yt-dlp 2026.1.16.233125.dev0__py3-none-any.whl → 2026.1.19.233146.dev0__py3-none-any.whl

yt_dlp/extractor/_extractors.py

@@ -1,32 +1,4 @@
 # flake8: noqa: F401
-# isort: off
-
-from .youtube import (  # Youtube is moved to the top to improve performance
-    YoutubeIE,
-    YoutubeClipIE,
-    YoutubeFavouritesIE,
-    YoutubeNotificationsIE,
-    YoutubeHistoryIE,
-    YoutubeTabIE,
-    YoutubeLivestreamEmbedIE,
-    YoutubePlaylistIE,
-    YoutubeRecommendedIE,
-    YoutubeSearchDateIE,
-    YoutubeSearchIE,
-    YoutubeSearchURLIE,
-    YoutubeMusicSearchURLIE,
-    YoutubeSubscriptionsIE,
-    YoutubeTruncatedIDIE,
-    YoutubeTruncatedURLIE,
-    YoutubeYtBeIE,
-    YoutubeYtUserIE,
-    YoutubeWatchLaterIE,
-    YoutubeShortsAudioPivotIE,
-    YoutubeConsentRedirectIE,
-)
-
-# isort: on
-
 from .abc import (
     ABCIE,
     ABCIViewIE,
@@ -2551,6 +2523,29 @@ from .youporn import (
     YouPornTagIE,
     YouPornVideosIE,
 )
+from .youtube import (
+    YoutubeClipIE,
+    YoutubeConsentRedirectIE,
+    YoutubeFavouritesIE,
+    YoutubeHistoryIE,
+    YoutubeIE,
+    YoutubeLivestreamEmbedIE,
+    YoutubeMusicSearchURLIE,
+    YoutubeNotificationsIE,
+    YoutubePlaylistIE,
+    YoutubeRecommendedIE,
+    YoutubeSearchDateIE,
+    YoutubeSearchIE,
+    YoutubeSearchURLIE,
+    YoutubeShortsAudioPivotIE,
+    YoutubeSubscriptionsIE,
+    YoutubeTabIE,
+    YoutubeTruncatedIDIE,
+    YoutubeTruncatedURLIE,
+    YoutubeWatchLaterIE,
+    YoutubeYtBeIE,
+    YoutubeYtUserIE,
+)
 from .zaiko import (
     ZaikoETicketIE,
     ZaikoIE,

yt_dlp/extractor/cbc.py

@@ -105,7 +105,7 @@ class CBCIE(InfoExtractor):
         # multiple CBC.APP.Caffeine.initInstance(...)
         'url': 'http://www.cbc.ca/news/canada/calgary/dog-indoor-exercise-winter-1.3928238',
         'info_dict': {
-            'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',  # FIXME: actual title includes " | CBC News"
+            'title': 'Keep Rover active during the deep freeze with doggie pushups and other fun indoor tasks',
             'id': 'dog-indoor-exercise-winter-1.3928238',
             'description': 'md5:c18552e41726ee95bd75210d1ca9194c',
         },
@@ -134,6 +134,13 @@ class CBCIE(InfoExtractor):
         title = (self._og_search_title(webpage, default=None)
                  or self._html_search_meta('twitter:title', webpage, 'title', default=None)
                  or self._html_extract_title(webpage))
+        title = self._search_regex(
+            r'^(?P<title>.+?)(?:\s*[|–-]\s*CBC.*)?$',
+            title, 'cleaned title', group='title', default=title)
+        data = self._search_json(
+            r'window\.__INITIAL_STATE__\s*=', webpage,
+            'initial state', display_id, default={}, transform_source=js_to_json)
+
         entries = [
             self._extract_player_init(player_init, display_id)
             for player_init in re.findall(r'CBC\.APP\.Caffeine\.initInstance\(({.+?})\);', webpage)]
@@ -143,6 +150,11 @@ class CBCIE(InfoExtractor):
                 r'<div[^>]+\bid=["\']player-(\d+)',
                 r'guid["\']\s*:\s*["\'](\d+)'):
             media_ids.extend(re.findall(media_id_re, webpage))
+        media_ids.extend(traverse_obj(data, (
+            'detail', 'content', 'body', ..., 'content',
+            lambda _, v: v['type'] == 'polopoly_media', 'content', 'sourceId', {str})))
+        if content_id := traverse_obj(data, ('app', 'contentId', {str})):
+            media_ids.append(content_id)
         entries.extend([
             self.url_result(f'cbcplayer:{media_id}', 'CBCPlayer', media_id)
             for media_id in orderedSet(media_ids)])
@@ -268,7 +280,7 @@ class CBCPlayerIE(InfoExtractor):
             'duration': 2692.833,
             'subtitles': {
                 'en-US': [{
-                    'name': 'English Captions',
+                    'name': r're:English',
                     'url': 'https://cbchls.akamaized.net/delivery/news-shows/2024/06/17/NAT_JUN16-00-55-00/NAT_JUN16_cc.vtt',
                 }],
             },
@@ -322,6 +334,7 @@ class CBCPlayerIE(InfoExtractor):
             'categories': ['Olympics Summer Soccer', 'Summer Olympics Replays', 'Summer Olympics Soccer Replays'],
             'location': 'Canada',
         },
+        'skip': 'Video no longer available',
         'params': {'skip_download': 'm3u8'},
     }, {
         'url': 'https://www.cbc.ca/player/play/video/9.6459530',
@@ -380,7 +393,8 @@ class CBCPlayerIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(f'https://www.cbc.ca/player/play/{video_id}', video_id)
         data = self._search_json(
-            r'window\.__INITIAL_STATE__\s*=', webpage, 'initial state', video_id)['video']['currentClip']
+            r'window\.__INITIAL_STATE__\s*=', webpage,
+            'initial state', video_id, transform_source=js_to_json)['video']['currentClip']
         assets = traverse_obj(
             data, ('media', 'assets', lambda _, v: url_or_none(v['key']) and v['type']))
 
@@ -492,12 +506,14 @@ class CBCPlayerPlaylistIE(InfoExtractor):
         'info_dict': {
             'id': 'news/tv shows/the national/latest broadcast',
         },
+        'skip': 'Playlist no longer available',
     }, {
         'url': 'https://www.cbc.ca/player/news/Canada/North',
         'playlist_mincount': 25,
         'info_dict': {
             'id': 'news/canada/north',
         },
+        'skip': 'Playlist no longer available',
     }]
 
     def _real_extract(self, url):

yt_dlp/extractor/ccc.py

@@ -18,23 +18,41 @@ class CCCIE(InfoExtractor):
             'id': '1839',
             'ext': 'mp4',
             'title': 'Introduction to Processor Design',
-            'creator': 'byterazor',
+            'creators': ['byterazor'],
             'description': 'md5:df55f6d073d4ceae55aae6f2fd98a0ac',
             'thumbnail': r're:^https?://.*\.jpg$',
             'upload_date': '20131228',
             'timestamp': 1388188800,
             'duration': 3710,
             'tags': list,
+            'display_id': '30C3_-_5443_-_en_-_saal_g_-_201312281830_-_introduction_to_processor_design_-_byterazor',
+            'view_count': int,
         },
     }, {
         'url': 'https://media.ccc.de/v/32c3-7368-shopshifting#download',
         'only_matching': True,
+    }, {
+        'url': 'https://media.ccc.de/v/39c3-schlechte-karten-it-sicherheit-im-jahr-null-der-epa-fur-alle',
+        'info_dict': {
+            'id': '16261',
+            'ext': 'mp4',
+            'title': 'Schlechte Karten - IT-Sicherheit im Jahr null der ePA für alle',
+            'display_id': '39c3-schlechte-karten-it-sicherheit-im-jahr-null-der-epa-fur-alle',
+            'description': 'md5:719a5a9a52630249d606219c55056cbf',
+            'view_count': int,
+            'duration': 3619,
+            'thumbnail': 'https://static.media.ccc.de/media/congress/2025/2403-2b5a6a8e-327e-594d-8f92-b91201d18a02.jpg',
+            'tags': list,
+            'creators': ['Bianca Kastl'],
+            'timestamp': 1767024900,
+            'upload_date': '20251229',
+        },
     }]
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
-        event_id = self._search_regex(r"data-id='(\d+)'", webpage, 'event id')
+        event_id = self._search_regex(r"data-id=(['\"])(?P<event_id>\d+)\1", webpage, 'event id', group='event_id')
         event_data = self._download_json(f'https://media.ccc.de/public/events/{event_id}', event_id)
 
         formats = []

yt_dlp/extractor/extractors.py

@@ -1,4 +1,4 @@
-import inspect
+import itertools
 import os
 
 from ..globals import LAZY_EXTRACTORS
@@ -17,12 +17,18 @@ else:
 if not _CLASS_LOOKUP:
     from . import _extractors
 
-    _CLASS_LOOKUP = {
-        name: value
-        for name, value in inspect.getmembers(_extractors)
-        if name.endswith('IE') and name != 'GenericIE'
-    }
-    _CLASS_LOOKUP['GenericIE'] = _extractors.GenericIE
+    members = tuple(
+        (name, getattr(_extractors, name))
+        for name in dir(_extractors)
+        if name.endswith('IE')
+    )
+    _CLASS_LOOKUP = dict(itertools.chain(
+        # Add Youtube first to improve matching performance
+        ((name, value) for name, value in members if '.youtube' in value.__module__),
+        # Add Generic last so that it is the fallback
+        ((name, value) for name, value in members if name != 'GenericIE'),
+        (('GenericIE', _extractors.GenericIE),),
+    ))
 
 # We want to append to the main lookup
 _current = _extractors_context.value