do not return possibly zero timestamp

Authored by: bashonly

.github/workflows/build.yml

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

README.md

@@ -1792,7 +1792,7 @@ The following extractors use this feature:
 #### youtube
 * `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
 * `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
-* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
+* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
 * `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata.  See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
 * `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
 * `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)

pyproject.toml

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

yt_dlp/extractor/_extractors.py

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

yt_dlp/extractor/amcnetworks.py

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

yt_dlp/extractor/bitchute.py

@@ -1,30 +1,32 @@
 import functools
+import json
 import re
 
 from .common import InfoExtractor
 from ..networking import HEADRequest
+from ..networking.exceptions import HTTPError
 from ..utils import (
     ExtractorError,
     OnDemandPagedList,
     clean_html,
-    extract_attributes,
+    determine_ext,
+    format_field,
     get_element_by_class,
-    get_element_by_id,
-    get_element_html_by_class,
     get_elements_html_by_class,
     int_or_none,
     orderedSet,
     parse_count,
     parse_duration,
-    traverse_obj,
-    unified_strdate,
+    parse_iso8601,
+    url_or_none,
     urlencode_postdata,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BitChuteIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/]+)/(?P<id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:(?:www|old)\.)?bitchute\.com/(?:video|embed|torrent/[^/?#]+)/(?P<id>[^/?#&]+)'
     _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
     _TESTS = [{
         'url': 'https://www.bitchute.com/video/UGlrF9o9b-Q/',
@@ -34,12 +36,17 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'title': 'This is the first video on #BitChute !',
             'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20170103',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 16.0,
+            'timestamp': 1483425443,
         },
     }, {
         # test case: video with different channel and uploader
@@ -49,13 +56,18 @@ class BitChuteIE(InfoExtractor):
             'id': 'Yti_j9A-UZ4',
             'ext': 'mp4',
             'title': 'Israel at War | Full Measure',
-            'description': 'md5:38cf7bc6f42da1a877835539111c69ef',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:e60198b89971966d6030d22b3268f08f',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'sharylattkisson',
             'upload_date': '20231106',
             'uploader_url': 'https://www.bitchute.com/profile/9K0kUWA9zmd9/',
             'channel': 'Full Measure with Sharyl Attkisson',
             'channel_url': 'https://www.bitchute.com/channel/sharylattkisson/',
+            'uploader_id': '9K0kUWA9zmd9',
+            'channel_id': 'NpdxoCRv3ZLb',
+            'view_count': int,
+            'duration': 554.0,
+            'timestamp': 1699296106,
         },
     }, {
         # video not downloadable in browser, but we can recover it
@@ -66,25 +78,21 @@ class BitChuteIE(InfoExtractor):
             'ext': 'mp4',
             'filesize': 71537926,
             'title': 'STYXHEXENHAMMER666 - Election Fraud, Clinton 2020, EU Armies, and Gun Control',
-            'description': 'md5:228ee93bd840a24938f536aeac9cf749',
-            'thumbnail': r're:^https?://.*\.jpg$',
+            'description': 'md5:2029c7c212ccd4b040f52bb2d036ef4e',
+            'thumbnail': r're:https?://.+/.+\.jpg$',
             'uploader': 'BitChute',
             'upload_date': '20181113',
             'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
             'channel': 'BitChute',
             'channel_url': 'https://www.bitchute.com/channel/bitchute/',
+            'uploader_id': 'I5NgtHZn9vPj',
+            'channel_id': '1VBwRfyNcKdX',
+            'view_count': int,
+            'duration': 1701.0,
+            'tags': ['bitchute'],
+            'timestamp': 1542130287,
         },
         'params': {'check_formats': None},
-    }, {
-        # restricted video
-        'url': 'https://www.bitchute.com/video/WEnQU7XGcTdl/',
-        'info_dict': {
-            'id': 'WEnQU7XGcTdl',
-            'ext': 'mp4',
-            'title': 'Impartial Truth - Ein Letzter Appell an die Vernunft',
-        },
-        'params': {'skip_download': True},
-        'skip': 'Georestricted in DE',
     }, {
         'url': 'https://www.bitchute.com/embed/lbb5G1hjPhw/',
         'only_matching': True,
@@ -96,11 +104,8 @@ class BitChuteIE(InfoExtractor):
         'only_matching': True,
     }]
     _GEO_BYPASS = False
-
-    _HEADERS = {
-        'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/69.0.3497.57 Safari/537.36',
-        'Referer': 'https://www.bitchute.com/',
-    }
+    _UPLOADER_URL_TMPL = 'https://www.bitchute.com/profile/%s/'
+    _CHANNEL_URL_TMPL = 'https://www.bitchute.com/channel/%s/'
 
     def _check_format(self, video_url, video_id):
         urls = orderedSet(
@@ -112,7 +117,7 @@ class BitChuteIE(InfoExtractor):
         for url in urls:
             try:
                 response = self._request_webpage(
-                    HEADRequest(url), video_id=video_id, note=f'Checking {url}', headers=self._HEADERS)
+                    HEADRequest(url), video_id=video_id, note=f'Checking {url}')
             except ExtractorError as e:
                 self.to_screen(f'{video_id}: URL is invalid, skipping: {e.cause}')
                 continue
@@ -121,54 +126,79 @@ class BitChuteIE(InfoExtractor):
                 'filesize': int_or_none(response.headers.get('Content-Length')),
             }
 
-    def _raise_if_restricted(self, webpage):
-        page_title = clean_html(get_element_by_class('page-title', webpage)) or ''
-        if re.fullmatch(r'(?:Channel|Video) Restricted', page_title):
-            reason = clean_html(get_element_by_id('page-detail', webpage)) or page_title
-            self.raise_geo_restricted(reason)
-
-    @staticmethod
-    def _make_url(html):
-        path = extract_attributes(get_element_html_by_class('spa', html) or '').get('href')
-        return urljoin('https://www.bitchute.com', path)
+    def _call_api(self, endpoint, data, display_id, fatal=True):
+        note = endpoint.rpartition('/')[2]
+        try:
+            return self._download_json(
+                f'https://api.bitchute.com/api/beta/{endpoint}', display_id,
+                f'Downloading {note} API JSON', f'Unable to download {note} API JSON',
+                data=json.dumps(data).encode(),
+                headers={
+                    'Accept': 'application/json',
+                    'Content-Type': 'application/json',
+                })
+        except ExtractorError as e:
+            if isinstance(e.cause, HTTPError) and e.cause.status == 403:
+                errors = '. '.join(traverse_obj(e.cause.response.read().decode(), (
+                    {json.loads}, 'errors', lambda _, v: v['context'] == 'reason', 'message', {str})))
+                if errors and 'location' in errors:
+                    # Can always be fatal since the video/media call will reach this code first
+                    self.raise_geo_restricted(errors)
+            if fatal:
+                raise
+            self.report_warning(e.msg)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
-        webpage = self._download_webpage(
-            f'https://old.bitchute.com/video/{video_id}', video_id, headers=self._HEADERS)
-
-        self._raise_if_restricted(webpage)
-        publish_date = clean_html(get_element_by_class('video-publish-date', webpage))
-        entries = self._parse_html5_media_entries(url, webpage, video_id)
+        data = {'video_id': video_id}
+        media_url = self._call_api('video/media', data, video_id)['media_url']
 
         formats = []
-        for format_ in traverse_obj(entries, (0, 'formats', ...)):
+        if determine_ext(media_url) == 'm3u8':
+            formats.extend(
+                self._extract_m3u8_formats(media_url, video_id, 'mp4', m3u8_id='hls', live=True))
+        else:
             if self.get_param('check_formats') is not False:
-                format_.update(self._check_format(format_.pop('url'), video_id) or {})
-                if 'url' not in format_:
-                    continue
-            formats.append(format_)
+                if fmt := self._check_format(media_url, video_id):
+                    formats.append(fmt)
+            else:
+                formats.append({'url': media_url})
 
         if not formats:
             self.raise_no_formats(
                 'Video is unavailable. Please make sure this video is playable in the browser '
                 'before reporting this issue.', expected=True, video_id=video_id)
 
-        details = get_element_by_class('details', webpage) or ''
-        uploader_html = get_element_html_by_class('creator', details) or ''
-        channel_html = get_element_html_by_class('name', details) or ''
+        video = self._call_api('video', data, video_id, fatal=False)
+        channel = None
+        if channel_id := traverse_obj(video, ('channel', 'channel_id', {str})):
+            channel = self._call_api('channel', {'channel_id': channel_id}, video_id, fatal=False)
 
         return {
+            **traverse_obj(video, {
+                'title': ('video_name', {str}),
+                'description': ('description', {str}),
+                'thumbnail': ('thumbnail_url', {url_or_none}),
+                'channel': ('channel', 'channel_name', {str}),
+                'channel_id': ('channel', 'channel_id', {str}),
+                'channel_url': ('channel', 'channel_url', {urljoin('https://www.bitchute.com/')}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+                'timestamp': ('date_published', {parse_iso8601}),
+                'duration': ('duration', {parse_duration}),
+                'tags': ('hashtags', ..., {str}, filter, all, filter),
+                'view_count': ('view_count', {int_or_none}),
+                'is_live': ('state_id', {lambda x: x == 'live'}),
+            }),
+            **traverse_obj(channel, {
+                'channel': ('channel_name', {str}),
+                'channel_id': ('channel_id', {str}),
+                'channel_url': ('url_slug', {format_field(template=self._CHANNEL_URL_TMPL)}, filter),
+                'uploader': ('profile_name', {str}),
+                'uploader_id': ('profile_id', {str}),
+                'uploader_url': ('profile_id', {format_field(template=self._UPLOADER_URL_TMPL)}, filter),
+            }),
             'id': video_id,
-            'title': self._html_extract_title(webpage) or self._og_search_title(webpage),
-            'description': self._og_search_description(webpage, default=None),
-            'thumbnail': self._og_search_thumbnail(webpage),
-            'uploader': clean_html(uploader_html),
-            'uploader_url': self._make_url(uploader_html),
-            'channel': clean_html(channel_html),
-            'channel_url': self._make_url(channel_html),
-            'upload_date': unified_strdate(self._search_regex(
-                r'at \d+:\d+ UTC on (.+?)\.', publish_date, 'upload date', fatal=False)),
             'formats': formats,
         }
 
@@ -190,7 +220,7 @@ class BitChuteChannelIE(InfoExtractor):
                     'ext': 'mp4',
                     'title': 'This is the first video on #BitChute !',
                     'description': 'md5:a0337e7b1fe39e32336974af8173a034',
-                    'thumbnail': r're:^https?://.*\.jpg$',
+                    'thumbnail': r're:https?://.+/.+\.jpg$',
                     'uploader': 'BitChute',
                     'upload_date': '20170103',
                     'uploader_url': 'https://www.bitchute.com/profile/I5NgtHZn9vPj/',
@@ -198,6 +228,9 @@ class BitChuteChannelIE(InfoExtractor):
                     'channel_url': 'https://www.bitchute.com/channel/bitchute/',
                     'duration': 16,
                     'view_count': int,
+                    'uploader_id': 'I5NgtHZn9vPj',
+                    'channel_id': '1VBwRfyNcKdX',
+                    'timestamp': 1483425443,
                 },
             },
         ],
@@ -213,6 +246,7 @@ class BitChuteChannelIE(InfoExtractor):
             'title': 'Bruce MacDonald and "The Light of Darkness"',
             'description': 'md5:747724ef404eebdfc04277714f81863e',
         },
+        'skip': '404 Not Found',
     }, {
         'url': 'https://old.bitchute.com/playlist/wV9Imujxasw9/',
         'only_matching': True,

yt_dlp/extractor/cartoonnetwork.py

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

yt_dlp/extractor/espn.py

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

yt_dlp/extractor/firsttv.py

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

yt_dlp/extractor/gamespot.py

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

yt_dlp/extractor/iprima.py

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

yt_dlp/extractor/jiosaavn.py

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

yt_dlp/extractor/lrt.py

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

yt_dlp/extractor/nebula.py

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

yt_dlp/extractor/niconico.py

@@ -16,6 +16,7 @@ from ..utils import (
     determine_ext,
     float_or_none,
     int_or_none,
+    parse_bitrate,
     parse_duration,
     parse_iso8601,
     parse_qs,
@@ -23,7 +24,6 @@ from ..utils import (
     qualities,
     remove_start,
     str_or_none,
-    try_get,
     unescapeHTML,
     unified_timestamp,
     update_url_query,
@@ -785,8 +785,6 @@ class NiconicoLiveIE(NiconicoBaseIE):
         'only_matching': True,
     }]
 
-    _KNOWN_LATENCY = ('high', 'low')
-
     def _real_extract(self, url):
         video_id = self._match_id(url)
         webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
@@ -802,22 +800,19 @@ class NiconicoLiveIE(NiconicoBaseIE):
         })
 
         hostname = remove_start(urllib.parse.urlparse(urlh.url).hostname, 'sp.')
-        latency = try_get(self._configuration_arg('latency'), lambda x: x[0])
-        if latency not in self._KNOWN_LATENCY:
-            latency = 'high'
 
         ws = self._request_webpage(
             Request(ws_url, headers={'Origin': f'https://{hostname}'}),
             video_id=video_id, note='Connecting to WebSocket server')
 
-        self.write_debug('[debug] Sending HLS server request')
+        self.write_debug('Sending HLS server request')
         ws.send(json.dumps({
             'type': 'startWatching',
             'data': {
                 'stream': {
                     'quality': 'abr',
-                    'protocol': 'hls+fmp4',
-                    'latency': latency,
+                    'protocol': 'hls',
+                    'latency': 'high',
                     'accessRightMethod': 'single_cookie',
                     'chasePlay': False,
                 },
@@ -881,18 +876,29 @@ class NiconicoLiveIE(NiconicoBaseIE):
         for cookie in cookies:
             self._set_cookie(
                 cookie['domain'], cookie['name'], cookie['value'],
-                expire_time=unified_timestamp(cookie['expires']), path=cookie['path'], secure=cookie['secure'])
+                expire_time=unified_timestamp(cookie.get('expires')), path=cookie['path'], secure=cookie['secure'])
+
+        fmt_common = {
+            'live_latency': 'high',
+            'origin': hostname,
+            'protocol': 'niconico_live',
+            'video_id': video_id,
+            'ws': ws,
+        }
+        q_iter = (q for q in qualities[1:] if not q.startswith('audio_'))  # ignore initial 'abr'
+        a_map = {96: 'audio_low', 192: 'audio_high'}
 
         formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
-        for fmt, q in zip(formats, reversed(qualities[1:])):
-            fmt.update({
-                'format_id': q,
-                'protocol': 'niconico_live',
-                'ws': ws,
-                'video_id': video_id,
-                'live_latency': latency,
-                'origin': hostname,
-            })
+        for fmt in formats:
+            if fmt.get('acodec') == 'none':
+                fmt['format_id'] = next(q_iter, fmt['format_id'])
+            elif fmt.get('vcodec') == 'none':
+                abr = parse_bitrate(fmt['url'].lower())
+                fmt.update({
+                    'abr': abr,
+                    'format_id': a_map.get(abr, fmt['format_id']),
+                })
+            fmt.update(fmt_common)
 
         return {
             'id': video_id,

yt_dlp/extractor/nytimes.py

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

yt_dlp/extractor/once.py

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

yt_dlp/extractor/playsuisse.py

@@ -7,11 +7,13 @@ from .common import InfoExtractor
 from ..utils import (
     ExtractorError,
     int_or_none,
+    join_nonempty,
     parse_qs,
     traverse_obj,
     update_url_query,
     urlencode_postdata,
 )
+from ..utils.traversal import unpack
 
 
 class PlaySuisseIE(InfoExtractor):
@@ -26,12 +28,12 @@ class PlaySuisseIE(InfoExtractor):
         {
             # episode in a series
             'url': 'https://www.playsuisse.ch/watch/763182?episodeId=763211',
-            'md5': '82df2a470b2dfa60c2d33772a8a60cf8',
+            'md5': 'e20d1ede6872a03b41905ca1060a1ef2',
             'info_dict': {
                 'id': '763211',
                 'ext': 'mp4',
                 'title': 'Knochen',
-                'description': 'md5:8ea7a8076ba000cd9e8bc132fd0afdd8',
+                'description': 'md5:3bdd80e2ce20227c47aab1df2a79a519',
                 'duration': 3344,
                 'series': 'Wilder',
                 'season': 'Season 1',
@@ -42,24 +44,33 @@ class PlaySuisseIE(InfoExtractor):
             },
         }, {
             # film
-            'url': 'https://www.playsuisse.ch/watch/808675',
-            'md5': '818b94c1d2d7c4beef953f12cb8f3e75',
+            'url': 'https://www.playsuisse.ch/detail/2573198',
+            'md5': '1f115bb0a5191477b1a5771643a4283d',
             'info_dict': {
-                'id': '808675',
+                'id': '2573198',
                 'ext': 'mp4',
-                'title': 'Der Läufer',
-                'description': 'md5:9f61265c7e6dcc3e046137a792b275fd',
-                'duration': 5280,
+                'title': 'Azor',
+                'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
+                'genres': ['Fiction'],
+                'creators': ['Andreas Fontana'],
+                'cast': ['Fabrizio Rongione', 'Stéphanie Cléau', 'Gilles Privat', 'Alexandre Trocki'],
+                'location': 'France; Argentine',
+                'release_year': 2021,
+                'duration': 5981,
                 'thumbnail': 're:https://playsuisse-img.akamaized.net/',
             },
         }, {
             # series (treated as a playlist)
             'url': 'https://www.playsuisse.ch/detail/1115687',
             'info_dict': {
-                'description': 'md5:e4a2ae29a8895823045b5c3145a02aa3',
                 'id': '1115687',
                 'series': 'They all came out to Montreux',
                 'title': 'They all came out to Montreux',
+                'description': 'md5:0fefd8c5b4468a0bb35e916887681520',
+                'genres': ['Documentary'],
+                'creators': ['Oliver Murray'],
+                'location': 'Switzerland',
+                'release_year': 2021,
             },
             'playlist': [{
                 'info_dict': {
@@ -120,6 +131,12 @@ class PlaySuisseIE(InfoExtractor):
             id
             name
             description
+            descriptionLong
+            year
+            contentTypes
+            directors
+            mainCast
+            productionCountries
             duration
             episodeNumber
             seasonNumber
@@ -215,9 +232,7 @@ class PlaySuisseIE(InfoExtractor):
         if not self._ID_TOKEN:
             raise ExtractorError('Login failed')
 
-    def _get_media_data(self, media_id):
-        # NOTE In the web app, the "locale" header is used to switch between languages,
-        # However this doesn't seem to take effect when passing the header here.
+    def _get_media_data(self, media_id, locale=None):
         response = self._download_json(
             'https://www.playsuisse.ch/api/graphql',
             media_id, data=json.dumps({
@@ -225,7 +240,7 @@ class PlaySuisseIE(InfoExtractor):
                 'query': self._GRAPHQL_QUERY,
                 'variables': {'assetId': media_id},
             }).encode(),
-            headers={'Content-Type': 'application/json', 'locale': 'de'})
+            headers={'Content-Type': 'application/json', 'locale': locale or 'de'})
 
         return response['data']['assetV2']
 
@@ -234,7 +249,7 @@ class PlaySuisseIE(InfoExtractor):
             self.raise_login_required(method='password')
 
         media_id = self._match_id(url)
-        media_data = self._get_media_data(media_id)
+        media_data = self._get_media_data(media_id, traverse_obj(parse_qs(url), ('locale', 0)))
         info = self._extract_single(media_data)
         if media_data.get('episodes'):
             info.update({
@@ -257,15 +272,22 @@ class PlaySuisseIE(InfoExtractor):
             self._merge_subtitles(subs, target=subtitles)
 
         return {
-            'id': media_data['id'],
-            'title': media_data.get('name'),
-            'description': media_data.get('description'),
             'thumbnails': thumbnails,
-            'duration': int_or_none(media_data.get('duration')),
             'formats': formats,
             'subtitles': subtitles,
-            'series': media_data.get('seriesName'),
-            'season_number': int_or_none(media_data.get('seasonNumber')),
-            'episode': media_data.get('name') if media_data.get('episodeNumber') else None,
-            'episode_number': int_or_none(media_data.get('episodeNumber')),
+            **traverse_obj(media_data, {
+                'id': ('id', {str}),
+                'title': ('name', {str}),
+                'description': (('descriptionLong', 'description'), {str}, any),
+                'genres': ('contentTypes', ..., {str}),
+                'creators': ('directors', ..., {str}),
+                'cast': ('mainCast', ..., {str}),
+                'location': ('productionCountries', ..., {str}, all, {unpack(join_nonempty, delim='; ')}, filter),
+                'release_year': ('year', {str}, {lambda x: x[:4]}, {int_or_none}),
+                'duration': ('duration', {int_or_none}),
+                'series': ('seriesName', {str}),
+                'season_number': ('seasonNumber', {int_or_none}),
+                'episode': ('name', {str}, {lambda x: x if media_data['episodeNumber'] is not None else None}),
+                'episode_number': ('episodeNumber', {int_or_none}),
+            }),
         }

yt_dlp/extractor/sprout.py

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

yt_dlp/extractor/svt.py

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

yt_dlp/extractor/theplatform.py

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

yt_dlp/extractor/twitch.py

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

yt_dlp/extractor/voxmedia.py

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

yt_dlp/extractor/wat.py

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

yt_dlp/extractor/weverse.py

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

yt_dlp/extractor/youtube/_clip.py

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

yt_dlp/extractor/youtube/_redirect.py

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

yt_dlp/extractor/youtube/_video.py

@@ -376,6 +376,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Afrojack',
                 'uploader_url': 'https://www.youtube.com/@Afrojack',
                 'uploader_id': '@Afrojack',
+                'media_type': 'video',
             },
             'params': {
                 'youtube_include_dash_manifest': True,
@@ -413,10 +414,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1401991663,
+                'media_type': 'video',
             },
         },
         {
-            'note': 'Age-gate video with embed allowed in public site',
+            'note': 'Formerly an age-gate video with embed allowed in public site',
             'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
             'info_dict': {
                 'id': 'HsUATh_Nc2U',
@@ -424,8 +426,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'title': 'Godzilla 2 (Official Video)',
                 'description': 'md5:bf77e03fcae5529475e500129b05668a',
                 'upload_date': '20200408',
-                'age_limit': 18,
-                'availability': 'needs_auth',
+                'age_limit': 0,
+                'availability': 'public',
                 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
                 'channel': 'FlyingKitty',
                 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
@@ -443,8 +445,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@FlyingKitty900',
                 'comment_count': int,
                 'channel_is_verified': True,
+                'media_type': 'video',
             },
-            'skip': 'Age-restricted; requires authentication',
         },
         {
             'note': 'Age-gate video embedable only with clientScreen=EMBED',
@@ -507,6 +509,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Herr Lurik',
                 'uploader_url': 'https://www.youtube.com/@HerrLurik',
                 'uploader_id': '@HerrLurik',
+                'media_type': 'video',
             },
         },
         {
@@ -546,6 +549,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'deadmau5',
                 'uploader_url': 'https://www.youtube.com/@deadmau5',
                 'uploader_id': '@deadmau5',
+                'media_type': 'video',
             },
             'expected_warnings': [
                 'DASH manifest missing',
@@ -581,6 +585,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@Olympics',
                 'channel_is_verified': True,
                 'timestamp': 1440707674,
+                'media_type': 'livestream',
             },
             'params': {
                 'skip_download': 'requires avconv',
@@ -615,6 +620,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@AllenMeow',
                 'uploader_id': '@AllenMeow',
                 'timestamp': 1299776999,
+                'media_type': 'video',
             },
         },
         # url_encoded_fmt_stream_map is empty string
@@ -809,6 +815,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'like_count': int,
                 'age_limit': 0,
                 'channel_follower_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -868,6 +875,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@BKCHarvard',
                 'uploader_url': 'https://www.youtube.com/@BKCHarvard',
                 'timestamp': 1422422076,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -904,6 +912,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1447987198,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -968,6 +977,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'timestamp': 1484761047,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1070,6 +1080,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'tags': 'count:11',
                 'live_status': 'not_live',
                 'channel_follower_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1124,6 +1135,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@ElevageOrVert',
                 'uploader_id': '@ElevageOrVert',
                 'timestamp': 1497343210,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1163,6 +1175,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1377976349,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1207,6 +1220,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_follower_count': int,
                 'uploader': 'The Cinematic Orchestra',
                 'comment_count': int,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1275,6 +1289,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_url': 'https://www.youtube.com/@walkaroundjapan7124',
                 'uploader_id': '@walkaroundjapan7124',
                 'timestamp': 1605884416,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1371,6 +1386,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1395685455,
+                'media_type': 'video',
             }, 'params': {'format': 'mhtml', 'skip_download': True},
         }, {
             # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
@@ -1401,6 +1417,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@LeonNguyen',
                 'heatmap': 'count:100',
                 'timestamp': 1641170939,
+                'media_type': 'video',
             },
         }, {
             # date text is premiered video, ensure upload date in UTC (published 1641172509)
@@ -1434,6 +1451,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
                 'timestamp': 1641172509,
+                'media_type': 'video',
             },
         },
         {   # continuous livestream.
@@ -1495,6 +1513,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'Lesmiscore',
                 'uploader_url': 'https://www.youtube.com/@lesmiscore',
                 'timestamp': 1648005313,
+                'media_type': 'short',
             },
         }, {
             # Prefer primary title+description language metadata by default
@@ -1523,6 +1542,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@coletdjnz',
                 'uploader': 'cole-dlp-test-acc',
                 'timestamp': 1662677394,
+                'media_type': 'video',
             },
             'params': {'skip_download': True},
         }, {
@@ -1551,6 +1571,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader': 'cole-dlp-test-acc',
                 'timestamp': 1659073275,
                 'like_count': int,
+                'media_type': 'video',
             },
             'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
             'expected_warnings': [r'Preferring "fr" translated fields'],
@@ -1587,6 +1608,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
+                'media_type': 'video',
             },
             'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
         }, {
@@ -1687,6 +1709,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'comment_count': int,
                 'channel_is_verified': True,
                 'heatmap': 'count:100',
+                'media_type': 'video',
             },
             'params': {
                 'extractor_args': {'youtube': {'player_client': ['ios'], 'player_skip': ['webpage']}},
@@ -1719,6 +1742,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'channel_follower_count': int,
                 'categories': ['People & Blogs'],
                 'tags': [],
+                'media_type': 'short',
             },
         },
     ]
@@ -1754,6 +1778,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'uploader_id': '@ChristopherSykesDocumentaries',
                 'heatmap': 'count:100',
                 'timestamp': 1211825920,
+                'media_type': 'video',
             },
             'params': {
                 'skip_download': True,
@@ -1819,6 +1844,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     else:
                         retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
                     continue
+
+                # Formats from ended premieres will be missing a manifest_url
+                # See https://github.com/yt-dlp/yt-dlp/issues/8543
+                if not f.get('manifest_url'):
+                    break
+
                 return f['manifest_url'], f['manifest_stream_number'], is_live
             return None
 
@@ -3109,9 +3140,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 else:
                     prs.append(pr)
 
+            # web_embedded can work around age-gate and age-verification for some embeddable videos
+            if self._is_agegated(pr) and variant != 'web_embedded':
+                append_client(f'web_embedded.{base_client}')
+            # Unauthenticated users will only get web_embedded client formats if age-gated
+            if self._is_agegated(pr) and not self.is_authenticated:
+                self.to_screen(
+                    f'{video_id}: This video is age-restricted; some formats may be missing '
+                    f'without authentication. {self._youtube_login_hint}', only_once=True)
+
             # EU countries require age-verification for accounts to access age-restricted videos
             # If account is not age-verified, _is_agegated() will be truthy for non-embedded clients
-            if self.is_authenticated and self._is_agegated(pr):
+            embedding_is_disabled = variant == 'web_embedded' and self._is_unplayable(pr)
+            if self.is_authenticated and (self._is_agegated(pr) or embedding_is_disabled):
                 self.to_screen(
                     f'{video_id}: This video is age-restricted and YouTube is requiring '
                     'account age-verification; some formats may be missing', only_once=True)
@@ -3771,7 +3812,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'tags': keywords,
             'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
             'live_status': live_status,
-            'media_type': 'livestream' if get_first(video_details, 'isLiveContent') else None,
+            'media_type': (
+                'livestream' if get_first(video_details, 'isLiveContent')
+                else 'short' if get_first(microformats, 'isShortsEligible')
+                else 'video'),
             'release_timestamp': live_start_time,
             '_format_sort_fields': (  # source_preference is lower for potentially damaged formats
                 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec', 'channels', 'acodec', 'lang', 'proto'),

yt_dlp/options.py

@@ -470,7 +470,7 @@ def create_parser():
     general.add_option(
         '--live-from-start',
         action='store_true', dest='live_from_start',
-        help='Download livestreams from the start. Currently only supported for YouTube (Experimental)')
+        help='Download livestreams from the start. Currently only supported for YouTube (experimental) and Twitch')
     general.add_option(
         '--no-live-from-start',
         action='store_false', dest='live_from_start',