mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-10-03 08:42:42 +00:00
Compare commits
36 Commits
2025.03.21
...
2025.03.31
Author | SHA1 | Date | |
---|---|---|---|
|
349f36606f | ||
|
5e457af57f | ||
|
61046c3161 | ||
|
07f04005e4 | ||
|
e465b078ea | ||
|
d63696f23a | ||
|
bb321cfdc3 | ||
|
5fc521cbd0 | ||
|
f033d86b96 | ||
|
9a1ec1d36e | ||
|
2956035912 | ||
|
22e34adbd7 | ||
|
6a6d97b2cb | ||
|
3ddbebb3c6 | ||
|
48be862b32 | ||
|
a8b9ff3c2a | ||
|
6eaa574c82 | ||
|
ecee97b4fa | ||
|
a550dfc904 | ||
|
336b33e72f | ||
|
9dde546e7e | ||
|
66e0bab814 | ||
|
801afeac91 | ||
|
86ab79e1a5 | ||
|
3396eb50dc | ||
|
5086d4aed6 | ||
|
9491b44032 | ||
|
b7fbb5a0a1 | ||
|
4054a2b623 | ||
|
b9c979461b | ||
|
9d5e6de2e7 | ||
|
9bf23902ce | ||
|
be5af3f9e9 | ||
|
fe4f14b836 | ||
|
b872ffec50 | ||
|
e2dfccaf80 |
@@ -757,3 +757,6 @@ rysson
|
||||
somini
|
||||
thedenv
|
||||
vallovic
|
||||
arabcoders
|
||||
mireq
|
||||
mlabeeb03
|
||||
|
63
Changelog.md
63
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
|
||||
|
11
README.md
11
README.md
@@ -1782,6 +1782,7 @@ 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`
|
||||
|
||||
#### 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 +1867,9 @@ 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 +2219,7 @@ 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 +2238,10 @@ 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:
|
||||
|
||||
|
@@ -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.*,<0.7.2; 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'",
|
||||
]
|
||||
secretstorage = [
|
||||
"cffi",
|
||||
|
@@ -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**
|
||||
- **SenateISVP**
|
||||
- **senate.gov**
|
||||
- **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**)
|
||||
|
@@ -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',
|
||||
'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',
|
||||
}, {
|
||||
# 192kbps (bitrate not provided in m3u8)
|
||||
'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',
|
||||
|
@@ -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'),
|
||||
|
@@ -614,7 +614,6 @@ 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:
|
||||
|
@@ -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/
|
||||
|
@@ -1260,6 +1260,7 @@ 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"')
|
||||
|
@@ -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):
|
||||
func = YoutubeIE(FakeYDL())._parse_sig_js(jscode)
|
||||
def signature(jscode, sig_input, player_url):
|
||||
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])
|
||||
|
||||
|
||||
|
@@ -654,19 +654,21 @@ 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(
|
||||
@@ -4150,7 +4152,7 @@ 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):
|
||||
|
@@ -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')
|
||||
|
@@ -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 (
|
||||
@@ -1989,6 +1987,7 @@ from .storyfire import (
|
||||
StoryFireSeriesIE,
|
||||
StoryFireUserIE,
|
||||
)
|
||||
from .streaks import StreaksIE
|
||||
from .streamable import StreamableIE
|
||||
from .streamcz import StreamCZIE
|
||||
from .streetvoice import StreetVoiceIE
|
||||
@@ -2352,10 +2351,6 @@ from .viewlift import (
|
||||
ViewLiftIE,
|
||||
)
|
||||
from .viidea import ViideaIE
|
||||
from .viki import (
|
||||
VikiChannelIE,
|
||||
VikiIE,
|
||||
)
|
||||
from .vimeo import (
|
||||
VHXEmbedIE,
|
||||
VimeoAlbumIE,
|
||||
@@ -2400,6 +2395,12 @@ from .voxmedia import (
|
||||
VoxMediaIE,
|
||||
VoxMediaVolumeIE,
|
||||
)
|
||||
from .vrsquare import (
|
||||
VrSquareChannelIE,
|
||||
VrSquareIE,
|
||||
VrSquareSearchIE,
|
||||
VrSquareSectionIE,
|
||||
)
|
||||
from .vrt import (
|
||||
VRTIE,
|
||||
DagelijkseKostIE,
|
||||
|
@@ -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 = [{
|
||||
|
@@ -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':
|
||||
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':
|
||||
if 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(
|
||||
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
|
||||
fatal = video_status == 'UPLOAD'
|
||||
playback = self._parse_json(video_meta['liveRewindPlaybackJson'], video_id, fatal=fatal)
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
|
||||
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,
|
||||
|
@@ -78,6 +78,7 @@ from ..utils import (
|
||||
parse_iso8601,
|
||||
parse_m3u8_attributes,
|
||||
parse_resolution,
|
||||
qualities,
|
||||
sanitize_url,
|
||||
smuggle_url,
|
||||
str_or_none,
|
||||
@@ -2177,6 +2178,8 @@ 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 +2192,11 @@ 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 +2291,8 @@ 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 +2315,28 @@ 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(
|
||||
|
@@ -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,
|
||||
}
|
87
yt_dlp/extractor/francaisfacile.py
Normal file
87
yt_dlp/extractor/francaisfacile.py
Normal file
@@ -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),
|
||||
}),
|
||||
}
|
@@ -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')
|
||||
duration = self._extract_m3u8_vod_duration(
|
||||
m3u8_format['url'], info.get('id'), note='Checking m3u8 live status',
|
||||
errnote='Failed to download m3u8 media playlist', headers=headers)
|
||||
headers = m3u8_format.get('http_headers') or info.get('http_headers') or {}
|
||||
display_id = info.get('id')
|
||||
urlh = self._request_webpage(
|
||||
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)
|
||||
|
@@ -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',
|
||||
|
@@ -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}),
|
||||
})
|
||||
|
@@ -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):
|
||||
formats = self._extract_ism_formats(ism_url, video_id)
|
||||
def _extract_ism(self, ism_url, video_id, fatal=True):
|
||||
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}),
|
||||
|
@@ -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:
|
||||
raise ExtractorError(errors, expected=True)
|
||||
elif errors: # Only warn when 'blacked out' since radio formats are available
|
||||
if errors: # Only warn when 'blacked out' or 'not entitled'; radio formats may be 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')
|
||||
|
@@ -3,8 +3,8 @@ from .dailymotion import DailymotionIE
|
||||
|
||||
|
||||
class MoviepilotIE(InfoExtractor):
|
||||
_IE_NAME = 'moviepilot'
|
||||
_IE_DESC = 'Moviepilot trailer'
|
||||
IE_NAME = 'moviepilot'
|
||||
IE_DESC = 'Moviepilot trailer'
|
||||
_VALID_URL = r'https?://(?:www\.)?moviepilot\.de/movies/(?P<id>[^/]+)'
|
||||
|
||||
_TESTS = [{
|
||||
|
@@ -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,
|
||||
unified_strdate,
|
||||
unified_timestamp,
|
||||
url_or_none,
|
||||
)
|
||||
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>[^/?#]+)'
|
||||
_GEO_COUNTRIES = ['AU']
|
||||
_VALID_URL = r'https?://(?:www\.)?9now\.com\.au/(?:[^/?#]+/){2}(?P<id>(?P<type>clip|episode)-[^/?#]+)'
|
||||
_GEO_BYPASS = False
|
||||
_TESTS = [{
|
||||
# clip
|
||||
'url': 'https://www.9now.com.au/afl-footy-show/2016/clip-ciql02091000g0hp5oktrnytc',
|
||||
'md5': '17cf47d63ec9323e562c9957a968b565',
|
||||
'url': 'https://www.9now.com.au/today/season-2025/clip-cm8hw9h5z00080hquqa5hszq7',
|
||||
'info_dict': {
|
||||
'id': '16801',
|
||||
'id': '6370295582112',
|
||||
'ext': 'mp4',
|
||||
'title': 'St. Kilda\'s Joey Montagna on the potential for a player\'s strike',
|
||||
'description': 'Is a boycott of the NAB Cup "on the table"?',
|
||||
'title': 'Would Karl Stefanovic be able to land a plane?',
|
||||
'description': 'The Today host\'s skills are put to the test with the latest simulation tech.',
|
||||
'uploader_id': '4460760524001',
|
||||
'upload_date': '20160713',
|
||||
'timestamp': 1468421266,
|
||||
'duration': 197.376,
|
||||
'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'):
|
||||
current_key = page_data.get(kind, {}).get(
|
||||
f'current{kind.capitalize()}Key')
|
||||
if not current_key:
|
||||
continue
|
||||
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')
|
||||
common_data = traverse_obj(
|
||||
re.findall(r'<script[^>]*>\s*self\.__next_f\.push\(\s*(\[.+?\])\s*\);?\s*</script>', webpage),
|
||||
(..., {json.loads}, ..., {self._find_json},
|
||||
lambda _, v: v['payload'][video_type]['slug'] == display_id,
|
||||
'payload', any, {require('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(
|
||||
common_data, lambda x: x['episode']['video']['brightcoveId'], str) or 'ref:{}'.format(common_data['episode']['video']['referenceId'])
|
||||
video_id = str_or_none(try_get(common_data, lambda x: x['episode']['video']['id'])) or brightcove_id
|
||||
|
||||
title = try_get(common_data, lambda x: x['episode']['name'], str)
|
||||
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()]
|
||||
brightcove_id = traverse_obj(common_data, (
|
||||
video_type, 'video', (
|
||||
('brightcoveId', {str}),
|
||||
('referenceId', {str}, {lambda x: f'ref:{x}' if x else None}),
|
||||
), any, {require('brightcove ID')}))
|
||||
|
||||
return {
|
||||
'_type': 'url_transparent',
|
||||
'url': smuggle_url(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
|
||||
{'geo_countries': self._GEO_COUNTRIES}),
|
||||
'id': video_id,
|
||||
'title': title,
|
||||
'description': try_get(common_data, lambda x: x['episode']['description'], str),
|
||||
'duration': float_or_none(try_get(common_data, lambda x: x['episode']['video']['duration'], float), 1000),
|
||||
'thumbnails': thumbnails,
|
||||
'ie_key': 'BrightcoveNew',
|
||||
'season_number': season_number,
|
||||
'episode_number': episode_number,
|
||||
'timestamp': timestamp,
|
||||
'release_date': release_date,
|
||||
'ie_key': BrightcoveNewIE.ie_key(),
|
||||
'url': self.BRIGHTCOVE_URL_TEMPLATE.format(brightcove_id),
|
||||
**traverse_obj(common_data, {
|
||||
'id': (video_type, 'video', 'id', {int}, ({str_or_none}, {value(brightcove_id)}), any),
|
||||
'title': (video_type, 'name', {str}),
|
||||
'description': (video_type, 'description', {str}),
|
||||
'duration': (video_type, 'video', 'duration', {float_or_none(scale=1000)}),
|
||||
'tags': (video_type, 'tags', ..., 'name', {str}, all, filter),
|
||||
'series': ('tvSeries', 'name', {str}),
|
||||
'season_number': ('season', 'seasonNumber', {int_or_none}),
|
||||
'episode_number': ('episode', 'episodeNumber', {int_or_none}),
|
||||
'timestamp': ('episode', 'airDate', {parse_iso8601}),
|
||||
'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'),
|
||||
}),
|
||||
}),
|
||||
}
|
||||
|
@@ -11,12 +11,15 @@ class On24IE(InfoExtractor):
|
||||
IE_NAME = 'on24'
|
||||
IE_DESC = 'ON24'
|
||||
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://event\.on24\.com/(?:
|
||||
wcc/r/(?P<id_1>\d{7})/(?P<key_1>[0-9A-F]{32})|
|
||||
eventRegistration/(?:console/EventConsoleApollo|EventLobbyServlet\?target=lobby30)
|
||||
\.jsp\?(?:[^/#?]*&)?eventid=(?P<id_2>\d{7})[^/#?]*&key=(?P<key_2>[0-9A-F]{32})
|
||||
)'''
|
||||
_ID_RE = r'(?P<id>\d{7})'
|
||||
_KEY_RE = r'(?P<key>[0-9A-F]{32})'
|
||||
_URL_BASE_RE = r'https?://event\.on24\.com'
|
||||
_URL_QUERY_RE = rf'(?:[^#]*&)?eventid={_ID_RE}&(?:[^#]+&)?key={_KEY_RE}'
|
||||
_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 = mobj.group('id_1') or mobj.group('id_2')
|
||||
event_key = mobj.group('key_1') or mobj.group('key_2')
|
||||
event_id, event_key = self._match_valid_url(url).group('id', 'key')
|
||||
|
||||
event_data = self._download_json(
|
||||
'https://event.on24.com/apic/utilApp/EventConsoleCachedServlet',
|
||||
|
@@ -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 = [{
|
||||
|
@@ -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
|
||||
|
@@ -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):
|
||||
|
@@ -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',
|
||||
}
|
||||
|
@@ -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',
|
||||
|
236
yt_dlp/extractor/streaks.py
Normal file
236
yt_dlp/extractor/streaks.py
Normal file
@@ -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'),
|
||||
}))
|
@@ -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'
|
||||
|
@@ -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',
|
||||
'url': 'https://tver.jp/episodes/ep83nf3w4p',
|
||||
# via Streaks backend
|
||||
'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!',
|
||||
'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',
|
||||
'id': 'epc1hdugbk',
|
||||
'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': [
|
||||
{
|
||||
'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',
|
||||
},
|
||||
}],
|
||||
'playlist_mincount': 21,
|
||||
}, {
|
||||
'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 {
|
||||
'_type': 'url_transparent',
|
||||
metadata = {
|
||||
'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(
|
||||
self.BRIGHTCOVE_URL_TEMPLATE % (p_id, r_id), {'geo_countries': ['JP']}),
|
||||
'ie_key': 'BrightcoveNew',
|
||||
**traverse_obj(video_info, {
|
||||
'description': ('description', {str}),
|
||||
'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,
|
||||
}
|
||||
|
@@ -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',
|
||||
'uploader': 'stereotype_',
|
||||
'uploader_id': '43566419',
|
||||
'creators': ['EA'],
|
||||
'channel': 'EA',
|
||||
'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, [{
|
||||
'operationName': 'VideoAccessToken_Clip',
|
||||
'variables': {
|
||||
'slug': video_id,
|
||||
},
|
||||
slug, [{
|
||||
'operationName': 'ShareClipRenderStatus',
|
||||
'variables': {'slug': slug},
|
||||
}],
|
||||
'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'],
|
||||
}
|
||||
|
||||
data = self._download_base_gql(
|
||||
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
|
||||
asset_default = traverse_obj(clip, ('assets', 0, {dict})) or {}
|
||||
asset_portrait = traverse_obj(clip, ('assets', 1, {dict})) or {}
|
||||
|
||||
formats = []
|
||||
for option in clip.get('videoQualities', []):
|
||||
if not isinstance(option, dict):
|
||||
continue
|
||||
source = url_or_none(option.get('sourceURL'))
|
||||
if not source:
|
||||
continue
|
||||
default_aspect_ratio = float_or_none(asset_default.get('aspectRatio'))
|
||||
formats.extend(traverse_obj(asset_default, ('videoQualities', lambda _, v: url_or_none(v['sourceURL']), {
|
||||
'url': ('sourceURL', {update_url_query(query=access_query)}),
|
||||
'format_id': ('quality', {str}),
|
||||
'height': ('quality', {int_or_none}),
|
||||
'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),
|
||||
'format_id': option.get('quality'),
|
||||
'height': int_or_none(option.get('quality')),
|
||||
'fps': int_or_none(option.get('frameRate')),
|
||||
'url': update_url_query(source['sourceURL'], access_query),
|
||||
'format_id': join_nonempty('portrait', source.get('quality')),
|
||||
'height': int_or_none(source.get('quality')),
|
||||
'fps': float_or_none(source.get('frameRate')),
|
||||
'aspect_ratio': portrait_aspect_ratio,
|
||||
'quality': -2,
|
||||
})
|
||||
|
||||
thumbnails = []
|
||||
for thumbnail_id in ('tiny', 'small', 'medium'):
|
||||
thumbnail_url = clip.get(thumbnail_id)
|
||||
if not thumbnail_url:
|
||||
continue
|
||||
thumb = {
|
||||
'id': thumbnail_id,
|
||||
'url': thumbnail_url,
|
||||
}
|
||||
mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url)
|
||||
if mobj:
|
||||
thumb.update({
|
||||
'height': int(mobj.group(2)),
|
||||
'width': int(mobj.group(1)),
|
||||
})
|
||||
thumbnails.append(thumb)
|
||||
thumb_asset_default_url = url_or_none(asset_default.get('thumbnailURL'))
|
||||
if thumb_asset_default_url:
|
||||
thumbnails.append({
|
||||
'id': 'default',
|
||||
'url': thumb_asset_default_url,
|
||||
'preference': 0,
|
||||
})
|
||||
if thumb_asset_portrait_url := url_or_none(asset_portrait.get('thumbnailURL')):
|
||||
thumbnails.append({
|
||||
'id': 'portrait',
|
||||
'url': thumb_asset_portrait_url,
|
||||
'preference': -1,
|
||||
})
|
||||
thumb_default_url = url_or_none(clip.get('thumbnailURL'))
|
||||
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,
|
||||
'title': clip.get('title'),
|
||||
'display_id': slug,
|
||||
'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),
|
||||
'uploader': try_get(clip, lambda x: x['curator']['displayName'], str),
|
||||
'uploader_id': try_get(clip, lambda x: x['curator']['id'], str),
|
||||
**traverse_obj(clip, {
|
||||
'title': ('title', {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),
|
||||
}),
|
||||
}
|
||||
|
@@ -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):
|
||||
|
@@ -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'))
|
185
yt_dlp/extractor/vrsquare.py
Normal file
185
yt_dlp/extractor/vrsquare.py
Normal file
@@ -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))
|
@@ -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+)'
|
||||
|
||||
|
@@ -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/
|
||||
|
@@ -803,12 +803,14 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
|
||||
|
||||
@classmethod
|
||||
def _extract_continuation_ep_data(cls, continuation_ep: dict):
|
||||
if isinstance(continuation_ep, dict):
|
||||
continuation = try_get(
|
||||
continuation_ep, lambda x: x['continuationCommand']['token'], str)
|
||||
continuation_commands = traverse_obj(
|
||||
continuation_ep, ('commandExecutorCommand', 'commands', ..., {dict}))
|
||||
continuation_commands.append(continuation_ep)
|
||||
for command in continuation_commands:
|
||||
continuation = traverse_obj(command, ('continuationCommand', 'token', {str}))
|
||||
if not continuation:
|
||||
return
|
||||
ctp = continuation_ep.get('clickTrackingParams')
|
||||
continue
|
||||
ctp = command.get('clickTrackingParams')
|
||||
return cls._build_api_continuation_query(continuation, ctp)
|
||||
|
||||
@classmethod
|
||||
|
@@ -34,6 +34,7 @@ from ...utils import (
|
||||
clean_html,
|
||||
datetime_from_str,
|
||||
filesize_from_tbr,
|
||||
filter_dict,
|
||||
float_or_none,
|
||||
format_field,
|
||||
get_first,
|
||||
@@ -1760,6 +1761,16 @@ 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
|
||||
@@ -1939,6 +1950,21 @@ 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 +1979,17 @@ 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 +2005,29 @@ 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)
|
||||
if player_id not in self._code_cache:
|
||||
player_js_key = self._player_js_cache_key(player_url)
|
||||
if player_js_key not in self._code_cache:
|
||||
code = self._download_webpage(
|
||||
player_url, video_id, fatal=fatal,
|
||||
note='Downloading player ' + player_id,
|
||||
errnote=f'Download of {player_url} failed')
|
||||
note=f'Downloading player {player_js_key}',
|
||||
errnote=f'Download of {player_js_key} failed')
|
||||
if code:
|
||||
self._code_cache[player_id] = code
|
||||
return self._code_cache.get(player_id)
|
||||
self._code_cache[player_js_key] = code
|
||||
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 +2075,7 @@ 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 +2099,9 @@ 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 = {}
|
||||
_, 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)
|
||||
initial_function = jsi.extract_function(funcname, filter_dict({varname: global_list}))
|
||||
return lambda s: initial_function([s])
|
||||
|
||||
def _cached(self, func, *cache_id):
|
||||
@@ -2087,6 +2120,24 @@ 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 +2178,31 @@ 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 +2232,7 @@ 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 +2245,60 @@ 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):
|
||||
global_var, varname, _ = self._extract_player_js_global_var(full_code)
|
||||
if global_var:
|
||||
self.write_debug(f'Prepending n function code with global array variable "{varname}"')
|
||||
code = global_var + ', ' + code
|
||||
def _interpret_player_js_global_var(self, jscode, player_url):
|
||||
"""Returns tuple of: variable name string, variable value list"""
|
||||
_, varname, array_code = self._extract_player_js_global_var(jscode, player_url)
|
||||
jsi = JSInterpreter(array_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')
|
||||
return argnames, re.sub(
|
||||
rf';\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(?:(["\'])undefined\1|{varname}\[\d+\])\s*\)\s*return\s+{argnames[0]};',
|
||||
';', code)
|
||||
varname = 'dlp_wins'
|
||||
global_list = []
|
||||
|
||||
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 +2308,8 @@ 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):
|
||||
@@ -3160,7 +3261,8 @@ 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 +3280,7 @@ 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)
|
||||
|
||||
|
@@ -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
|
||||
|
||||
|
@@ -1,6 +1,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import io
|
||||
import itertools
|
||||
import math
|
||||
import re
|
||||
import urllib.parse
|
||||
@@ -31,9 +32,9 @@ 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 +98,7 @@ 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 +106,51 @@ 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 +158,21 @@ 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 = {
|
||||
**({
|
||||
ImpersonateTarget('chrome', '124', 'macos', '14'): curl_cffi.requests.BrowserType.chrome124,
|
||||
ImpersonateTarget('chrome', '123', 'macos', '14'): curl_cffi.requests.BrowserType.chrome123,
|
||||
ImpersonateTarget('chrome', '120', 'macos', '14'): curl_cffi.requests.BrowserType.chrome120,
|
||||
ImpersonateTarget('chrome', '119', 'macos', '14'): curl_cffi.requests.BrowserType.chrome119,
|
||||
ImpersonateTarget('chrome', '116', 'windows', '10'): curl_cffi.requests.BrowserType.chrome116,
|
||||
} if curl_cffi_version >= (0, 7, 0) else {}),
|
||||
ImpersonateTarget('chrome', '110', 'windows', '10'): curl_cffi.requests.BrowserType.chrome110,
|
||||
ImpersonateTarget('chrome', '107', 'windows', '10'): curl_cffi.requests.BrowserType.chrome107,
|
||||
ImpersonateTarget('chrome', '104', 'windows', '10'): curl_cffi.requests.BrowserType.chrome104,
|
||||
ImpersonateTarget('chrome', '101', 'windows', '10'): curl_cffi.requests.BrowserType.chrome101,
|
||||
ImpersonateTarget('chrome', '100', 'windows', '10'): curl_cffi.requests.BrowserType.chrome100,
|
||||
ImpersonateTarget('chrome', '99', 'windows', '10'): curl_cffi.requests.BrowserType.chrome99,
|
||||
ImpersonateTarget('edge', '101', 'windows', '10'): curl_cffi.requests.BrowserType.edge101,
|
||||
ImpersonateTarget('edge', '99', 'windows', '10'): curl_cffi.requests.BrowserType.edge99,
|
||||
**({
|
||||
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 {}),
|
||||
target: name if curl_cffi_version >= (0, 9) else curl_cffi.requests.BrowserType[name]
|
||||
for name, target in dict(sorted(itertools.chain.from_iterable(
|
||||
targets.items()
|
||||
for version, targets in BROWSER_TARGETS.items()
|
||||
if curl_cffi_version >= version
|
||||
), key=lambda x: (
|
||||
# deprioritize mobile targets since they give very different behavior
|
||||
x[1].os not in ('ios', 'android'),
|
||||
# prioritize edge < firefox < safari < chrome
|
||||
('edge', 'firefox', 'safari', 'chrome').index(x[1].client),
|
||||
# prioritize newest version
|
||||
float(x[1].version) if x[1].version else 0,
|
||||
# group by os name
|
||||
x[1].os,
|
||||
), reverse=True)).items()
|
||||
}
|
||||
|
||||
def _create_instance(self, cookiejar=None):
|
||||
|
@@ -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 '
|
||||
|
@@ -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):
|
||||
|
@@ -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'
|
||||
|
Reference in New Issue
Block a user