Release 2023.11.16

Created by: bashonly

:ci skip all :ci run dl

.github/workflows/build.yml

@@ -204,11 +204,11 @@ jobs:
             apt -y install zlib1g-dev python3.8 python3.8-dev python3.8-distutils python3-pip
             python3.8 -m pip install -U pip setuptools wheel
             # Cannot access requirements.txt from the repo directory at this stage
-            python3.8 -m pip install -U Pyinstaller mutagen pycryptodomex websockets brotli certifi
+            python3.8 -m pip install -U Pyinstaller mutagen pycryptodomex websockets brotli certifi secretstorage
 
           run: |
             cd repo
-            python3.8 -m pip install -U Pyinstaller -r requirements.txt  # Cached version may be out of date
+            python3.8 -m pip install -U Pyinstaller secretstorage -r requirements.txt  # Cached version may be out of date
             python3.8 devscripts/update-version.py -c "${{ inputs.channel }}" -r "${{ needs.process.outputs.origin }}" "${{ inputs.version }}"
             python3.8 devscripts/make_lazy_extractors.py
             python3.8 pyinst.py

.github/workflows/release.yml

@@ -216,8 +216,8 @@ jobs:
         if: |
           !inputs.prerelease && env.target_repo == github.repository
         run: |
-          git config --global user.name github-actions
-          git config --global user.email github-actions@github.com
+          git config --global user.name "github-actions[bot]"
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
           git add -u
           git commit -m "Release ${{ env.version }}" \
             -m "Created by: ${{ github.event.sender.login }}" -m ":ci skip all :ci run dl"

CONTRIBUTORS

@@ -524,3 +524,7 @@ peci1
 saintliao
 shubhexists
 SirElderling
+almx
+elivinsky
+starius
+TravisDupes

Changelog.md

@@ -4,6 +4,23 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2023.11.16
+
+#### Extractor changes
+- **abc.net.au**: iview, showseries: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/15cb3528cbda7b6198f49a6b5953c226d701696b) ([#8586](https://github.com/yt-dlp/yt-dlp/issues/8586)) by [bashonly](https://github.com/bashonly)
+- **beatbump**: [Update `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/21dc069bea2d4d99345dd969e098f4535c751d45) ([#8576](https://github.com/yt-dlp/yt-dlp/issues/8576)) by [seproDev](https://github.com/seproDev)
+- **dailymotion**: [Improve `_VALID_URL`](https://github.com/yt-dlp/yt-dlp/commit/a489f071508ec5caf5f32052d142afe86c28df7a) ([#7692](https://github.com/yt-dlp/yt-dlp/issues/7692)) by [TravisDupes](https://github.com/TravisDupes)
+- **drtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0783fd558ed0d3a8bc754beb75a406256f8b97b2) ([#8484](https://github.com/yt-dlp/yt-dlp/issues/8484)) by [almx](https://github.com/almx), [seproDev](https://github.com/seproDev)
+- **eltrecetv**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/dcfad52812aa8ce007cefbfbe63f58b49f6b1046) ([#8216](https://github.com/yt-dlp/yt-dlp/issues/8216)) by [elivinsky](https://github.com/elivinsky)
+- **jiosaavn**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/b530118e7f48232cacf8050d79a6b20bdfcf5468) ([#8307](https://github.com/yt-dlp/yt-dlp/issues/8307)) by [awalgarg](https://github.com/awalgarg)
+- **njpwworld**: [Remove](https://github.com/yt-dlp/yt-dlp/commit/e569c2d1f4b665795a2b64f0aaf7f76930664233) ([#8570](https://github.com/yt-dlp/yt-dlp/issues/8570)) by [aarubui](https://github.com/aarubui)
+- **tv5mondeplus**: [Extract subtitles](https://github.com/yt-dlp/yt-dlp/commit/0f634dba3afdc429ece8839b02f6d56c27b7973a) ([#4209](https://github.com/yt-dlp/yt-dlp/issues/4209)) by [FrankZ85](https://github.com/FrankZ85)
+- **twitcasting**: [Fix livestream detection](https://github.com/yt-dlp/yt-dlp/commit/2325d03aa7bb80f56ba52cd6992258e44727b424) ([#8574](https://github.com/yt-dlp/yt-dlp/issues/8574)) by [JC-Chung](https://github.com/JC-Chung)
+- **zenyandex**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/5efe68b73cbf6e907c2e6a3aa338664385084184) ([#8454](https://github.com/yt-dlp/yt-dlp/issues/8454)) by [starius](https://github.com/starius)
+
+#### Misc. changes
+- **build**: [Make `secretstorage` an optional dependency](https://github.com/yt-dlp/yt-dlp/commit/24f827875c6ba513f12ed09a3aef2bbed223760d) ([#8585](https://github.com/yt-dlp/yt-dlp/issues/8585)) by [bashonly](https://github.com/bashonly)
+
 ### 2023.11.14
 
 #### Important changes

requirements.txt

@@ -6,4 +6,3 @@ brotlicffi; implementation_name!='cpython'
 certifi
 requests>=2.31.0,<3
 urllib3>=1.26.17,<3
-secretstorage; sys_platform=='linux' and (implementation_name!='pypy' or implementation_version>='7.3.10')

supportedsites.md

@@ -414,6 +414,7 @@
  - **EllenTubeVideo**
  - **Elonet**
  - **ElPais**: El País
+ - **ElTreceTV**: El Trece TV (Argentina)
  - **Embedly**
  - **EMPFlix**
  - **Engadget**
@@ -654,6 +655,8 @@
  - **Jamendo**
  - **JamendoAlbum**
  - **JeuxVideo**
+ - **JioSaavnAlbum**
+ - **JioSaavnSong**
  - **Joj**
  - **Jove**
  - **JStream**
@@ -976,7 +979,6 @@
  - **Nitter**
  - **njoy**: N-JOY
  - **njoy:embed**
- - **NJPWWorld**: [*njpwworld*](## "netrc machine") 新日本プロレスワールド
  - **NobelPrize**
  - **NoicePodcast**
  - **NonkTube**

yt_dlp/extractor/_extractors.py

@@ -565,6 +565,7 @@ from .ellentube import (
 )
 from .elonet import ElonetIE
 from .elpais import ElPaisIE
+from .eltrecetv import ElTreceTVIE
 from .embedly import EmbedlyIE
 from .engadget import EngadgetIE
 from .epicon import (
@@ -893,6 +894,10 @@ from .japandiet import (
     SangiinIE,
 )
 from .jeuxvideo import JeuxVideoIE
+from .jiosaavn import (
+    JioSaavnSongIE,
+    JioSaavnAlbumIE,
+)
 from .jove import JoveIE
 from .joj import JojIE
 from .jstream import JStreamIE
@@ -1320,7 +1325,6 @@ from .ninegag import NineGagIE
 from .ninenow import NineNowIE
 from .nintendo import NintendoIE
 from .nitter import NitterIE
-from .njpwworld import NJPWWorldIE
 from .nobelprize import NobelPrizeIE
 from .noice import NoicePodcastIE
 from .nonktube import NonkTubeIE

yt_dlp/extractor/abc.py

@@ -16,6 +16,7 @@ from ..utils import (
     try_get,
     unescapeHTML,
     update_url_query,
+    url_or_none,
 )
 
 
@@ -379,6 +380,18 @@ class ABCIViewShowSeriesIE(InfoExtractor):
             'noplaylist': True,
             'skip_download': 'm3u8',
         },
+    }, {
+        # 'videoEpisodes' is a dict with `items` key
+        'url': 'https://iview.abc.net.au/show/7-30-mark-humphries-satire',
+        'info_dict': {
+            'id': '178458-0',
+            'title': 'Episodes',
+            'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
+            'series': '7.30 Mark Humphries Satire',
+            'season': 'Episodes',
+            'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
+        },
+        'playlist_count': 15,
     }]
 
     def _real_extract(self, url):
@@ -398,12 +411,14 @@ class ABCIViewShowSeriesIE(InfoExtractor):
         series = video_data['selectedSeries']
         return {
             '_type': 'playlist',
-            'entries': [self.url_result(episode['shareUrl'])
-                        for episode in series['_embedded']['videoEpisodes']],
+            'entries': [self.url_result(episode_url, ABCIViewIE)
+                        for episode_url in traverse_obj(series, (
+                            '_embedded', 'videoEpisodes', (None, 'items'), ..., 'shareUrl', {url_or_none}))],
             'id': series.get('id'),
             'title': dict_get(series, ('title', 'displaySubtitle')),
             'description': series.get('description'),
             'series': dict_get(series, ('showTitle', 'displayTitle')),
             'season': dict_get(series, ('title', 'displaySubtitle')),
-            'thumbnail': series.get('thumbnail'),
+            'thumbnail': traverse_obj(
+                series, 'thumbnail', ('images', lambda _, v: v['name'] == 'seriesThumbnail', 'url'), get_all=False),
         }

yt_dlp/extractor/beatbump.py

@@ -3,14 +3,13 @@ from .youtube import YoutubeIE, YoutubeTabIE
 
 
 class BeatBumpVideoIE(InfoExtractor):
-    _VALID_URL = r'https://beatbump\.ml/listen\?id=(?P<id>[\w-]+)'
+    _VALID_URL = r'https://beatbump\.(?:ml|io)/listen\?id=(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://beatbump.ml/listen?id=MgNrAu2pzNs',
         'md5': '5ff3fff41d3935b9810a9731e485fe66',
         'info_dict': {
             'id': 'MgNrAu2pzNs',
             'ext': 'mp4',
-            'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
             'artist': 'Stephen',
             'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
             'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
@@ -22,10 +21,9 @@ class BeatBumpVideoIE(InfoExtractor):
             'alt_title': 'Voyeur Girl',
             'view_count': int,
             'track': 'Voyeur Girl',
-            'uploader': 'Stephen - Topic',
+            'uploader': 'Stephen',
             'title': 'Voyeur Girl',
             'channel_follower_count': int,
-            'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
             'age_limit': 0,
             'availability': 'public',
             'live_status': 'not_live',
@@ -36,7 +34,12 @@ class BeatBumpVideoIE(InfoExtractor):
             'tags': 'count:11',
             'creator': 'Stephen',
             'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
-        }
+            'channel_is_verified': True,
+            'heatmap': 'count:100',
+        },
+    }, {
+        'url': 'https://beatbump.io/listen?id=LDGZAprNGWo',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -45,7 +48,7 @@ class BeatBumpVideoIE(InfoExtractor):
 
 
 class BeatBumpPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https://beatbump\.ml/(?:release\?id=|artist/|playlist/)(?P<id>[\w-]+)'
+    _VALID_URL = r'https://beatbump\.(?:ml|io)/(?:release\?id=|artist/|playlist/)(?P<id>[\w-]+)'
     _TESTS = [{
         'url': 'https://beatbump.ml/release?id=MPREb_gTAcphH99wE',
         'playlist_count': 50,
@@ -56,25 +59,28 @@ class BeatBumpPlaylistIE(InfoExtractor):
             'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
             'description': '',
             'tags': [],
-            'modified_date': '20221223',
-        }
+            'modified_date': '20231110',
+        },
+        'expected_warnings': ['YouTube Music is not directly supported'],
     }, {
         'url': 'https://beatbump.ml/artist/UC_aEa8K-EOJ3D6gOs7HcyNg',
         'playlist_mincount': 1,
         'params': {'flatplaylist': True},
         'info_dict': {
             'id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
-            'uploader_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
+            'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
             'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
-            'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
+            'uploader_id': '@NoCopyrightSounds',
             'channel_follower_count': int,
-            'title': 'NoCopyrightSounds - Videos',
+            'title': 'NoCopyrightSounds',
             'uploader': 'NoCopyrightSounds',
             'description': 'md5:cd4fd53d81d363d05eee6c1b478b491a',
             'channel': 'NoCopyrightSounds',
-            'tags': 'count:12',
+            'tags': 'count:65',
             'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
+            'channel_is_verified': True,
         },
+        'expected_warnings': ['YouTube Music is not directly supported'],
     }, {
         'url': 'https://beatbump.ml/playlist/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
         'playlist_mincount': 1,
@@ -84,16 +90,20 @@ class BeatBumpPlaylistIE(InfoExtractor):
             'uploader_url': 'https://www.youtube.com/@NoCopyrightSounds',
             'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
             'view_count': int,
-            'channel_url': 'https://www.youtube.com/@NoCopyrightSounds',
-            'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
+            'channel_url': 'https://www.youtube.com/channel/UC_aEa8K-EOJ3D6gOs7HcyNg',
+            'uploader_id': '@NoCopyrightSounds',
             'title': 'NCS : All Releases 💿',
             'uploader': 'NoCopyrightSounds',
             'availability': 'public',
             'channel': 'NoCopyrightSounds',
             'tags': [],
-            'modified_date': '20221225',
+            'modified_date': '20231112',
             'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
-        }
+        },
+        'expected_warnings': ['YouTube Music is not directly supported'],
+    }, {
+        'url': 'https://beatbump.io/playlist/VLPLFCHGavqRG-q_2ZhmgU2XB2--ZY6irT1c',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/dailymotion.py

@@ -93,7 +93,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
     _VALID_URL = r'''(?ix)
                     https?://
                         (?:
-                            (?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:(?:embed|swf|\#)/)|player\.html\?)?video|swf)|
+                            (?:(?:www|touch|geo)\.)?dailymotion\.[a-z]{2,3}/(?:(?:(?:(?:embed|swf|\#)/)|player(?:/\w+)?\.html\?)?video|swf)|
                             (?:www\.)?lequipe\.fr/video
                         )
                         [/=](?P<id>[^/?_&]+)(?:.+?\bplaylist=(?P<playlist_id>x[0-9a-z]+))?
@@ -107,13 +107,17 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'id': 'x5kesuj',
             'ext': 'mp4',
             'title': 'Office Christmas Party Review –  Jason Bateman, Olivia Munn, T.J. Miller',
-            'description': 'Office Christmas Party Review -  Jason Bateman, Olivia Munn, T.J. Miller',
+            'description': 'Office Christmas Party Review - Jason Bateman, Olivia Munn, T.J. Miller',
             'duration': 187,
             'timestamp': 1493651285,
             'upload_date': '20170501',
             'uploader': 'Deadline',
             'uploader_id': 'x1xm8ri',
             'age_limit': 0,
+            'view_count': int,
+            'like_count': int,
+            'tags': ['hollywood', 'celeb', 'celebrity', 'movies', 'red carpet'],
+            'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/K456B1aXqIx58LKWQ/x1080',
         },
     }, {
         'url': 'https://geo.dailymotion.com/player.html?video=x89eyek&mute=true',
@@ -132,7 +136,7 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
             'view_count': int,
             'like_count': int,
             'tags': ['en_quete_d_esprit'],
-            'thumbnail': 'https://s2.dmcdn.net/v/Tncwi1YGKdvFbDuDY/x1080',
+            'thumbnail': r're:https://(?:s[12]\.)dmcdn\.net/v/Tncwi1YNg_RUl7ueu/x1080',
         }
     }, {
         'url': 'https://www.dailymotion.com/video/x2iuewm_steam-machine-models-pricing-listed-on-steam-store-ign-news_videogames',
@@ -201,6 +205,12 @@ class DailymotionIE(DailymotionBaseInfoExtractor):
     }, {
         'url': 'https://www.dailymotion.com/video/x3z49k?playlist=xv4bw',
         'only_matching': True,
+    }, {
+        'url': 'https://geo.dailymotion.com/player/x86gw.html?video=k46oCapRs4iikoz9DWy',
+        'only_matching': True,
+    }, {
+        'url': 'https://geo.dailymotion.com/player/xakln.html?video=x8mjju4&customConfig%5BcustomParams%5D=%2Ffr-fr%2Ftennis%2Fwimbledon-mens-singles%2Farticles-video',
+        'only_matching': True,
     }]
     _GEO_BYPASS = False
     _COMMON_MEDIA_FIELDS = '''description

yt_dlp/extractor/drtv.py

@@ -1,21 +1,17 @@
-import binascii
-import hashlib
-import re
+import json
+import uuid
 
 from .common import InfoExtractor
-from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
-from ..compat import compat_urllib_parse_unquote
 from ..utils import (
     ExtractorError,
-    float_or_none,
     int_or_none,
     mimetype2ext,
-    str_or_none,
-    traverse_obj,
-    unified_timestamp,
+    parse_iso8601,
+    try_call,
     update_url_query,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 SERIES_API = 'https://production-cdn.dr-massive.com/api/page?device=web_browser&item_detail_expand=all&lang=da&max_list_prefetch=3&path=%s'
 
@@ -24,7 +20,7 @@ class DRTVIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?dr\.dk/(?:tv/se|nyheder|(?P<radio>radio|lyd)(?:/ondemand)?)/(?:[^/]+/)*|
+                            (?:www\.)?dr\.dk/tv/se(?:/ondemand)?/(?:[^/?#]+/)*|
                             (?:www\.)?(?:dr\.dk|dr-massive\.com)/drtv/(?:se|episode|program)/
                         )
                         (?P<id>[\da-z_-]+)
@@ -53,22 +49,6 @@ class DRTVIE(InfoExtractor):
         },
         'expected_warnings': ['Unable to download f4m manifest'],
         'skip': 'this video has been removed',
-    }, {
-        # embed
-        'url': 'https://www.dr.dk/nyheder/indland/live-christianias-rydning-af-pusher-street-er-i-gang',
-        'info_dict': {
-            'id': 'urn:dr:mu:programcard:57c926176187a50a9c6e83c6',
-            'ext': 'mp4',
-            'title': 'christiania pusher street ryddes drdkrjpo',
-            'description': 'md5:2a71898b15057e9b97334f61d04e6eb5',
-            'timestamp': 1472800279,
-            'upload_date': '20160902',
-            'duration': 131.4,
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'expected_warnings': ['Unable to download f4m manifest'],
     }, {
         # with SignLanguage formats
         'url': 'https://www.dr.dk/tv/se/historien-om-danmark/-/historien-om-danmark-stenalder',
@@ -87,33 +67,54 @@ class DRTVIE(InfoExtractor):
             'season': 'Historien om Danmark',
             'series': 'Historien om Danmark',
         },
-        'params': {
-            'skip_download': True,
-        },
+        'skip': 'this video has been removed',
     }, {
-        'url': 'https://www.dr.dk/lyd/p4kbh/regionale-nyheder-kh4/p4-nyheder-2019-06-26-17-30-9',
-        'only_matching': True,
-    }, {
-        'url': 'https://www.dr.dk/drtv/se/bonderoeven_71769',
+        'url': 'https://www.dr.dk/drtv/se/frank-and-kastaniegaarden_71769',
         'info_dict': {
             'id': '00951930010',
             'ext': 'mp4',
-            'title': 'Bonderøven 2019 (1:8)',
-            'description': 'md5:b6dcfe9b6f0bea6703e9a0092739a5bd',
-            'timestamp': 1654856100,
-            'upload_date': '20220610',
-            'duration': 2576.6,
-            'season': 'Bonderøven 2019',
-            'season_id': 'urn:dr:mu:bundle:5c201667a11fa01ca4528ce5',
+            'title': 'Frank & Kastaniegaarden',
+            'description': 'md5:974e1780934cf3275ef10280204bccb0',
+            'release_timestamp': 1546545600,
+            'release_date': '20190103',
+            'duration': 2576,
+            'season': 'Frank & Kastaniegaarden',
+            'season_id': '67125',
             'release_year': 2019,
             'season_number': 2019,
             'series': 'Frank & Kastaniegaarden',
             'episode_number': 1,
-            'episode': 'Episode 1',
+            'episode': 'Frank & Kastaniegaarden',
+            'thumbnail': r're:https?://.+',
         },
         'params': {
             'skip_download': True,
         },
+    }, {
+        # Foreign and Regular subtitle track
+        'url': 'https://www.dr.dk/drtv/se/spise-med-price_-pasta-selv_397445',
+        'info_dict': {
+            'id': '00212301010',
+            'ext': 'mp4',
+            'episode_number': 1,
+            'title': 'Spise med Price: Pasta Selv',
+            'alt_title': '1. Pasta Selv',
+            'release_date': '20230807',
+            'description': 'md5:2da9060524fed707810d71080b3d0cd8',
+            'duration': 1750,
+            'season': 'Spise med Price',
+            'release_timestamp': 1691438400,
+            'season_id': '397440',
+            'episode': 'Spise med Price: Pasta Selv',
+            'thumbnail': r're:https?://.+',
+            'season_number': 15,
+            'series': 'Spise med Price',
+            'release_year': 2022,
+            'subtitles': 'mincount:2',
+        },
+        'params': {
+            'skip_download': 'm3u8',
+        },
     }, {
         'url': 'https://www.dr.dk/drtv/episode/bonderoeven_71769',
         'only_matching': True,
@@ -123,226 +124,127 @@ class DRTVIE(InfoExtractor):
     }, {
         'url': 'https://www.dr.dk/drtv/program/jagten_220924',
         'only_matching': True,
-    }, {
-        'url': 'https://www.dr.dk/lyd/p4aarhus/regionale-nyheder-ar4/regionale-nyheder-2022-05-05-12-30-3',
-        'info_dict': {
-            'id': 'urn:dr:mu:programcard:6265cb2571401424d0360113',
-            'title': "Regionale nyheder",
-            'ext': 'mp4',
-            'duration': 120.043,
-            'series': 'P4 Østjylland regionale nyheder',
-            'timestamp': 1651746600,
-            'season': 'Regionale nyheder',
-            'release_year': 0,
-            'season_id': 'urn:dr:mu:bundle:61c26889539f0201586b73c5',
-            'description': '',
-            'upload_date': '20220505',
-        },
-        'params': {
-            'skip_download': True,
-        },
-        'skip': 'this video has been removed',
-    }, {
-        'url': 'https://www.dr.dk/lyd/p4kbh/regionale-nyheder-kh4/regionale-nyheder-2023-03-14-10-30-9',
-        'info_dict': {
-            'ext': 'mp4',
-            'id': '14802310112',
-            'timestamp': 1678786200,
-            'duration': 120.043,
-            'season_id': 'urn:dr:mu:bundle:63a4f7c87140143504b6710f',
-            'series': 'P4 København regionale nyheder',
-            'upload_date': '20230314',
-            'release_year': 0,
-            'description': 'Hør seneste regionale nyheder fra P4 København.',
-            'season': 'Regionale nyheder',
-            'title': 'Regionale nyheder',
-        },
     }]
 
+    SUBTITLE_LANGS = {
+        'DanishLanguageSubtitles': 'da',
+        'ForeignLanguageSubtitles': 'da_foreign',
+        'CombinedLanguageSubtitles': 'da_combined',
+    }
+
+    _TOKEN = None
+
+    def _real_initialize(self):
+        if self._TOKEN:
+            return
+
+        token_response = self._download_json(
+            'https://production.dr-massive.com/api/authorization/anonymous-sso', None,
+            note='Downloading anonymous token', headers={
+                'content-type': 'application/json',
+            }, query={
+                'device': 'web_browser',
+                'ff': 'idp,ldp,rpt',
+                'lang': 'da',
+                'supportFallbackToken': 'true',
+            }, data=json.dumps({
+                'deviceId': str(uuid.uuid4()),
+                'scopes': ['Catalog'],
+                'optout': True,
+            }).encode())
+
+        self._TOKEN = traverse_obj(
+            token_response, (lambda _, x: x['type'] == 'UserAccount', 'value', {str}), get_all=False)
+        if not self._TOKEN:
+            raise ExtractorError('Unable to get anonymous token')
+
     def _real_extract(self, url):
-        raw_video_id, is_radio_url = self._match_valid_url(url).group('id', 'radio')
+        url_slug = self._match_id(url)
+        webpage = self._download_webpage(url, url_slug)
 
-        webpage = self._download_webpage(url, raw_video_id)
-
-        if '>Programmet er ikke længere tilgængeligt' in webpage:
-            raise ExtractorError(
-                'Video %s is not available' % raw_video_id, expected=True)
-
-        video_id = self._search_regex(
-            (r'data-(?:material-identifier|episode-slug)="([^"]+)"',
-             r'data-resource="[^>"]+mu/programcard/expanded/([^"]+)"'),
-            webpage, 'video id', default=None)
-
-        if not video_id:
-            video_id = self._search_regex(
-                r'(urn(?:%3A|:)dr(?:%3A|:)mu(?:%3A|:)programcard(?:%3A|:)[\da-f]+)',
-                webpage, 'urn', default=None)
-            if video_id:
-                video_id = compat_urllib_parse_unquote(video_id)
-
-        _PROGRAMCARD_BASE = 'https://www.dr.dk/mu-online/api/1.4/programcard'
-        query = {'expanded': 'true'}
-
-        if video_id:
-            programcard_url = '%s/%s' % (_PROGRAMCARD_BASE, video_id)
+        json_data = self._search_json(
+            r'window\.__data\s*=', webpage, 'data', url_slug, fatal=False) or {}
+        item = traverse_obj(
+            json_data, ('cache', 'page', ..., (None, ('entries', 0)), 'item', {dict}), get_all=False)
+        if item:
+            item_id = item.get('id')
         else:
-            programcard_url = _PROGRAMCARD_BASE
-            if is_radio_url:
-                video_id = self._search_nextjs_data(
-                    webpage, raw_video_id)['props']['pageProps']['episode']['productionNumber']
-            else:
-                json_data = self._search_json(
-                    r'window\.__data\s*=', webpage, 'data', raw_video_id)
-                video_id = traverse_obj(json_data, (
-                    'cache', 'page', ..., (None, ('entries', 0)), 'item', 'customId',
-                    {lambda x: x.split(':')[-1]}), get_all=False)
-                if not video_id:
-                    raise ExtractorError('Unable to extract video id')
-            query['productionnumber'] = video_id
+            item_id = url_slug.rsplit('_', 1)[-1]
+            item = self._download_json(
+                f'https://production-cdn.dr-massive.com/api/items/{item_id}', item_id,
+                note='Attempting to download backup item data', query={
+                    'device': 'web_browser',
+                    'expand': 'all',
+                    'ff': 'idp,ldp,rpt',
+                    'geoLocation': 'dk',
+                    'isDeviceAbroad': 'false',
+                    'lang': 'da',
+                    'segments': 'drtv,optedout',
+                    'sub': 'Anonymous',
+                })
 
-        data = self._download_json(
-            programcard_url, video_id, 'Downloading video JSON', query=query)
-
-        supplementary_data = {}
-        if re.search(r'_\d+$', raw_video_id):
-            supplementary_data = self._download_json(
-                SERIES_API % f'/episode/{raw_video_id}', raw_video_id, fatal=False) or {}
-
-        title = str_or_none(data.get('Title')) or re.sub(
-            r'\s*\|\s*(?:TV\s*\|\s*DR|DRTV)$', '',
-            self._og_search_title(webpage))
-        description = self._og_search_description(
-            webpage, default=None) or data.get('Description')
-
-        timestamp = unified_timestamp(
-            data.get('PrimaryBroadcastStartTime') or data.get('SortDateTime'))
-
-        thumbnail = None
-        duration = None
-
-        restricted_to_denmark = False
+        video_id = try_call(lambda: item['customId'].rsplit(':', 1)[-1]) or item_id
+        stream_data = self._download_json(
+            f'https://production.dr-massive.com/api/account/items/{item_id}/videos', video_id,
+            note='Downloading stream data', query={
+                'delivery': 'stream',
+                'device': 'web_browser',
+                'ff': 'idp,ldp,rpt',
+                'lang': 'da',
+                'resolution': 'HD-1080',
+                'sub': 'Anonymous',
+            }, headers={'authorization': f'Bearer {self._TOKEN}'})
 
         formats = []
         subtitles = {}
+        for stream in traverse_obj(stream_data, (lambda _, x: x['url'])):
+            format_id = stream.get('format', 'na')
+            access_service = stream.get('accessService')
+            preference = None
+            subtitle_suffix = ''
+            if access_service in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
+                preference = -1
+                format_id += f'-{access_service}'
+                subtitle_suffix = f'-{access_service}'
+            elif access_service == 'StandardVideo':
+                preference = 1
+            fmts, subs = self._extract_m3u8_formats_and_subtitles(
+                stream.get('url'), video_id, preference=preference, m3u8_id=format_id, fatal=False)
+            formats.extend(fmts)
 
-        assets = []
-        primary_asset = data.get('PrimaryAsset')
-        if isinstance(primary_asset, dict):
-            assets.append(primary_asset)
-        secondary_assets = data.get('SecondaryAssets')
-        if isinstance(secondary_assets, list):
-            for secondary_asset in secondary_assets:
-                if isinstance(secondary_asset, dict):
-                    assets.append(secondary_asset)
+            api_subtitles = traverse_obj(stream, ('subtitles', lambda _, v: url_or_none(v['link']), {dict}))
+            if not api_subtitles:
+                self._merge_subtitles(subs, target=subtitles)
 
-        def hex_to_bytes(hex):
-            return binascii.a2b_hex(hex.encode('ascii'))
+            for sub_track in api_subtitles:
+                lang = sub_track.get('language') or 'da'
+                subtitles.setdefault(self.SUBTITLE_LANGS.get(lang, lang) + subtitle_suffix, []).append({
+                    'url': sub_track['link'],
+                    'ext': mimetype2ext(sub_track.get('format')) or 'vtt'
+                })
 
-        def decrypt_uri(e):
-            n = int(e[2:10], 16)
-            a = e[10 + n:]
-            data = hex_to_bytes(e[10:10 + n])
-            key = hashlib.sha256(('%s:sRBzYNXBzkKgnjj8pGtkACch' % a).encode('utf-8')).digest()
-            iv = hex_to_bytes(a)
-            decrypted = unpad_pkcs7(aes_cbc_decrypt_bytes(data, key, iv))
-            return decrypted.decode('utf-8').split('?')[0]
-
-        for asset in assets:
-            kind = asset.get('Kind')
-            if kind == 'Image':
-                thumbnail = url_or_none(asset.get('Uri'))
-            elif kind in ('VideoResource', 'AudioResource'):
-                duration = float_or_none(asset.get('DurationInMilliseconds'), 1000)
-                restricted_to_denmark = asset.get('RestrictedToDenmark')
-                asset_target = asset.get('Target')
-                for link in asset.get('Links', []):
-                    uri = link.get('Uri')
-                    if not uri:
-                        encrypted_uri = link.get('EncryptedUri')
-                        if not encrypted_uri:
-                            continue
-                        try:
-                            uri = decrypt_uri(encrypted_uri)
-                        except Exception:
-                            self.report_warning(
-                                'Unable to decrypt EncryptedUri', video_id)
-                            continue
-                    uri = url_or_none(uri)
-                    if not uri:
-                        continue
-                    target = link.get('Target')
-                    format_id = target or ''
-                    if asset_target in ('SpokenSubtitles', 'SignLanguage', 'VisuallyInterpreted'):
-                        preference = -1
-                        format_id += '-%s' % asset_target
-                    elif asset_target == 'Default':
-                        preference = 1
-                    else:
-                        preference = None
-                    if target == 'HDS':
-                        f4m_formats = self._extract_f4m_formats(
-                            uri + '?hdcore=3.3.0&plugin=aasp-3.3.0.99.43',
-                            video_id, preference, f4m_id=format_id, fatal=False)
-                        if kind == 'AudioResource':
-                            for f in f4m_formats:
-                                f['vcodec'] = 'none'
-                        formats.extend(f4m_formats)
-                    elif target == 'HLS':
-                        fmts, subs = self._extract_m3u8_formats_and_subtitles(
-                            uri, video_id, 'mp4', entry_protocol='m3u8_native',
-                            quality=preference, m3u8_id=format_id, fatal=False)
-                        formats.extend(fmts)
-                        self._merge_subtitles(subs, target=subtitles)
-                    else:
-                        bitrate = link.get('Bitrate')
-                        if bitrate:
-                            format_id += '-%s' % bitrate
-                        formats.append({
-                            'url': uri,
-                            'format_id': format_id,
-                            'tbr': int_or_none(bitrate),
-                            'ext': link.get('FileFormat'),
-                            'vcodec': 'none' if kind == 'AudioResource' else None,
-                            'quality': preference,
-                        })
-            subtitles_list = asset.get('SubtitlesList') or asset.get('Subtitleslist')
-            if isinstance(subtitles_list, list):
-                LANGS = {
-                    'Danish': 'da',
-                }
-                for subs in subtitles_list:
-                    if not isinstance(subs, dict):
-                        continue
-                    sub_uri = url_or_none(subs.get('Uri'))
-                    if not sub_uri:
-                        continue
-                    lang = subs.get('Language') or 'da'
-                    subtitles.setdefault(LANGS.get(lang, lang), []).append({
-                        'url': sub_uri,
-                        'ext': mimetype2ext(subs.get('MimeType')) or 'vtt'
-                    })
-
-        if not formats and restricted_to_denmark:
-            self.raise_geo_restricted(
-                'Unfortunately, DR is not allowed to show this program outside Denmark.',
-                countries=self._GEO_COUNTRIES)
+        if not formats and traverse_obj(item, ('season', 'customFields', 'IsGeoRestricted')):
+            self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
 
         return {
             'id': video_id,
-            'title': title,
-            'description': description,
-            'thumbnail': thumbnail,
-            'timestamp': timestamp,
-            'duration': duration,
             'formats': formats,
             'subtitles': subtitles,
-            'series': str_or_none(data.get('SeriesTitle')),
-            'season': str_or_none(data.get('SeasonTitle')),
-            'season_number': int_or_none(data.get('SeasonNumber')),
-            'season_id': str_or_none(data.get('SeasonUrn')),
-            'episode': traverse_obj(supplementary_data, ('entries', 0, 'item', 'contextualTitle')) or str_or_none(data.get('EpisodeTitle')),
-            'episode_number': traverse_obj(supplementary_data, ('entries', 0, 'item', 'episodeNumber')) or int_or_none(data.get('EpisodeNumber')),
-            'release_year': int_or_none(data.get('ProductionYear')),
+            **traverse_obj(item, {
+                'title': 'title',
+                'alt_title': 'contextualTitle',
+                'description': 'description',
+                'thumbnail': ('images', 'wallpaper'),
+                'release_timestamp': ('customFields', 'BroadcastTimeDK', {parse_iso8601}),
+                'duration': ('duration', {int_or_none}),
+                'series': ('season', 'show', 'title'),
+                'season': ('season', 'title'),
+                'season_number': ('season', 'seasonNumber', {int_or_none}),
+                'season_id': 'seasonId',
+                'episode': 'episodeName',
+                'episode_number': ('episodeNumber', {int_or_none}),
+                'release_year': ('releaseYear', {int_or_none}),
+            }),
         }
 
 
@@ -412,6 +314,8 @@ class DRTVSeasonIE(InfoExtractor):
             'display_id': 'frank-and-kastaniegaarden',
             'title': 'Frank & Kastaniegaarden',
             'series': 'Frank & Kastaniegaarden',
+            'season_number': 2008,
+            'alt_title': 'Season 2008',
         },
         'playlist_mincount': 8
     }, {
@@ -421,6 +325,8 @@ class DRTVSeasonIE(InfoExtractor):
             'display_id': 'frank-and-kastaniegaarden',
             'title': 'Frank & Kastaniegaarden',
             'series': 'Frank & Kastaniegaarden',
+            'season_number': 2009,
+            'alt_title': 'Season 2009',
         },
         'playlist_mincount': 19
     }]
@@ -434,6 +340,7 @@ class DRTVSeasonIE(InfoExtractor):
             'url': f'https://www.dr.dk/drtv{episode["path"]}',
             'ie_key': DRTVIE.ie_key(),
             'title': episode.get('title'),
+            'alt_title': episode.get('contextualTitle'),
             'episode': episode.get('episodeName'),
             'description': episode.get('shortDescription'),
             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
@@ -446,6 +353,7 @@ class DRTVSeasonIE(InfoExtractor):
             'id': season_id,
             'display_id': display_id,
             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
+            'alt_title': traverse_obj(data, ('entries', 0, 'item', 'contextualTitle')),
             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
             'entries': entries,
             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber'))
@@ -463,6 +371,7 @@ class DRTVSeriesIE(InfoExtractor):
             'display_id': 'frank-and-kastaniegaarden',
             'title': 'Frank & Kastaniegaarden',
             'series': 'Frank & Kastaniegaarden',
+            'alt_title': '',
         },
         'playlist_mincount': 15
     }]
@@ -476,6 +385,7 @@ class DRTVSeriesIE(InfoExtractor):
             'url': f'https://www.dr.dk/drtv{season.get("path")}',
             'ie_key': DRTVSeasonIE.ie_key(),
             'title': season.get('title'),
+            'alt_title': season.get('contextualTitle'),
             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
             'season_number': traverse_obj(data, ('entries', 0, 'item', 'seasonNumber'))
         } for season in traverse_obj(data, ('entries', 0, 'item', 'show', 'seasons', 'items'))]
@@ -485,6 +395,7 @@ class DRTVSeriesIE(InfoExtractor):
             'id': series_id,
             'display_id': display_id,
             'title': traverse_obj(data, ('entries', 0, 'item', 'title')),
+            'alt_title': traverse_obj(data, ('entries', 0, 'item', 'contextualTitle')),
             'series': traverse_obj(data, ('entries', 0, 'item', 'title')),
             'entries': entries
         }

yt_dlp/extractor/eltrecetv.py

@@ -0,0 +1,62 @@
+from .common import InfoExtractor
+
+
+class ElTreceTVIE(InfoExtractor):
+    IE_DESC = 'El Trece TV (Argentina)'
+    _VALID_URL = r'https?://(?:www\.)?eltrecetv\.com\.ar/[\w-]+/capitulos/temporada-\d+/(?P<id>[\w-]+)'
+    _TESTS = [
+        {
+            'url': 'https://www.eltrecetv.com.ar/ahora-caigo/capitulos/temporada-2023/programa-del-061023/',
+            'md5': '71a66673dc63f9a5939d97bfe4b311ba',
+            'info_dict': {
+                'id': 'AHCA05102023145553329621094',
+                'ext': 'mp4',
+                'title': 'AHORA CAIGO - Programa 06/10/23',
+                'thumbnail': 'https://thumbs.vodgc.net/AHCA05102023145553329621094.JPG?649339',
+            }
+        },
+        {
+            'url': 'https://www.eltrecetv.com.ar/poco-correctos/capitulos/temporada-2023/programa-del-250923-invitada-dalia-gutmann/',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.eltrecetv.com.ar/argentina-tierra-de-amor-y-venganza/capitulos/temporada-2023/atav-2-capitulo-121-del-250923/',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.eltrecetv.com.ar/ahora-caigo/capitulos/temporada-2023/programa-del-250923/',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.eltrecetv.com.ar/pasaplatos/capitulos/temporada-2023/pasaplatos-el-restaurante-del-250923/',
+            'only_matching': True,
+        },
+        {
+            'url': 'https://www.eltrecetv.com.ar/el-galpon/capitulos/temporada-2023/programa-del-160923-invitado-raul-lavie/',
+            'only_matching': True,
+        }
+    ]
+
+    def _real_extract(self, url):
+        slug = self._match_id(url)
+        webpage = self._download_webpage(url, slug)
+        config = self._search_json(
+            r'Fusion.globalContent\s*=', webpage, 'content', slug)['promo_items']['basic']['embed']['config']
+        video_url = config['m3u8']
+        video_id = self._search_regex(r'/(\w+)\.m3u8', video_url, 'video id', default=slug)
+
+        formats, subtitles = self._extract_m3u8_formats_and_subtitles(video_url, video_id, 'mp4', m3u8_id='hls')
+        formats.extend([{
+            'url': f['url'][:-23],
+            'format_id': f['format_id'].replace('hls', 'http'),
+            'width': f.get('width'),
+            'height': f.get('height'),
+        } for f in formats if f['url'].endswith('/tracks-v1a1/index.m3u8') and f.get('height') != 1080])
+
+        return {
+            'id': video_id,
+            'title': config.get('title'),
+            'thumbnail': config.get('thumbnail'),
+            'formats': formats,
+            'subtitles': subtitles,
+        }

yt_dlp/extractor/jiosaavn.py

@@ -0,0 +1,79 @@
+from .common import InfoExtractor
+from ..utils import (
+    js_to_json,
+    url_or_none,
+    urlencode_postdata,
+    urljoin,
+)
+from ..utils.traversal import traverse_obj
+
+
+class JioSaavnBaseIE(InfoExtractor):
+    def _extract_initial_data(self, url, audio_id):
+        webpage = self._download_webpage(url, audio_id)
+        return self._search_json(
+            r'window\.__INITIAL_DATA__\s*=', webpage,
+            'init json', audio_id, transform_source=js_to_json)
+
+
+class JioSaavnSongIE(JioSaavnBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:jiosaavn\.com/song/[^/?#]+/|saavn\.com/s/song/(?:[^/?#]+/){3})(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/song/leja-re/OQsEfQFVUXk',
+        'md5': '7b1f70de088ede3a152ea34aece4df42',
+        'info_dict': {
+            'id': 'OQsEfQFVUXk',
+            'ext': 'mp3',
+            'title': 'Leja Re',
+            'album': 'Leja Re',
+            'thumbnail': 'https://c.saavncdn.com/258/Leja-Re-Hindi-2018-20181124024539-500x500.jpg',
+        },
+    }, {
+        'url': 'https://www.saavn.com/s/song/hindi/Saathiya/O-Humdum-Suniyo-Re/KAMiazoCblU',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        audio_id = self._match_id(url)
+        song_data = self._extract_initial_data(url, audio_id)['song']['song']
+        media_data = self._download_json(
+            'https://www.jiosaavn.com/api.php', audio_id, data=urlencode_postdata({
+                '__call': 'song.generateAuthToken',
+                '_format': 'json',
+                'bitrate': '128',
+                'url': song_data['encrypted_media_url'],
+            }))
+
+        return {
+            'id': audio_id,
+            'url': media_data['auth_url'],
+            'ext': media_data.get('type'),
+            'vcodec': 'none',
+            **traverse_obj(song_data, {
+                'title': ('title', 'text'),
+                'album': ('album', 'text'),
+                'thumbnail': ('image', 0, {url_or_none}),
+            }),
+        }
+
+
+class JioSaavnAlbumIE(JioSaavnBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?(?:jio)?saavn\.com/album/[^/?#]+/(?P<id>[^/?#]+)'
+    _TESTS = [{
+        'url': 'https://www.jiosaavn.com/album/96/buIOjYZDrNA_',
+        'info_dict': {
+            'id': 'buIOjYZDrNA_',
+            'title': '96',
+        },
+        'playlist_count': 10,
+    }]
+
+    def _real_extract(self, url):
+        album_id = self._match_id(url)
+        album_view = self._extract_initial_data(url, album_id)['albumView']
+
+        return self.playlist_from_matches(
+            traverse_obj(album_view, (
+                'modules', lambda _, x: x['key'] == 'list', 'data', ..., 'title', 'action', {str})),
+            album_id, traverse_obj(album_view, ('album', 'title', 'text', {str})), ie=JioSaavnSongIE,
+            getter=lambda x: urljoin('https://www.jiosaavn.com/', x))

yt_dlp/extractor/njpwworld.py

@@ -1,82 +0,0 @@
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import (
-    get_element_by_class,
-    urlencode_postdata,
-)
-
-
-class NJPWWorldIE(InfoExtractor):
-    _VALID_URL = r'https?://(front\.)?njpwworld\.com/p/(?P<id>[a-z0-9_]+)'
-    IE_DESC = '新日本プロレスワールド'
-    _NETRC_MACHINE = 'njpwworld'
-
-    _TESTS = [{
-        'url': 'http://njpwworld.com/p/s_series_00155_1_9/',
-        'info_dict': {
-            'id': 's_series_00155_1_9',
-            'ext': 'mp4',
-            'title': '闘強導夢2000 2000年1月4日 東京ドーム 第9試合 ランディ・サベージ VS リック・スタイナー',
-            'tags': list,
-        },
-        'params': {
-            'skip_download': True,  # AES-encrypted m3u8
-        },
-        'skip': 'Requires login',
-    }, {
-        'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
-        'info_dict': {
-            'id': 's_series_00563_16_bs',
-            'ext': 'mp4',
-            'title': 'WORLD TAG LEAGUE 2020 & BEST OF THE SUPER Jr.27 2020年12月6日 福岡・福岡国際センター バックステージコメント（字幕あり）',
-            'tags': ["福岡・福岡国際センター", "バックステージコメント", "2020", "20年代"],
-        },
-        'params': {
-            'skip_download': True,
-        },
-    }]
-
-    _LOGIN_URL = 'https://front.njpwworld.com/auth/login'
-
-    def _perform_login(self, username, password):
-        # Setup session (will set necessary cookies)
-        self._request_webpage(
-            'https://njpwworld.com/', None, note='Setting up session')
-
-        webpage, urlh = self._download_webpage_handle(
-            self._LOGIN_URL, None,
-            note='Logging in', errnote='Unable to login',
-            data=urlencode_postdata({'login_id': username, 'pw': password}),
-            headers={'Referer': 'https://front.njpwworld.com/auth'})
-        # /auth/login will return 302 for successful logins
-        if urlh.url == self._LOGIN_URL:
-            self.report_warning('unable to login')
-            return False
-
-        return True
-
-    def _real_extract(self, url):
-        video_id = self._match_id(url)
-
-        webpage = self._download_webpage(url, video_id)
-
-        formats = []
-        for kind, vid in re.findall(r'if\s+\(\s*imageQualityType\s*==\s*\'([^\']+)\'\s*\)\s*{\s*video_id\s*=\s*"(\d+)"', webpage):
-            player_path = '/intent?id=%s&type=url' % vid
-            player_url = compat_urlparse.urljoin(url, player_path)
-            formats += self._extract_m3u8_formats(
-                player_url, video_id, 'mp4', 'm3u8_native', m3u8_id=kind, fatal=False, quality=int(kind == 'high'))
-
-        tag_block = get_element_by_class('tag-block', webpage)
-        tags = re.findall(
-            r'<a[^>]+class="tag-[^"]+"[^>]*>([^<]+)</a>', tag_block
-        ) if tag_block else None
-
-        return {
-            'id': video_id,
-            'title': get_element_by_class('article-title', webpage) or self._og_search_title(webpage),
-            'formats': formats,
-            'tags': tags,
-        }

yt_dlp/extractor/tv5mondeplus.py

@@ -84,6 +84,13 @@ class TV5MondePlusIE(InfoExtractor):
     }]
     _GEO_BYPASS = False
 
+    @staticmethod
+    def _extract_subtitles(data_captions):
+        subtitles = {}
+        for f in traverse_obj(data_captions, ('files', lambda _, v: url_or_none(v['file']))):
+            subtitles.setdefault(f.get('label') or 'fra', []).append({'url': f['file']})
+        return subtitles
+
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
@@ -176,6 +183,8 @@ class TV5MondePlusIE(InfoExtractor):
             'duration': duration,
             'upload_date': upload_date,
             'formats': formats,
+            'subtitles': self._extract_subtitles(self._parse_json(
+                traverse_obj(vpl_data, ('data-captions', {str}), default='{}'), display_id, fatal=False)),
             'series': series,
             'episode': episode,
         }

yt_dlp/extractor/twitcasting.py

@@ -11,6 +11,7 @@ from ..utils import (
     float_or_none,
     get_element_by_class,
     get_element_by_id,
+    int_or_none,
     parse_duration,
     qualities,
     str_to_int,
@@ -241,6 +242,8 @@ class TwitCastingLiveIE(InfoExtractor):
         'expected_exception': 'UserNotLive',
     }]
 
+    _PROTECTED_LIVE_RE = r'(?s)(<span\s*class="tw-movie-thumbnail2-badge"\s*data-status="live">\s*LIVE)'
+
     def _real_extract(self, url):
         uploader_id = self._match_id(url)
         self.to_screen(
@@ -248,24 +251,27 @@ class TwitCastingLiveIE(InfoExtractor):
             'Pass "https://twitcasting.tv/{0}/show" to download the history'.format(uploader_id))
 
         webpage = self._download_webpage(url, uploader_id)
-        current_live = self._search_regex(
-            (r'data-type="movie" data-id="(\d+)">',
-             r'tw-sound-flag-open-link" data-id="(\d+)" style=',),
-            webpage, 'current live ID', default=None)
-        if not current_live:
+        is_live = self._search_regex(  # first pattern is for public live
+            (r'(data-is-onlive="true")', self._PROTECTED_LIVE_RE), webpage, 'is live?', default=None)
+        current_live = int_or_none(self._search_regex(
+            (r'data-type="movie" data-id="(\d+)">',  # not available?
+             r'tw-sound-flag-open-link" data-id="(\d+)" style=',  # not available?
+             r'data-movie-id="(\d+)"'),  # if not currently live, value may be 0
+            webpage, 'current live ID', default=None))
+        if is_live and not current_live:
             # fetch unfiltered /show to find running livestreams; we can't get ID of the password-protected livestream above
             webpage = self._download_webpage(
                 f'https://twitcasting.tv/{uploader_id}/show/', uploader_id,
                 note='Downloading live history')
-            is_live = self._search_regex(r'(?s)(<span\s*class="tw-movie-thumbnail-badge"\s*data-status="live">\s*LIVE)', webpage, 'is live?', default=None)
+            is_live = self._search_regex(self._PROTECTED_LIVE_RE, webpage, 'is live?', default=None)
             if is_live:
                 # get the first live; running live is always at the first
                 current_live = self._search_regex(
-                    r'(?s)<a\s+class="tw-movie-thumbnail"\s*href="/[^/]+/movie/(?P<video_id>\d+)"\s*>.+?</a>',
+                    r'(?s)<a\s+class="tw-movie-thumbnail2"\s*href="/[^/]+/movie/(?P<video_id>\d+)"\s*>.+?</a>',
                     webpage, 'current live ID 2', default=None, group='video_id')
         if not current_live:
             raise UserNotLive(video_id=uploader_id)
-        return self.url_result('https://twitcasting.tv/%s/movie/%s' % (uploader_id, current_live))
+        return self.url_result(f'https://twitcasting.tv/{uploader_id}/movie/{current_live}', TwitCastingIE)
 
 
 class TwitCastingUserIE(InfoExtractor):

yt_dlp/extractor/unsupported.py

@@ -48,6 +48,7 @@ class KnownDRMIE(UnsupportedInfoExtractor):
         r'joyn\.de',
         r'amazon\.(?:\w{2}\.)?\w+/gp/video',
         r'music\.amazon\.(?:\w{2}\.)?\w+',
+        r'(?:watch|front)\.njpwworld\.com',
     )
 
     _TESTS = [{
@@ -141,6 +142,13 @@ class KnownDRMIE(UnsupportedInfoExtractor):
         # https://github.com/yt-dlp/yt-dlp/issues/5767
         'url': 'https://www.hulu.com/movie/anthem-6b25fac9-da2b-45a3-8e09-e4156b0471cc',
         'only_matching': True,
+    }, {
+        # https://github.com/yt-dlp/yt-dlp/pull/8570
+        'url': 'https://watch.njpwworld.com/player/36447/series?assetType=series',
+        'only_matching': True,
+    }, {
+        'url': 'https://front.njpwworld.com/p/s_series_00563_16_bs',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/yandexvideo.py

@@ -194,7 +194,7 @@ class ZenYandexIE(InfoExtractor):
             'id': '60c7c443da18892ebfe85ed7',
             'ext': 'mp4',
             'title': 'ВОТ ЭТО Focus. Деды Морозы на гидроциклах',
-            'description': 'md5:f3db3d995763b9bbb7b56d4ccdedea89',
+            'description': 'md5:8684912f6086f298f8078d4af0e8a600',
             'thumbnail': 're:^https://avatars.dzeninfra.ru/',
             'uploader': 'AcademeG DailyStream'
         },
@@ -209,7 +209,7 @@ class ZenYandexIE(InfoExtractor):
             'id': '60c7c443da18892ebfe85ed7',
             'ext': 'mp4',
             'title': 'ВОТ ЭТО Focus. Деды Морозы на гидроциклах',
-            'description': 'md5:f3db3d995763b9bbb7b56d4ccdedea89',
+            'description': 'md5:8684912f6086f298f8078d4af0e8a600',
             'thumbnail': r're:^https://avatars\.dzeninfra\.ru/',
             'uploader': 'AcademeG DailyStream',
             'upload_date': '20191111',
@@ -258,7 +258,7 @@ class ZenYandexIE(InfoExtractor):
             video_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, video_id, note='Redirecting')
         data_json = self._search_json(
-            r'data\s*=', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
+            r'("data"\s*:|data\s*=)', webpage, 'metadata', video_id, contains_pattern=r'{["\']_*serverState_*video.+}')
         serverstate = self._search_regex(r'(_+serverState_+video-site_[^_]+_+)',
                                          webpage, 'server state').replace('State', 'Settings')
         uploader = self._search_regex(r'(<a\s*class=["\']card-channel-link[^"\']+["\'][^>]+>)',
@@ -266,22 +266,25 @@ class ZenYandexIE(InfoExtractor):
         uploader_name = extract_attributes(uploader).get('aria-label')
         video_json = try_get(data_json, lambda x: x[serverstate]['exportData']['video'], dict)
         stream_urls = try_get(video_json, lambda x: x['video']['streams'])
-        formats = []
+        formats, subtitles = [], {}
         for s_url in stream_urls:
             ext = determine_ext(s_url)
             if ext == 'mpd':
-                formats.extend(self._extract_mpd_formats(s_url, video_id, mpd_id='dash'))
+                fmts, subs = self._extract_mpd_formats_and_subtitles(s_url, video_id, mpd_id='dash')
             elif ext == 'm3u8':
-                formats.extend(self._extract_m3u8_formats(s_url, video_id, 'mp4'))
+                fmts, subs = self._extract_m3u8_formats_and_subtitles(s_url, video_id, 'mp4')
+            formats.extend(fmts)
+            subtitles = self._merge_subtitles(subtitles, subs)
         return {
             'id': video_id,
             'title': video_json.get('title') or self._og_search_title(webpage),
             'formats': formats,
+            'subtitles': subtitles,
             'duration': int_or_none(video_json.get('duration')),
             'view_count': int_or_none(video_json.get('views')),
             'timestamp': int_or_none(video_json.get('publicationDate')),
             'uploader': uploader_name or data_json.get('authorName') or try_get(data_json, lambda x: x['publisher']['name']),
-            'description': self._og_search_description(webpage) or try_get(data_json, lambda x: x['og']['description']),
+            'description': video_json.get('description') or self._og_search_description(webpage),
             'thumbnail': self._og_search_thumbnail(webpage) or try_get(data_json, lambda x: x['og']['imageUrl']),
         }
 
@@ -296,6 +299,7 @@ class ZenYandexChannelIE(InfoExtractor):
             'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56',
         },
         'playlist_mincount': 169,
+        'skip': 'The page does not exist',
     }, {
         'url': 'https://dzen.ru/tok_media',
         'info_dict': {
@@ -304,6 +308,7 @@ class ZenYandexChannelIE(InfoExtractor):
             'description': 'md5:a9e5b3c247b7fe29fd21371a428bcf56',
         },
         'playlist_mincount': 169,
+        'skip': 'The page does not exist',
     }, {
         'url': 'https://zen.yandex.ru/id/606fd806cc13cb3c58c05cf5',
         'info_dict': {
@@ -318,21 +323,21 @@ class ZenYandexChannelIE(InfoExtractor):
         'url': 'https://zen.yandex.ru/jony_me',
         'info_dict': {
             'id': 'jony_me',
-            'description': 'md5:a2c62b4ef5cf3e3efb13d25f61f739e1',
+            'description': 'md5:ce0a5cad2752ab58701b5497835b2cc5',
             'title': 'JONY ',
         },
-        'playlist_count': 20,
+        'playlist_count': 18,
     }, {
         # Test that the playlist extractor finishes extracting when the
         # channel has more than one page of entries
         'url': 'https://zen.yandex.ru/tatyanareva',
         'info_dict': {
             'id': 'tatyanareva',
-            'description': 'md5:296b588d60841c3756c9105f237b70c6',
+            'description': 'md5:40a1e51f174369ec3ba9d657734ac31f',
             'title': 'Татьяна Рева',
             'entries': 'maxcount:200',
         },
-        'playlist_count': 46,
+        'playlist_mincount': 46,
     }, {
         'url': 'https://dzen.ru/id/606fd806cc13cb3c58c05cf5',
         'info_dict': {
@@ -375,7 +380,7 @@ class ZenYandexChannelIE(InfoExtractor):
             item_id = self._match_id(redirect)
             webpage = self._download_webpage(redirect, item_id, note='Redirecting')
         data = self._search_json(
-            r'var\s+data\s*=', webpage, 'channel data', item_id, contains_pattern=r'{\"__serverState__.+}')
+            r'("data"\s*:|data\s*=)', webpage, 'channel data', item_id, contains_pattern=r'{\"__serverState__.+}')
         server_state_json = traverse_obj(data, lambda k, _: k.startswith('__serverState__'), get_all=False)
         server_settings_json = traverse_obj(data, lambda k, _: k.startswith('__serverSettings__'), get_all=False)
 

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2023.11.14'
+__version__ = '2023.11.16'
 
-RELEASE_GIT_HEAD = 'a9d3f4b20a3533d2a40104c85bc2cc6c2564c800'
+RELEASE_GIT_HEAD = '24f827875c6ba513f12ed09a3aef2bbed223760d'
 
 VARIANT = None
 
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
 
 ORIGIN = 'yt-dlp/yt-dlp'
 
-_pkg_version = '2023.11.14'
+_pkg_version = '2023.11.16'