.com/

yt_dlp/extractor/youtube/_base.py

@@ -803,12 +803,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
 
     @classmethod
     def _extract_continuation_ep_data(cls, continuation_ep: dict):
-        if isinstance(continuation_ep, dict):
+        continuation_commands = traverse_obj(
-            continuation = try_get(
+            continuation_ep, ('commandExecutorCommand', 'commands', ..., {dict}))
-                continuation_ep, lambda x: x['continuationCommand']['token'], str)
+        continuation_commands.append(continuation_ep)
+        for command in continuation_commands:
+            continuation = traverse_obj(command, ('continuationCommand', 'token', {str}))
             if not continuation:
-                return
+                continue
-            ctp = continuation_ep.get('clickTrackingParams')
+            ctp = command.get('clickTrackingParams')
             return cls._build_api_continuation_query(continuation, ctp)
 
     @classmethod

yt_dlp/extractor/youtube/_tab.py

@@ -524,10 +524,16 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
             response = self._extract_response(
                 item_id=f'{item_id} page {page_num}',
                 query=continuation, headers=headers, ytcfg=ytcfg,
-                check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
+                check_get_keys=(
+                    'continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints',
+                    # Playlist recommendations may return with no data - ignore
+                    ('responseContext', 'serviceTrackingParams', ..., 'params', ..., lambda k, v: k == 'key' and v == 'GetRecommendedMusicPlaylists_rid'),
+                ))
 
             if not response:
                 break
+
+            continuation = None
             # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
             # See: https://github.com/ytdl-org/youtube-dl/issues/28702
             visitor_data = self._extract_visitor_data(response) or visitor_data
@@ -564,7 +570,13 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                 yield from func(video_items_renderer)
                 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
 
-            if not video_items_renderer:
+            # In the case only a continuation is returned, try to follow it.
+            # We extract this after trying to extract non-continuation items as otherwise this
+            # may be prioritized over other continuations.
+            # see: https://github.com/yt-dlp/yt-dlp/issues/12933
+            continuation = continuation or self._extract_continuation({'contents': [continuation_item]})
+
+            if not continuation and not video_items_renderer:
                 break
 
     @staticmethod
@@ -999,14 +1011,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 94,
         'info_dict': {
             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
-            'title': 'Igor Kleiner Ph.D. - Playlists',
+            'title': 'Igor Kleiner  - Playlists',
             'description': 'md5:15d7dd9e333cb987907fcb0d604b233a',
-            'uploader': 'Igor Kleiner Ph.D.',
+            'uploader': 'Igor Kleiner ',
             'uploader_id': '@IgorDataScience',
             'uploader_url': 'https://www.youtube.com/@IgorDataScience',
-            'channel': 'Igor Kleiner Ph.D.',
+            'channel': 'Igor Kleiner ',
             'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
-            'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'],
+            'tags': 'count:23',
             'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
             'channel_follower_count': int,
         },
@@ -1016,18 +1028,19 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 94,
         'info_dict': {
             'id': 'UCqj7Cz7revf5maW9g5pgNcg',
-            'title': 'Igor Kleiner Ph.D. - Playlists',
+            'title': 'Igor Kleiner  - Playlists',
             'description': 'md5:15d7dd9e333cb987907fcb0d604b233a',
-            'uploader': 'Igor Kleiner Ph.D.',
+            'uploader': 'Igor Kleiner ',
             'uploader_id': '@IgorDataScience',
             'uploader_url': 'https://www.youtube.com/@IgorDataScience',
-            'tags': ['критическое мышление', 'наука просто', 'математика', 'анализ данных'],
+            'tags': 'count:23',
             'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
-            'channel': 'Igor Kleiner Ph.D.',
+            'channel': 'Igor Kleiner ',
             'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
             'channel_follower_count': int,
         },
     }, {
+        # TODO: fix channel_is_verified extraction
         'note': 'playlists, series',
         'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
         'playlist_mincount': 5,
@@ -1066,22 +1079,23 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
         'only_matching': True,
     }, {
+        # TODO: fix availability extraction
         'note': 'basic, single video playlist',
-        'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
+        'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlSLRHmI1qNm0wjyVNWw1pCU',
         'info_dict': {
-            'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
+            'id': 'PLt5yu3-wZAlSLRHmI1qNm0wjyVNWw1pCU',
-            'title': 'youtube-dl public playlist',
+            'title': 'single video playlist',
             'description': '',
             'tags': [],
             'view_count': int,
-            'modified_date': '20201130',
+            'modified_date': '20250417',
-            'channel': 'Sergey M.',
+            'channel': 'cole-dlp-test-acc',
-            'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
+            'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
-            'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
+            'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
             'availability': 'public',
-            'uploader': 'Sergey M.',
+            'uploader': 'cole-dlp-test-acc',
-            'uploader_url': 'https://www.youtube.com/@sergeym.6173',
+            'uploader_url': 'https://www.youtube.com/@coletdjnz',
-            'uploader_id': '@sergeym.6173',
+            'uploader_id': '@coletdjnz',
         },
         'playlist_count': 1,
     }, {
@@ -1171,11 +1185,11 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'playlist_mincount': 17,
     }, {
-        'note': 'Community tab',
+        'note': 'Posts tab',
         'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
         'info_dict': {
             'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
-            'title': 'lex will - Community',
+            'title': 'lex will - Posts',
             'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
             'channel': 'lex will',
             'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
@@ -1188,30 +1202,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'playlist_mincount': 18,
     }, {
-        'note': 'Channels tab',
+        # TODO: fix channel_is_verified extraction
-        'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
-        'info_dict': {
-            'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
-            'title': 'lex will - Channels',
-            'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
-            'channel': 'lex will',
-            'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
-            'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
-            'tags': ['bible', 'history', 'prophesy'],
-            'channel_follower_count': int,
-            'uploader_url': 'https://www.youtube.com/@lexwill718',
-            'uploader_id': '@lexwill718',
-            'uploader': 'lex will',
-        },
-        'playlist_mincount': 12,
-    }, {
         'note': 'Search tab',
         'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
         'playlist_mincount': 40,
         'info_dict': {
             'id': 'UCYO_jab_esuFRV4b17AJtAw',
             'title': '3Blue1Brown - Search - linear algebra',
-            'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9',
+            'description': 'md5:602e3789e6a0cb7d9d352186b720e395',
             'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
             'tags': ['Mathematics'],
             'channel': '3Blue1Brown',
@@ -1232,6 +1230,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
         'only_matching': True,
     }, {
+        # TODO: fix availability extraction
         'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
         'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
         'info_dict': {
@@ -1294,24 +1293,25 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'playlist_mincount': 21,
     }, {
+        # TODO: fix availability extraction
         'note': 'Playlist with "show unavailable videos" button',
-        'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
+        'url': 'https://www.youtube.com/playlist?list=PLYwq8WOe86_xGmR7FrcJq8Sb7VW8K3Tt2',
         'info_dict': {
-            'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
+            'title': 'The Memes Of 2010s.....',
-            'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
+            'id': 'PLYwq8WOe86_xGmR7FrcJq8Sb7VW8K3Tt2',
             'view_count': int,
-            'channel': 'Phim Siêu Nhân Nhật Bản',
+            'channel': "I'm Not JiNxEd",
             'tags': [],
-            'description': '',
+            'description': 'md5:44dc3b315ba69394feaafa2f40e7b2a1',
-            'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
+            'channel_url': 'https://www.youtube.com/channel/UC5H5H85D1QE5-fuWWQ1hdNg',
-            'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
+            'channel_id': 'UC5H5H85D1QE5-fuWWQ1hdNg',
             'modified_date': r're:\d{8}',
             'availability': 'public',
-            'uploader_url': 'https://www.youtube.com/@phimsieunhannhatban',
+            'uploader_url': 'https://www.youtube.com/@imnotjinxed1998',
-            'uploader_id': '@phimsieunhannhatban',
+            'uploader_id': '@imnotjinxed1998',
-            'uploader': 'Phim Siêu Nhân Nhật Bản',
+            'uploader': "I'm Not JiNxEd",
         },
-        'playlist_mincount': 200,
+        'playlist_mincount': 150,
         'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
     }, {
         'note': 'Playlist with unavailable videos in page 7',
@@ -1334,6 +1334,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 1000,
         'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
     }, {
+        # TODO: fix availability extraction
         'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
         'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
         'info_dict': {
@@ -1384,7 +1385,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
     }, {
         'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
         'info_dict': {
-            'id': 'hGkQjiJLjWQ',  # This will keep changing
+            'id': 'YDvsBbKfLPA',  # This will keep changing
             'ext': 'mp4',
             'title': str,
             'upload_date': r're:\d{8}',
@@ -1409,6 +1410,8 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             'uploader_id': '@SkyNews',
             'uploader': 'Sky News',
             'channel_is_verified': True,
+            'media_type': 'livestream',
+            'timestamp': int,
         },
         'params': {
             'skip_download': True,
@@ -1496,6 +1499,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
         'only_matching': True,
     }, {
+        # TODO: fix availability extraction
         'note': 'VLPL, should redirect to playlist?list=PL...',
         'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
         'info_dict': {
@@ -1537,6 +1541,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
     }, {
         # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
         # Treat as a general feed
+        # TODO: fix extraction
         'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
         'info_dict': {
             'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
@@ -1560,21 +1565,21 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'expected_warnings': ['YouTube Music is not directly supported'],
     }, {
         'note': 'unlisted single video playlist',
-        'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
+        'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQLfIN0MMgp0wVV6MP3bM4_',
         'info_dict': {
-            'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
+            'id': 'PLt5yu3-wZAlQLfIN0MMgp0wVV6MP3bM4_',
-            'title': 'yt-dlp unlisted playlist test',
+            'title': 'unlisted playlist',
             'availability': 'unlisted',
             'tags': [],
-            'modified_date': '20220418',
+            'modified_date': '20250417',
-            'channel': 'colethedj',
+            'channel': 'cole-dlp-test-acc',
             'view_count': int,
             'description': '',
-            'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
+            'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
-            'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
+            'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
-            'uploader_url': 'https://www.youtube.com/@colethedj1894',
+            'uploader_url': 'https://www.youtube.com/@coletdjnz',
-            'uploader_id': '@colethedj1894',
+            'uploader_id': '@coletdjnz',
-            'uploader': 'colethedj',
+            'uploader': 'cole-dlp-test-acc',
         },
         'playlist': [{
             'info_dict': {
@@ -1596,6 +1601,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_count': 1,
         'params': {'extract_flat': True},
     }, {
+        # By default, recommended is always empty.
         'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
         'url': 'https://www.youtube.com/feed/recommended',
         'info_dict': {
@@ -1603,7 +1609,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             'title': 'recommended',
             'tags': [],
         },
-        'playlist_mincount': 50,
+        'playlist_count': 0,
         'params': {
             'skip_download': True,
             'extractor_args': {'youtubetab': {'skip': ['webpage']}},
@@ -1628,6 +1634,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         },
         'skip': 'Query for sorting no longer works',
     }, {
+        # TODO: fix 'unviewable' issue with this playlist when reloading with unavailable videos
         'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
         'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
         'info_dict': {
@@ -1654,11 +1661,12 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
         'only_matching': True,
     }, {
+        # TODO: fix metadata extraction
         'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
         'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
         'info_dict': {
             'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
-            'modified_date': '20220407',
+            'modified_date': '20250115',
             'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
             'tags': [],
             'availability': 'unlisted',
@@ -1692,6 +1700,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'expected_warnings': ['Preferring "ja"'],
     }, {
         # XXX: this should really check flat playlist entries, but the test suite doesn't support that
+        # TODO: fix availability extraction
         'note': 'preferred lang set with playlist with translated video titles',
         'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
         'info_dict': {
@@ -1714,6 +1723,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
     }, {
         # shorts audio pivot for 2GtVksBMYFM.
         'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
+        # TODO: fix extraction
         'info_dict': {
             'id': 'sfv_audio_pivot',
             'title': 'sfv_audio_pivot',
@@ -1751,6 +1761,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 8,
     }, {
         # Should get three playlists for videos, shorts and streams tabs
+        # TODO: fix channel_is_verified extraction
         'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
         'info_dict': {
             'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
@@ -1758,7 +1769,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             'channel_follower_count': int,
             'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
             'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
-            'description': 'md5:49809d8bf9da539bc48ed5d1f83c33f2',
+            'description': 'md5:01e53f350ab8ad6fcf7c4fedb3c1b99f',
             'channel': 'Polka Ch. 尾丸ポルカ',
             'tags': 'count:35',
             'uploader_url': 'https://www.youtube.com/@OmaruPolka',
@@ -1769,14 +1780,14 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_count': 3,
     }, {
         # Shorts tab with channel with handle
-        # TODO: fix channel description
+        # TODO: fix channel_is_verified extraction
         'url': 'https://www.youtube.com/@NotJustBikes/shorts',
         'info_dict': {
             'id': 'UC0intLFzLaudFG-xAvUEO-A',
             'title': 'Not Just Bikes - Shorts',
             'tags': 'count:10',
             'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
-            'description': 'md5:5e82545b3a041345927a92d0585df247',
+            'description': 'md5:1d9fc1bad7f13a487299d1fe1712e031',
             'channel_follower_count': int,
             'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
             'channel': 'Not Just Bikes',
@@ -1797,7 +1808,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
             'channel': '中村悠一',
             'channel_follower_count': int,
-            'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
+            'description': 'md5:e8fd705073a594f27d6d6d020da560dc',
             'uploader_url': 'https://www.youtube.com/@Yuichi-Nakamura',
             'uploader_id': '@Yuichi-Nakamura',
             'uploader': '中村悠一',
@@ -1815,6 +1826,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'only_matching': True,
     }, {
         # No videos tab but has a shorts tab
+        # TODO: fix metadata extraction
         'url': 'https://www.youtube.com/c/TKFShorts',
         'info_dict': {
             'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
@@ -1851,6 +1863,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
     }, {
         # Shorts url result in shorts tab
         # TODO: Fix channel id extraction
+        # TODO: fix test suite, 208163447408c78673b08c172beafe5c310fb167 broke this test
         'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
         'info_dict': {
             'id': 'UCiu-3thuViMebBjw_5nWYrA',
@@ -1879,6 +1892,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'params': {'extract_flat': True},
     }, {
         # Live video status should be extracted
+        # TODO: fix test suite, 208163447408c78673b08c172beafe5c310fb167 broke this test
         'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
         'info_dict': {
             'id': 'UCQvWX73GQygcwXOTSf_VDVg',
@@ -1907,6 +1921,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 1,
     }, {
         # Channel renderer metadata. Contains number of videos on the channel
+        # TODO: channels tab removed, change this test to use another page with channel renderer
         'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
         'info_dict': {
             'id': 'UCiu-3thuViMebBjw_5nWYrA',
@@ -1940,7 +1955,9 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             },
         }],
         'params': {'extract_flat': True},
+        'skip': 'channels tab removed',
     }, {
+        # TODO: fix channel_is_verified extraction
         'url': 'https://www.youtube.com/@3blue1brown/about',
         'info_dict': {
             'id': '@3blue1brown',
@@ -1950,7 +1967,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
             'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
             'channel': '3Blue1Brown',
             'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
-            'description': 'md5:4d1da95432004b7ba840ebc895b6b4c9',
+            'description': 'md5:602e3789e6a0cb7d9d352186b720e395',
             'uploader_url': 'https://www.youtube.com/@3blue1brown',
             'uploader_id': '@3blue1brown',
             'uploader': '3Blue1Brown',
@@ -1976,6 +1993,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_count': 5,
     }, {
         # Releases tab, with rich entry playlistRenderers (same as Podcasts tab)
+        # TODO: fix channel_is_verified extraction
         'url': 'https://www.youtube.com/@AHimitsu/releases',
         'info_dict': {
             'id': 'UCgFwu-j5-xNJml2FtTrrB3A',
@@ -2015,6 +2033,7 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
         'playlist_mincount': 100,
         'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
     }, {
+        # TODO: fix channel_is_verified extraction
         'note': 'Tags containing spaces',
         'url': 'https://www.youtube.com/channel/UC7_YxT-KID8kRbqZo7MyscQ',
         'playlist_count': 3,
@@ -2035,6 +2054,24 @@ class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
                      'challenges', 'sketches', 'scary games', 'funny games', 'rage games',
                      'mark fischbach'],
         },
+    }, {
+        # https://github.com/yt-dlp/yt-dlp/issues/12933
+        'note': 'streams tab, some scheduled streams. Empty intermediate response with only continuation - must follow',
+        'url': 'https://www.youtube.com/@sbcitygov/streams',
+        'playlist_mincount': 150,
+        'info_dict': {
+            'id': 'UCH6-qfQwlUgz9SAf05jvc_w',
+            'channel': 'sbcitygov',
+            'channel_id': 'UCH6-qfQwlUgz9SAf05jvc_w',
+            'title': 'sbcitygov - Live',
+            'channel_follower_count': int,
+            'description': 'md5:ca1a92059835c071e33b3db52f4a6d67',
+            'uploader_id': '@sbcitygov',
+            'uploader_url': 'https://www.youtube.com/@sbcitygov',
+            'uploader': 'sbcitygov',
+            'channel_url': 'https://www.youtube.com/channel/UCH6-qfQwlUgz9SAf05jvc_w',
+            'tags': [],
+        },
     }]
 
     @classmethod

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
@@ -34,6 +36,7 @@ from ...utils import (
     clean_html,
     datetime_from_str,
     filesize_from_tbr,
+    filter_dict,
     float_or_none,
     format_field,
     get_first,
@@ -65,6 +68,7 @@ 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'
@@ -1760,6 +1764,16 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         },
     ]
 
+    _PLAYER_JS_VARIANT_MAP = {
+        'main': 'player_ias.vflset/en_US/base.js',
+        'tce': 'player_ias_tce.vflset/en_US/base.js',
+        'tv': 'tv-player-ias.vflset/tv-player-ias.js',
+        'tv_es6': 'tv-player-es6.vflset/tv-player-es6.js',
+        'phone': 'player-plasma-ias-phone-en_US.vflset/base.js',
+        'tablet': 'player-plasma-ias-tablet-en_US.vflset/base.js',
+    }
+    _INVERSE_PLAYER_JS_VARIANT_MAP = {v: k for k, v in _PLAYER_JS_VARIANT_MAP.items()}
+
     @classmethod
     def suitable(cls, url):
         from yt_dlp.utils import parse_qs
@@ -1773,6 +1787,11 @@ 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()
@@ -1939,6 +1958,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             get_all=False, expected_type=str)
         if not player_url:
             return
+
+        requested_js_variant = self._configuration_arg('player_js_variant', [''])[0] or 'actual'
+        if requested_js_variant in self._PLAYER_JS_VARIANT_MAP:
+            player_id = self._extract_player_info(player_url)
+            original_url = player_url
+            player_url = f'/s/player/{player_id}/{self._PLAYER_JS_VARIANT_MAP[requested_js_variant]}'
+            if original_url != player_url:
+                self.write_debug(
+                    f'Forcing "{requested_js_variant}" player JS variant for player {player_id}\n'
+                    f'        original url = {original_url}', only_once=True)
+        elif requested_js_variant != 'actual':
+            self.report_warning(
+                f'Invalid player JS variant name "{requested_js_variant}" requested. '
+                f'Valid choices are: {", ".join(self._PLAYER_JS_VARIANT_MAP)}', only_once=True)
+
         return urljoin('https://www.youtube.com', player_url)
 
     def _download_player_url(self, video_id, fatal=False):
@@ -1953,6 +1987,17 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if player_version:
                 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
 
+    def _player_js_cache_key(self, player_url):
+        player_id = self._extract_player_info(player_url)
+        player_path = remove_start(urllib.parse.urlparse(player_url).path, f'/s/player/{player_id}/')
+        variant = self._INVERSE_PLAYER_JS_VARIANT_MAP.get(player_path)
+        if not variant:
+            self.write_debug(
+                f'Unable to determine player JS variant\n'
+                f'        player = {player_url}', only_once=True)
+            variant = re.sub(r'[^a-zA-Z0-9]', '_', remove_end(player_path, '.js'))
+        return join_nonempty(player_id, variant)
+
     def _signature_cache_id(self, example_sig):
         """ Return a string representation of a signature """
         return '.'.join(str(len(part)) for part in example_sig.split('.'))
@@ -1968,30 +2013,29 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return id_m.group('id')
 
     def _load_player(self, video_id, player_url, fatal=True):
-        player_id = self._extract_player_info(player_url)
+        player_js_key = self._player_js_cache_key(player_url)
-        if player_id not in self._code_cache:
+        if player_js_key not in self._code_cache:
             code = self._download_webpage(
                 player_url, video_id, fatal=fatal,
-                note='Downloading player ' + player_id,
+                note=f'Downloading player {player_js_key}',
-                errnote=f'Download of {player_url} failed')
+                errnote=f'Download of {player_js_key} failed')
             if code:
-                self._code_cache[player_id] = code
+                self._code_cache[player_js_key] = code
-        return self._code_cache.get(player_id)
+        return self._code_cache.get(player_js_key)
 
     def _extract_signature_function(self, video_id, player_url, example_sig):
-        player_id = self._extract_player_info(player_url)
-
         # Read from filesystem cache
-        func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
+        func_id = join_nonempty(
+            self._player_js_cache_key(player_url), self._signature_cache_id(example_sig))
         assert os.path.basename(func_id) == func_id
 
         self.write_debug(f'Extracting signature function {func_id}')
-        cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
+        cache_spec, code = self.cache.load('youtube-sigfuncs', func_id, min_ver='2025.03.31'), None
 
         if not cache_spec:
             code = self._load_player(video_id, player_url)
         if code:
-            res = self._parse_sig_js(code)
+            res = self._parse_sig_js(code, player_url)
             test_string = ''.join(map(chr, range(len(example_sig))))
             cache_spec = [ord(c) for c in res(test_string)]
             self.cache.store('youtube-sigfuncs', func_id, cache_spec)
@@ -2039,7 +2083,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 f'    return {expr_code}\n')
         self.to_screen('Extracted signature function:\n' + code)
 
-    def _parse_sig_js(self, jscode):
+    def _parse_sig_js(self, jscode, player_url):
         # Examples where `sig` is funcname:
         # sig=function(a){a=a.split(""); ... ;return a.join("")};
         # ;c&&(c=sig(decodeURIComponent(c)),a.set(b,encodeURIComponent(c)));return a};
@@ -2063,12 +2107,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
              r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
             jscode, 'Initial JS player signature function name', group='sig')
 
+        varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
         jsi = JSInterpreter(jscode)
-        global_var_map = {}
+        initial_function = jsi.extract_function(funcname, filter_dict({varname: global_list}))
-        _, varname, value = self._extract_player_js_global_var(jscode)
-        if varname:
-            global_var_map[varname] = jsi.interpret_expression(value, {}, allow_recursion=100)
-        initial_function = jsi.extract_function(funcname, global_var_map)
         return lambda s: initial_function([s])
 
     def _cached(self, func, *cache_id):
@@ -2087,6 +2128,24 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             return ret
         return inner
 
+    def _load_nsig_code_from_cache(self, player_url):
+        cache_id = ('youtube-nsig', self._player_js_cache_key(player_url))
+
+        if func_code := self._player_cache.get(cache_id):
+            return func_code
+
+        func_code = self.cache.load(*cache_id, min_ver='2025.03.31')
+        if func_code:
+            self._player_cache[cache_id] = func_code
+
+        return func_code
+
+    def _store_nsig_code_to_cache(self, player_url, func_code):
+        cache_id = ('youtube-nsig', self._player_js_cache_key(player_url))
+        if cache_id not in self._player_cache:
+            self.cache.store(*cache_id, func_code)
+            self._player_cache[cache_id] = func_code
+
     def _decrypt_signature(self, s, video_id, player_url):
         """Turn the encrypted s field into a working signature"""
         extract_sig = self._cached(
@@ -2127,9 +2186,31 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 video_id=video_id, note='Executing signature code').strip()
 
         self.write_debug(f'Decrypted nsig {s} => {ret}')
+        # Only cache nsig func JS code to disk if successful, and only once
+        self._store_nsig_code_to_cache(player_url, func_code)
         return ret
 
     def _extract_n_function_name(self, jscode, player_url=None):
+        varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
+        if debug_str := traverse_obj(global_list, (lambda _, v: v.endswith('_w8_'), any)):
+            funcname = self._search_regex(
+                r'''(?xs)
+                    [;\n](?:
+                        (?P<f>function\s+)|
+                        (?:var\s+)?
+                    )(?P<funcname>[a-zA-Z0-9_$]+)\s*(?(f)|=\s*function\s*)
+                    \((?P<argname>[a-zA-Z0-9_$]+)\)\s*\{
+                    (?:(?!\}[;\n]).)+
+                    \}\s*catch\(\s*[a-zA-Z0-9_$]+\s*\)\s*
+                    \{\s*return\s+%s\[%d\]\s*\+\s*(?P=argname)\s*\}\s*return\s+[^}]+\}[;\n]
+                ''' % (re.escape(varname), global_list.index(debug_str)),
+                jscode, 'nsig function name', group='funcname', default=None)
+            if funcname:
+                return funcname
+            self.write_debug(join_nonempty(
+                'Initial search was unable to find nsig function name',
+                player_url and f'        player = {player_url}', delim='\n'), only_once=True)
+
         # Examples (with placeholders nfunc, narray, idx):
         # *  .get("n"))&&(b=nfunc(b)
         # *  .get("n"))&&(b=narray[idx](b)
@@ -2159,7 +2240,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if not funcname:
             self.report_warning(join_nonempty(
                 'Falling back to generic n function search',
-                player_url and f'         player = {player_url}', delim='\n'))
+                player_url and f'         player = {player_url}', delim='\n'), only_once=True)
             return self._search_regex(
                 r'''(?xs)
                 ;\s*(?P<name>[a-zA-Z0-9_$]+)\s*=\s*function\([a-zA-Z0-9_$]+\)
@@ -2172,31 +2253,60 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
             f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
 
-    def _extract_player_js_global_var(self, jscode):
+    def _extract_player_js_global_var(self, jscode, player_url):
         """Returns tuple of strings: variable assignment code, variable name, variable value code"""
-        return self._search_regex(
+        extract_global_var = self._cached(self._search_regex, 'js global array', player_url)
+        varcode, varname, varvalue = extract_global_var(
             r'''(?x)
-                \'use\s+strict\';\s*
+                (?P<q1>["\'])use\s+strict(?P=q1);\s*
                 (?P<code>
                     var\s+(?P<name>[a-zA-Z0-9_$]+)\s*=\s*
-                    (?P<value>"(?:[^"\\]|\\.)+"\.split\("[^"]+"\))
+                    (?P<value>
+                        (?P<q2>["\'])(?:(?!(?P=q2)).|\\.)+(?P=q2)
+                        \.split\((?P<q3>["\'])(?:(?!(?P=q3)).)+(?P=q3)\)
+                        |\[\s*(?:(?P<q4>["\'])(?:(?!(?P=q4)).|\\.)*(?P=q4)\s*,?\s*)+\]
+                    )
                 )[;,]
             ''', jscode, 'global variable', group=('code', 'name', 'value'), default=(None, None, None))
+        if not varcode:
+            self.write_debug(join_nonempty(
+                'No global array variable found in player JS',
+                player_url and f'        player = {player_url}', delim='\n'), only_once=True)
+        return varcode, varname, varvalue
 
-    def _fixup_n_function_code(self, argnames, code, full_code):
+    def _interpret_player_js_global_var(self, jscode, player_url):
-        global_var, varname, _ = self._extract_player_js_global_var(full_code)
+        """Returns tuple of: variable name string, variable value list"""
-        if global_var:
+        _, varname, array_code = self._extract_player_js_global_var(jscode, player_url)
-            self.write_debug(f'Prepending n function code with global array variable "{varname}"')
+        jsi = JSInterpreter(array_code)
-            code = global_var + ', ' + code
+        interpret_global_var = self._cached(jsi.interpret_expression, 'js global list', player_url)
+        return varname, interpret_global_var(array_code, {}, allow_recursion=10)
+
+    def _fixup_n_function_code(self, argnames, nsig_code, jscode, player_url):
+        varcode, varname, _ = self._extract_player_js_global_var(jscode, player_url)
+        if varcode and varname:
+            nsig_code = varcode + '; ' + nsig_code
+            _, global_list = self._interpret_player_js_global_var(jscode, player_url)
         else:
-            self.write_debug('No global array variable found in player JS')
+            varname = 'dlp_wins'
-        return argnames, re.sub(
+            global_list = []
-            rf';\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(?:(["\'])undefined\1|{varname}\[\d+\])\s*\)\s*return\s+{argnames[0]};',
+
-            ';', code)
+        undefined_idx = global_list.index('undefined') if 'undefined' in global_list else r'\d+'
+        fixed_code = re.sub(
+            rf'''(?x)
+                ;\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(?:
+                    (["\'])undefined\1|
+                    {re.escape(varname)}\[{undefined_idx}\]
+                )\s*\)\s*return\s+{re.escape(argnames[0])};
+            ''', ';', nsig_code)
+        if fixed_code == nsig_code:
+            self.write_debug(join_nonempty(
+                'No typeof statement found in nsig function code',
+                player_url and f'        player = {player_url}', delim='\n'), only_once=True)
+        return argnames, fixed_code
 
     def _extract_n_function_code(self, video_id, player_url):
         player_id = self._extract_player_info(player_url)
-        func_code = self.cache.load('youtube-nsig', player_id, min_ver='2025.03.21')
+        func_code = self._load_nsig_code_from_cache(player_url)
         jscode = func_code or self._load_player(video_id, player_url)
         jsi = JSInterpreter(jscode)
 
@@ -2206,9 +2316,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         func_name = self._extract_n_function_name(jscode, player_url=player_url)
 
         # XXX: Workaround for the global array variable and lack of `typeof` implementation
-        func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name), jscode)
+        func_code = self._fixup_n_function_code(*jsi.extract_function_code(func_name), jscode, player_url)
 
-        self.cache.store('youtube-nsig', player_id, func_code)
         return jsi, player_id, func_code
 
     def _extract_n_function_from_code(self, jsi, func_code):
@@ -2717,7 +2826,7 @@ 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, **kwargs):
         """
         Fetch a PO Token for a given client and context. This function will validate required parameters for a given context and client.
 
@@ -2731,10 +2840,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         @param session_index: session index.
         @param player_url: player URL.
         @param video_id: video ID.
+        @param webpage: video webpage.
         @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:
@@ -2756,6 +2869,7 @@ 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
@@ -2765,7 +2879,7 @@ 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,
@@ -2774,11 +2888,61 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             session_index=session_index,
             player_url=player_url,
             video_id=video_id,
+            video_webpage=webpage,
             **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
+        if not (
+            _PoTokenContext(context) in self._get_default_ytcfg(client)['PO_TOKEN_REQUIRED_CONTEXTS']
+            or self._configuration_arg('fetch_pot', ['when_required'], ie_key=YoutubeIE)[0] == 'always'
+        ):
+            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):
@@ -2936,8 +3100,9 @@ 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(
@@ -3160,7 +3325,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     if player_url:
                         self.report_warning(
                             f'nsig extraction failed: Some formats may be missing\n'
-                            f'         n = {query["n"][0]} ; player = {player_url}',
+                            f'         n = {query["n"][0]} ; player = {player_url}\n'
+                            f'         {bug_reports_message(before="")}',
                             video_id=video_id, only_once=True)
                         self.write_debug(e, only_once=True)
                     else:
@@ -3178,7 +3344,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             is_damaged = try_call(lambda: format_duration < duration // 2)
             if is_damaged:
                 self.report_warning(
-                    f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
+                    'Some formats are possibly damaged. They will be deprioritized', video_id, only_once=True)
 
             po_token = fmt.get(STREAMING_DATA_INITIAL_PO_TOKEN)
 
@@ -3544,6 +3710,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 if 'sign in' in reason.lower():
                     reason = remove_end(reason, 'This helps protect our community. Learn more')
                     reason = f'{remove_end(reason.strip(), ".")}. {self._youtube_login_hint}'
+                elif get_first(playability_statuses, ('errorScreen', 'playerCaptchaViewModel', {dict})):
+                    reason += '. YouTube is requiring a captcha challenge before playback'
                 self.raise_no_formats(reason, expected=True)
 
         keywords = get_first(video_details, 'keywords', expected_type=list) or []
@@ -3772,7 +3940,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             if not traverse_obj(initial_data, 'contents'):
                 self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
                 initial_data = None
-        if not initial_data:
+        if not initial_data and 'initial_data' not in self._configuration_arg('player_skip'):
             query = {'videoId': video_id}
             query.update(self._get_checkok_params())
             initial_data = self._extract_response(

yt_dlp/extractor/youtube/pot/README.md

@@ -0,0 +1,285 @@
+# YoutubeIE PO Token Provider Framework
+
+As part of the YouTube extractor, we have a framework for providing PO Tokens programmatically. This can be used in plugins.
+
+Refer to the [PO Token Guide](https://github.com/yt-dlp/yt-dlp/wiki/PO-Token-Guide) for more information on PO Tokens.
+
+## 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 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 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 time 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, 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.
+  - 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`). Try to keep this to a minimum.
+- Use `self.logger.trace` to log a message to the PO Token debug output (`--extractor-args "youtube:pot_debug=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_debug=true"` to enable PO Token debug output.
+
+## Caching
+
+> [!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 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
+
+    """
+    Implement the below cache operations.
+
+    - expires_at is a timestamp in UTC. It MUST be respected - cache entries should not be returned if they have expired.
+    """
+
+    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):
+        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 YoutubeDL 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 (e.g. WebPO vs iOSGuard)
+
+```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 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 +1,2 @@
+# Trigger import of built-in providers
+from ._builtin import _trigger_import  # noqa: F401

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

@@ -0,0 +1,4 @@
+from .memory_cache import MemoryLRUPCP as _MemoryLRUPCP  # noqa: F401
+from .webpo_cachespec import WebPoPCSP as _WebPoPCSP  # noqa: F401
+
+_trigger_import = None  # noqa: F401

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

@@ -0,0 +1,80 @@
+from __future__ import annotations
+
+import datetime as dt
+import typing
+from collections import OrderedDict
+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'] = OrderedDict()
+        _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[OrderedDict, 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:
+                self.logger.trace('cache miss')
+                return None
+            value, expires_at = self.cache.pop(key)
+            if expires_at < int(dt.datetime.now(dt.timezone.utc).timestamp()):
+                self.logger.trace(f'cache expired key={key}')
+                return None
+            self.cache[key] = (value, expires_at)
+            self.logger.trace(f'cache hit key={key}')
+            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()):
+                self.logger.trace(f'ignoring expired key={key}')
+                return
+            if key in self.cache:
+                self.cache.pop(key)
+            self.cache[key] = (value, expires_at)
+            if len(self.cache) > self.max_size:
+                self.cache.popitem(last=False)
+            self.logger.trace(f'storing key={key}')
+
+    def delete(self, key: str):
+        with self.lock:
+            self.logger.trace(f'deleting key={key}')
+            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 +1,46 @@
+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:
+            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 +1,433 @@
+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 ExtractorError, bug_reports_message, format_field, join_nonempty, traverse_obj
+
+if typing.TYPE_CHECKING:
+    from yt_dlp.extractor.youtube.pot.cache import PCPPreference
+
+
+class YoutubeIEContentProviderLogger(IEContentProviderLogger):
+    def __init__(self, ie, prefix, log_level=IEContentProviderLogger.LogLevel.INFO):
+        self.__ie = ie
+        self.prefix = prefix
+        self.log_level = log_level
+
+    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[PCPPreference] | None = None,
+    ):
+        self.cache_providers: dict[str, PoTokenCacheProvider] = {
+            provider.PROVIDER_KEY: provider for provider in (cache_providers or [])
+        }
+        self.cache_provider_preferences: list[PCPPreference] = 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() 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: {e!r}{provider_bug_report_message(provider)}',
+                )
+                continue
+
+    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
+            '_yt': 'v1',
+            '_p': spec._provider.PROVIDER_KEY,
+        }
+        self.logger.trace('Generate cache key bindings: {}'.format(', '.join(f'{k}={v}' for k, v in bindings_cleaned.items())))
+        return bindings_cleaned
+
+    def _generate_key(self, bindings: dict) -> str:
+        binding_string = ''.join(f'{k}{v}' for k, v in 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}": {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: {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: {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: {e!r}{provider_bug_report_message(provider)}',
+                )
+                continue
+
+    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(): {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 (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: {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: {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 = {}
+        self.preferences = []
+        self.cache = cache
+        self.logger = logger
+
+    def register_provider(self, provider: PoTokenProvider):
+        self.providers[provider.PROVIDER_KEY] = provider
+
+    def register_preference(self, 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, trying next available provider. Reason: {e}')
+                continue
+            except PoTokenProviderError as e:
+                self.logger.warning(
+                    f'Error fetching PO Token from "{provider.PROVIDER_NAME}" provider: {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: {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: {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):
+    if not ie._downloader:
+        raise ExtractorError('Downloader not set', expected=False)
+
+    log_level = min(
+        IEContentProviderLogger.LogLevel(ie._configuration_arg('pot_log_level', ['INFO'], ie_key='youtube', casesense=False)[0].upper()),
+        IEContentProviderLogger.LogLevel.DEBUG if ie._downloader.params.get('verbose', False) else IEContentProviderLogger.LogLevel.INFO,
+    )
+
+    cache_providers = []
+    for cache_provider in _pot_cache_providers.value.values():
+        settings = traverse_obj(ie._downloader.params, ('extractor_args', f'{EXTRACTOR_ARG_PREFIX}-{cache_provider.PROVIDER_KEY.lower()}'))
+        cache_provider_logger = YoutubeIEContentProviderLogger(ie, f'pot:cache:{cache_provider.PROVIDER_NAME}', log_level=log_level)
+        cache_providers.append(cache_provider(ie, cache_provider_logger, settings or {}))
+
+    cache_spec_providers = []
+    for cache_spec_provider in _pot_pcs_providers.value.values():
+        settings = traverse_obj(ie._downloader.params, ('extractor_args', f'{EXTRACTOR_ARG_PREFIX}-{cache_spec_provider.PROVIDER_KEY.lower()}'))
+        cache_spec_provider_logger = YoutubeIEContentProviderLogger(ie, f'pot:cache:spec:{cache_spec_provider.PROVIDER_NAME}', log_level=log_level)
+        cache_spec_providers.append(cache_spec_provider(ie, cache_spec_provider_logger, settings or {}))
+
+    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():
+        settings = traverse_obj(ie._downloader.params, ('extractor_args', f'{EXTRACTOR_ARG_PREFIX}-{provider.PROVIDER_KEY.lower()}'))
+        logger = YoutubeIEContentProviderLogger(ie, f'pot:{provider.PROVIDER_NAME}', log_level=log_level)
+        director.register_provider(provider(ie, logger, settings or {}))
+
+    for preference in _ptp_preferences.value:
+        director.register_preference(preference)
+
+    if director.logger.log_level <= director.logger.LogLevel.DEBUG:
+        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):
+    if (
+        not isinstance(response, PoTokenResponse)
+        or not response.po_token
+        or not isinstance(response.po_token, str)
+    ):  # noqa: SIM103
+        return False
+
+    try:
+        clean_pot(response.po_token)
+    except ValueError:
+        return False
+
+    return (
+        response.expires_at is None
+        or (
+            isinstance(response.expires_at, int)
+            and (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 len({k for k in spec.key_bindings.values() if k is not None}) > 0
+    )

yt_dlp/extractor/youtube/pot/_provider.py

@@ -0,0 +1,151 @@
+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,
+    )
+
+
+# XXX: I don't think the typing is correct, and that we need py3.10 to properly type this
+def register_preference(*providers: type[PoTokenCacheProvider]) -> typing.Callable[[PCPPreference], PCPPreference]:
+    """Register a preference for a PoTokenCacheProvider"""
+    return register_preference_generic(
+        PoTokenCacheProvider,
+        _pot_cache_provider_preferences.value,
+        *providers,
+    )
+
+
+if typing.TYPE_CHECKING:
+    PCPPreference = typing.Callable[[PoTokenCacheProvider, PoTokenRequest, ...], int]

yt_dlp/extractor/youtube/pot/provider.py

@@ -0,0 +1,262 @@
+"""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'
+
+
+@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._builtin.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}. 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 support proxy scheme "{scheme}". Supported proxy schemes: {", ".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 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 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 (before + ' ' if before else '') + msg
+
+
+# XXX: I don't think the typing is correct, and that we need py3.10 to properly type this
+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]
+
+    # 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 +1,65 @@
+"""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 == PoTokenContext.PLAYER or client_name != 'WEB_REMIX':
+        return request.video_id, ContentBindingType.VIDEO_ID
+
+
+def _extract_visitor_id(visitor_data):
+    if not visitor_data:
+        return
+
+    # 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

@@ -188,6 +188,7 @@ _COMP_OPERATORS = {'===', '!==', '==', '!=', '<=', '>=', '<', '>'}
 _NAME_RE = r'[a-zA-Z_$][\w$]*'
 _MATCHING_PARENS = dict(zip(*zip('()', '{}', '[]')))
 _QUOTES = '\'"/'
+_NESTED_BRACKETS = r'[^[\]]+(?:\[[^[\]]+(?:\[[^\]]+\])?\])?'
 
 
 class JS_Undefined:
@@ -606,15 +607,18 @@ class JSInterpreter:
 
         m = re.match(fr'''(?x)
             (?P<assign>
-                (?P<out>{_NAME_RE})(?:\[(?P<index>[^\]]+?)\])?\s*
+                (?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<attribute>
-                (?P<var>{_NAME_RE})(?:(?P<nullish>\?)?\.(?P<member>[^(]+)|\[(?P<member2>[^\]]+)\])\s*
             )|(?P<function>
                 (?P<fname>{_NAME_RE})\((?P<args>.*)\)$
             )''', expr)
@@ -707,7 +711,7 @@ class JSInterpreter:
                 if obj is NO_DEFAULT:
                     if variable not in self._objects:
                         try:
-                            self._objects[variable] = self.extract_object(variable)
+                            self._objects[variable] = self.extract_object(variable, local_vars)
                         except self.Exception:
                             if not nullish:
                                 raise
@@ -847,7 +851,7 @@ class JSInterpreter:
             raise self.Exception('Cannot return from an expression', expr)
         return ret
 
-    def extract_object(self, objname):
+    def extract_object(self, objname, *global_stack):
         _FUNC_NAME_RE = r'''(?:[a-zA-Z$0-9]+|"[a-zA-Z$0-9]+"|'[a-zA-Z$0-9]+')'''
         obj = {}
         obj_m = re.search(
@@ -869,7 +873,8 @@ class JSInterpreter:
         for f in fields_m:
             argnames = f.group('args').split(',')
             name = remove_quotes(f.group('key'))
-            obj[name] = function_with_repr(self.build_function(argnames, f.group('code')), f'F<{name}>')
+            obj[name] = function_with_repr(
+                self.build_function(argnames, f.group('code'), *global_stack), f'F<{name}>')
 
         return obj
 

yt_dlp/networking/__init__.py

@@ -3,6 +3,7 @@ import warnings
 
 from .common import (
     HEADRequest,
+    PATCHRequest,
     PUTRequest,
     Request,
     RequestDirector,

yt_dlp/networking/_curlcffi.py

@@ -1,11 +1,13 @@
 from __future__ import annotations
 
 import io
+import itertools
 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,
@@ -31,9 +33,9 @@ if curl_cffi is None:
 
 curl_cffi_version = tuple(map(int, re.split(r'[^\d]+', curl_cffi.__version__)[:3]))
 
-if curl_cffi_version != (0, 5, 10) and not ((0, 7, 0) <= curl_cffi_version < (0, 7, 2)):
+if curl_cffi_version != (0, 5, 10) and not (0, 10) <= curl_cffi_version:
     curl_cffi._yt_dlp__version = f'{curl_cffi.__version__} (unsupported)'
-    raise ImportError('Only curl_cffi versions 0.5.10, 0.7.0 and 0.7.1 are supported')
+    raise ImportError('Only curl_cffi versions 0.5.10 and 0.10.x are supported')
 
 import curl_cffi.requests
 from curl_cffi.const import CurlECode, CurlOpt
@@ -97,7 +99,7 @@ class CurlCFFIResponseAdapter(Response):
             return self.fp.read(amt)
         except curl_cffi.requests.errors.RequestsError as e:
             if e.code == CurlECode.PARTIAL_FILE:
-                content_length = int_or_none(e.response.headers.get('Content-Length'))
+                content_length = e.response and int_or_none(e.response.headers.get('Content-Length'))
                 raise IncompleteRead(
                     partial=self.fp.bytes_read,
                     expected=content_length - self.fp.bytes_read if content_length is not None else None,
@@ -105,6 +107,51 @@ class CurlCFFIResponseAdapter(Response):
             raise TransportError(cause=e) from e
 
 
+# See: https://github.com/lexiforest/curl_cffi?tab=readme-ov-file#supported-impersonate-browsers
+#      https://github.com/lexiforest/curl-impersonate?tab=readme-ov-file#supported-browsers
+BROWSER_TARGETS: dict[tuple[int, ...], dict[str, ImpersonateTarget]] = {
+    (0, 5): {
+        'chrome99': ImpersonateTarget('chrome', '99', 'windows', '10'),
+        'chrome99_android': ImpersonateTarget('chrome', '99', 'android', '12'),
+        'chrome100': ImpersonateTarget('chrome', '100', 'windows', '10'),
+        'chrome101': ImpersonateTarget('chrome', '101', 'windows', '10'),
+        'chrome104': ImpersonateTarget('chrome', '104', 'windows', '10'),
+        'chrome107': ImpersonateTarget('chrome', '107', 'windows', '10'),
+        'chrome110': ImpersonateTarget('chrome', '110', 'windows', '10'),
+        'edge99': ImpersonateTarget('edge', '99', 'windows', '10'),
+        'edge101': ImpersonateTarget('edge', '101', 'windows', '10'),
+        'safari15_3': ImpersonateTarget('safari', '15.3', 'macos', '11'),
+        'safari15_5': ImpersonateTarget('safari', '15.5', 'macos', '12'),
+    },
+    (0, 7): {
+        'chrome116': ImpersonateTarget('chrome', '116', 'windows', '10'),
+        'chrome119': ImpersonateTarget('chrome', '119', 'macos', '14'),
+        'chrome120': ImpersonateTarget('chrome', '120', 'macos', '14'),
+        'chrome123': ImpersonateTarget('chrome', '123', 'macos', '14'),
+        'chrome124': ImpersonateTarget('chrome', '124', 'macos', '14'),
+        'safari17_0': ImpersonateTarget('safari', '17.0', 'macos', '14'),
+        'safari17_2_ios': ImpersonateTarget('safari', '17.2', 'ios', '17.2'),
+    },
+    (0, 9): {
+        'safari15_3': ImpersonateTarget('safari', '15.3', 'macos', '14'),
+        'safari15_5': ImpersonateTarget('safari', '15.5', 'macos', '14'),
+        'chrome119': ImpersonateTarget('chrome', '119', 'macos', '14'),
+        'chrome120': ImpersonateTarget('chrome', '120', 'macos', '14'),
+        'chrome123': ImpersonateTarget('chrome', '123', 'macos', '14'),
+        'chrome124': ImpersonateTarget('chrome', '124', 'macos', '14'),
+        'chrome131': ImpersonateTarget('chrome', '131', 'macos', '14'),
+        'chrome131_android': ImpersonateTarget('chrome', '131', 'android', '14'),
+        'chrome133a': ImpersonateTarget('chrome', '133', 'macos', '15'),
+        'firefox133': ImpersonateTarget('firefox', '133', 'macos', '14'),
+        'safari18_0': ImpersonateTarget('safari', '18.0', 'macos', '15'),
+        'safari18_0_ios': ImpersonateTarget('safari', '18.0', 'ios', '18.0'),
+    },
+    (0, 10): {
+        'firefox135': ImpersonateTarget('firefox', '135', 'macos', '14'),
+    },
+}
+
+
 @register_rh
 class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
     RH_NAME = 'curl_cffi'
@@ -112,30 +159,21 @@ class CurlCFFIRH(ImpersonateRequestHandler, InstanceStoreMixin):
     _SUPPORTED_FEATURES = (Features.NO_PROXY, Features.ALL_PROXY)
     _SUPPORTED_PROXY_SCHEMES = ('http', 'https', 'socks4', 'socks4a', 'socks5', 'socks5h')
     _SUPPORTED_IMPERSONATE_TARGET_MAP = {
-        **({
+        target: name if curl_cffi_version >= (0, 9) else curl_cffi.requests.BrowserType[name]
-            ImpersonateTarget('chrome', '124', 'macos', '14'): curl_cffi.requests.BrowserType.chrome124,
+        for name, target in dict(sorted(itertools.chain.from_iterable(
-            ImpersonateTarget('chrome', '123', 'macos', '14'): curl_cffi.requests.BrowserType.chrome123,
+            targets.items()
-            ImpersonateTarget('chrome', '120', 'macos', '14'): curl_cffi.requests.BrowserType.chrome120,
+            for version, targets in BROWSER_TARGETS.items()
-            ImpersonateTarget('chrome', '119', 'macos', '14'): curl_cffi.requests.BrowserType.chrome119,
+            if curl_cffi_version >= version
-            ImpersonateTarget('chrome', '116', 'windows', '10'): curl_cffi.requests.BrowserType.chrome116,
+        ), key=lambda x: (
-        } if curl_cffi_version >= (0, 7, 0) else {}),
+            # deprioritize mobile targets since they give very different behavior
-        ImpersonateTarget('chrome', '110', 'windows', '10'): curl_cffi.requests.BrowserType.chrome110,
+            x[1].os not in ('ios', 'android'),
-        ImpersonateTarget('chrome', '107', 'windows', '10'): curl_cffi.requests.BrowserType.chrome107,
+            # prioritize edge < firefox < safari < chrome
-        ImpersonateTarget('chrome', '104', 'windows', '10'): curl_cffi.requests.BrowserType.chrome104,
+            ('edge', 'firefox', 'safari', 'chrome').index(x[1].client),
-        ImpersonateTarget('chrome', '101', 'windows', '10'): curl_cffi.requests.BrowserType.chrome101,
+            # prioritize newest version
-        ImpersonateTarget('chrome', '100', 'windows', '10'): curl_cffi.requests.BrowserType.chrome100,
+            float(x[1].version) if x[1].version else 0,
-        ImpersonateTarget('chrome', '99', 'windows', '10'): curl_cffi.requests.BrowserType.chrome99,
+            # group by os name
-        ImpersonateTarget('edge', '101', 'windows', '10'): curl_cffi.requests.BrowserType.edge101,
+            x[1].os,
-        ImpersonateTarget('edge', '99', 'windows', '10'): curl_cffi.requests.BrowserType.edge99,
+        ), reverse=True)).items()
-        **({
-            ImpersonateTarget('safari', '17.0', 'macos', '14'): curl_cffi.requests.BrowserType.safari17_0,
-        } if curl_cffi_version >= (0, 7, 0) else {}),
-        ImpersonateTarget('safari', '15.5', 'macos', '12'): curl_cffi.requests.BrowserType.safari15_5,
-        ImpersonateTarget('safari', '15.3', 'macos', '11'): curl_cffi.requests.BrowserType.safari15_3,
-        ImpersonateTarget('chrome', '99', 'android', '12'): curl_cffi.requests.BrowserType.chrome99_android,
-        **({
-            ImpersonateTarget('safari', '17.2', 'ios', '17.2'): curl_cffi.requests.BrowserType.safari17_2_ios,
-        } if curl_cffi_version >= (0, 7, 0) else {}),
     }
 
     def _create_instance(self, cookiejar=None):

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/networking/common.py

@@ -505,6 +505,7 @@ class Request:
 
 
 HEADRequest = functools.partial(Request, method='HEAD')
+PATCHRequest = functools.partial(Request, method='PATCH')
 PUTRequest = functools.partial(Request, method='PUT')
 
 

yt_dlp/options.py

@@ -500,7 +500,8 @@ def create_parser():
                 'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
                 '2021': ['2022', 'no-certifi', 'filename-sanitization'],
                 '2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
-                '2023': ['prefer-vp9-sort'],
+                '2023': ['2024', 'prefer-vp9-sort'],
+                '2024': [],
             },
         }, help=(
             'Options that can help keep compatibility with youtube-dl or youtube-dlc '

yt_dlp/utils/_utils.py

@@ -2044,7 +2044,7 @@ def url_or_none(url):
     if not url or not isinstance(url, str):
         return None
     url = url.strip()
-    return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
+    return url if re.match(r'(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?|wss?):)?//', url) else None
 
 
 def strftime_or_none(timestamp, date_format='%Y%m%d', default=None):
@@ -2767,7 +2767,8 @@ def js_to_json(code, vars={}, *, strict=False):
     def template_substitute(match):
         evaluated = js_to_json(match.group(1), vars, strict=strict)
         if evaluated[0] == '"':
-            return json.loads(evaluated)
+            with contextlib.suppress(json.JSONDecodeError):
+                return json.loads(evaluated)
         return evaluated
 
     def fix_kv(m):

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__ = '2025.03.21'
+__version__ = '2025.03.31'
 
-RELEASE_GIT_HEAD = 'f36e4b6e65cb8403791aae2f520697115cb88dec'
+RELEASE_GIT_HEAD = '5e457af57fae9645b1b8fa0ed689229c8fb9656b'
 
 VARIANT = None
 
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
 
 ORIGIN = 'yt-dlp/yt-dlp'
 
-_pkg_version = '2025.03.21'
+_pkg_version = '2025.03.31'