Merge branch 'yt-dlp:master' into pr/2475

CONTRIBUTORS

@@ -711,3 +711,5 @@ gitninja1234
 jkruse
 xiaomac
 wesson09
+Crypto90
+MutantPiggieGolem1

Changelog.md

@@ -4,6 +4,20 @@
 # To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
 -->
 
+### 2024.12.13
+
+#### Extractor changes
+- **patreon**: campaign: [Support /c/ URLs](https://github.com/yt-dlp/yt-dlp/commit/bc262bcad4d3683ceadf61a7eb87e233e72adef3) ([#11756](https://github.com/yt-dlp/yt-dlp/issues/11756)) by [bashonly](https://github.com/bashonly)
+- **soundcloud**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/f4d3e9e6dc25077b79849a31a2f67f93fdc01e62) ([#11777](https://github.com/yt-dlp/yt-dlp/issues/11777)) by [bashonly](https://github.com/bashonly)
+- **youtube**
+    - [Fix `release_date` extraction](https://github.com/yt-dlp/yt-dlp/commit/d5e2a379f2adcb28bc48c7d9e90716d7278f89d2) ([#11759](https://github.com/yt-dlp/yt-dlp/issues/11759)) by [MutantPiggieGolem1](https://github.com/MutantPiggieGolem1)
+    - [Fix signature function extraction for `2f1832d2`](https://github.com/yt-dlp/yt-dlp/commit/5460cd91891bf613a2065e2fc278d9903c37a127) ([#11801](https://github.com/yt-dlp/yt-dlp/issues/11801)) by [bashonly](https://github.com/bashonly)
+    - [Prioritize original language over auto-dubbed audio](https://github.com/yt-dlp/yt-dlp/commit/dc3c4fddcc653989dae71fc563d82a308fc898cc) ([#11803](https://github.com/yt-dlp/yt-dlp/issues/11803)) by [bashonly](https://github.com/bashonly)
+    - search_url: [Fix playlist searches](https://github.com/yt-dlp/yt-dlp/commit/f6c73aad5f1a67544bea137ebd9d1e22e0e56567) ([#11782](https://github.com/yt-dlp/yt-dlp/issues/11782)) by [Crypto90](https://github.com/Crypto90)
+
+#### Misc. changes
+- **cleanup**: [Make more playlist entries lazy](https://github.com/yt-dlp/yt-dlp/commit/54216696261bc07cacd9a837c501d9e0b7fed09e) ([#11763](https://github.com/yt-dlp/yt-dlp/issues/11763)) by [seproDev](https://github.com/seproDev)
+
 ### 2024.12.06
 
 #### Core changes

test/test_youtube_signature.py

@@ -73,6 +73,11 @@ _SIG_TESTS = [
         '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
         'MyOSJXtKI3m-uME_jv7-pT12gOFC02RFkGoqWpzE0Cs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
     ),
+    (
+        'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
+        '2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
+        '0QJ8wRAIgXmPlOPSBkkUs1bYFYlJCfe29xxAj7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_EMu-m37KtXJ2OySqa0q',
+    ),
 ]
 
 _NSIG_TESTS = [
@@ -192,6 +197,10 @@ _NSIG_TESTS = [
         'https://www.youtube.com/s/player/3bb1f723/player_ias.vflset/en_US/base.js',
         'gK15nzVyaXE9RsMP3z', 'ZFFWFLPWx9DEgQ',
     ),
+    (
+        'https://www.youtube.com/s/player/2f1832d2/player_ias.vflset/en_US/base.js',
+        'YWt1qdbe8SAfkoPHW5d', 'RrRjWQOJmBiP',
+    ),
 ]
 
 

yt_dlp/extractor/brightcove.py

@@ -31,6 +31,7 @@ from ..utils import (
     update_url_query,
     url_or_none,
 )
+from ..utils.traversal import traverse_obj
 
 
 class BrightcoveLegacyIE(InfoExtractor):
@@ -935,8 +936,8 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
 
         if content_type == 'playlist':
             return self.playlist_result(
-                [self._parse_brightcove_metadata(vid, vid.get('id'), headers)
+                (self._parse_brightcove_metadata(vid, vid['id'], headers)
-                 for vid in json_data.get('videos', []) if vid.get('id')],
+                 for vid in traverse_obj(json_data, ('videos', lambda _, v: v['id']))),
                 json_data.get('id'), json_data.get('name'),
                 json_data.get('description'))
 

yt_dlp/extractor/dvtv.py

@@ -162,7 +162,7 @@ class DVTVIE(InfoExtractor):
         items = re.findall(r'(?s)playlist\.push\(({.+?})\);', webpage)
         if items:
             return self.playlist_result(
-                [self._parse_video_metadata(i, video_id, timestamp) for i in items],
+                (self._parse_video_metadata(i, video_id, timestamp) for i in items),
                 video_id, self._html_search_meta('twitter:title', webpage))
 
         item = self._search_regex(

yt_dlp/extractor/nytimes.py

@@ -343,7 +343,7 @@ class NYTimesCookingIE(NYTimesBaseIE):
         if media_ids:
             media_ids.append(lead_video_id)
             return self.playlist_result(
-                [self._extract_video(media_id) for media_id in media_ids], page_id, title, description)
+                map(self._extract_video, media_ids), page_id, title, description)
 
         return {
             **self._extract_video(lead_video_id),

yt_dlp/extractor/patreon.py

@@ -457,7 +457,7 @@ class PatreonCampaignIE(PatreonBaseIE):
     _VALID_URL = r'''(?x)
         https?://(?:www\.)?patreon\.com/(?:
             (?:m|api/campaigns)/(?P<campaign_id>\d+)|
-            (?P<vanity>(?!creation[?/]|posts/|rss[?/])[\w-]+)
+            (?:c/)?(?P<vanity>(?!creation[?/]|posts/|rss[?/])[\w-]+)
         )(?:/posts)?/?(?:$|[?#])'''
     _TESTS = [{
         'url': 'https://www.patreon.com/dissonancepod/',
@@ -509,6 +509,26 @@ class PatreonCampaignIE(PatreonBaseIE):
             'thumbnail': r're:^https?://.*$',
         },
         'playlist_mincount': 201,
+    }, {
+        'url': 'https://www.patreon.com/c/OgSog',
+        'info_dict': {
+            'id': '8504388',
+            'title': 'OGSoG',
+            'description': r're:(?s)Hello and welcome to our Patreon page. We are Mari, Lasercorn, .+',
+            'channel': 'OGSoG',
+            'channel_id': '8504388',
+            'channel_url': 'https://www.patreon.com/OgSog',
+            'uploader_url': 'https://www.patreon.com/OgSog',
+            'uploader_id': '72323575',
+            'uploader': 'David Moss',
+            'thumbnail': r're:https?://.+/.+',
+            'channel_follower_count': int,
+            'age_limit': 0,
+        },
+        'playlist_mincount': 331,
+    }, {
+        'url': 'https://www.patreon.com/c/OgSog/posts',
+        'only_matching': True,
     }, {
         'url': 'https://www.patreon.com/dissonancepod/posts',
         'only_matching': True,

yt_dlp/extractor/soundcloud.py

@@ -259,6 +259,8 @@ class SoundcloudBaseIE(InfoExtractor):
             preset_base = preset.partition('_')[0]
 
             protocol = traverse_obj(t, ('format', 'protocol', {str})) or 'http'
+            if protocol.startswith(('ctr-', 'cbc-')):
+                continue
             if protocol == 'progressive':
                 protocol = 'http'
             if protocol != 'hls' and '/hls' in format_url:

yt_dlp/extractor/vidyard.py

@@ -421,5 +421,5 @@ class VidyardIE(VidyardBaseIE):
             return self._process_video_json(video_json['chapters'][0], video_id)
 
         return self.playlist_result(
-            [self._process_video_json(chapter, video_id) for chapter in video_json['chapters']],
+            (self._process_video_json(chapter, video_id) for chapter in video_json['chapters']),
             str(video_json['playerUuid']), video_json.get('name'))

yt_dlp/extractor/youtube.py

@@ -3127,9 +3127,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         # ;N&&(N=sig(decodeURIComponent(N)),J.set(R,encodeURIComponent(N)));return J};
         # {var H=u,k=f.sp,v=sig(decodeURIComponent(f.s));H.set(k,encodeURIComponent(v))}
         funcname = self._search_regex(
-            (r'\b(?P<var>[a-zA-Z0-9$]+)&&\((?P=var)=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\((?P=var)\)\)',
+            (r'\b(?P<var>[a-zA-Z0-9_$]+)&&\((?P=var)=(?P<sig>[a-zA-Z0-9_$]{2,})\(decodeURIComponent\((?P=var)\)\)',
-             r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*(?P<arg>[a-zA-Z0-9$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)',
+             r'(?P<sig>[a-zA-Z0-9_$]+)\s*=\s*function\(\s*(?P<arg>[a-zA-Z0-9_$]+)\s*\)\s*{\s*(?P=arg)\s*=\s*(?P=arg)\.split\(\s*""\s*\)\s*;\s*[^}]+;\s*return\s+(?P=arg)\.join\(\s*""\s*\)',
-             r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\))?',
+             r'(?:\b|[^a-zA-Z0-9_$])(?P<sig>[a-zA-Z0-9_$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)(?:;[a-zA-Z0-9_$]{2}\.[a-zA-Z0-9_$]{2}\(a,\d+\))?',
              # Old patterns
              r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
@@ -4067,10 +4067,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 if height:
                     res_qualities[height] = quality
 
+            display_name = audio_track.get('displayName') or ''
+            is_original = 'original' in display_name.lower()
+            is_descriptive = 'descriptive' in display_name.lower()
             is_default = audio_track.get('audioIsDefault')
-            is_descriptive = 'descriptive' in (audio_track.get('displayName') or '').lower()
             language_code = audio_track.get('id', '').split('.')[0]
-            if language_code and is_default:
+            if language_code and (is_original or (is_default and not original_language)):
                 original_language = language_code
 
             # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
@@ -4151,7 +4153,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'filesize': int_or_none(fmt.get('contentLength')),
                 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
                 'format_note': join_nonempty(
-                    join_nonempty(audio_track.get('displayName'), is_default and ' (default)', delim=''),
+                    join_nonempty(display_name, is_default and ' (default)', delim=''),
                     name, fmt.get('isDrc') and 'DRC',
                     try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
                     try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
@@ -4170,7 +4172,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'url': fmt_url,
                 'width': int_or_none(fmt.get('width')),
                 'language': join_nonempty(language_code, 'desc' if is_descriptive else '') or None,
-                'language_preference': PREFERRED_LANG_VALUE if is_default else -10 if is_descriptive else -1,
+                'language_preference': PREFERRED_LANG_VALUE if is_original else 5 if is_default else -10 if is_descriptive else -1,
                 # Strictly de-prioritize broken, damaged and 3gp formats
                 'preference': -20 if is_broken else -10 if is_damaged else -2 if itag == '17' else None,
             }
@@ -4689,7 +4691,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                     (?=(?P<artist>[^\n]+))(?P=artist)\n+
                     (?=(?P<album>[^\n]+))(?P=album)\n
                     (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
-                    (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
+                    (?:.+?Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
                     (.+?\nArtist\s*:\s*
                         (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
                     )?.+\nAuto-generated\ by\ YouTube\.\s*$
@@ -5282,6 +5284,7 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
                     'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
                     'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)],
                     'richGridRenderer': lambda x: self._extract_entries(x, continuation_list),
+                    'lockupViewModel': lambda x: [self._extract_lockup_view_model(x)],
                 }
                 for key, renderer in isr_content.items():
                     if key not in known_renderers:

yt_dlp/version.py

@@ -1,8 +1,8 @@
 # Autogenerated by devscripts/update-version.py
 
-__version__ = '2024.12.06'
+__version__ = '2024.12.13'
 
-RELEASE_GIT_HEAD = '4bd2655398aed450456197a6767639114a24eac2'
+RELEASE_GIT_HEAD = '54216696261bc07cacd9a837c501d9e0b7fed09e'
 
 VARIANT = None
 
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
 
 ORIGIN = 'yt-dlp/yt-dlp'
 
-_pkg_version = '2024.12.06'
+_pkg_version = '2024.12.13'