[ie/kick:vod] Support ongoing livestream VODs (#14154)

Authored by: InvalidUsernameException

yt_dlp/extractor/googledrive.py

@@ -12,6 +12,7 @@ from ..utils import (
     get_element_html_by_id,
     int_or_none,
     lowercase_escape,
+    parse_qs,
     try_get,
     update_url_query,
 )
@@ -111,14 +112,18 @@ class GoogleDriveIE(InfoExtractor):
                     self._caption_formats_ext.append(f.attrib['fmt_code'])
 
     def _get_captions_by_type(self, video_id, subtitles_id, caption_type,
-                              origin_lang_code=None):
+                              origin_lang_code=None, origin_lang_name=None):
         if not subtitles_id or not caption_type:
             return
         captions = {}
         for caption_entry in self._captions_xml.findall(
                 self._CAPTIONS_ENTRY_TAG[caption_type]):
             caption_lang_code = caption_entry.attrib.get('lang_code')
-            if not caption_lang_code:
+            caption_name = caption_entry.attrib.get('name') or origin_lang_name
+            if not caption_lang_code or not caption_name:
+                self.report_warning(f'Missing necessary caption metadata. '
+                                    f'Need lang_code and name attributes. '
+                                    f'Found: {caption_entry.attrib}')
                 continue
             caption_format_data = []
             for caption_format in self._caption_formats_ext:
@@ -129,7 +134,7 @@ class GoogleDriveIE(InfoExtractor):
                     'lang': (caption_lang_code if origin_lang_code is None
                              else origin_lang_code),
                     'type': 'track',
-                    'name': '',
+                    'name': caption_name,
                     'kind': '',
                 }
                 if origin_lang_code is not None:
@@ -155,14 +160,15 @@ class GoogleDriveIE(InfoExtractor):
         self._download_subtitles_xml(video_id, subtitles_id, hl)
         if not self._captions_xml:
             return
-        track = self._captions_xml.find('track')
+        track = next((t for t in self._captions_xml.findall('track') if t.attrib.get('cantran') == 'true'), None)
         if track is None:
             return
         origin_lang_code = track.attrib.get('lang_code')
-        if not origin_lang_code:
+        origin_lang_name = track.attrib.get('name')
+        if not origin_lang_code or not origin_lang_name:
             return
         return self._get_captions_by_type(
-            video_id, subtitles_id, 'automatic_captions', origin_lang_code)
+            video_id, subtitles_id, 'automatic_captions', origin_lang_code, origin_lang_name)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
@@ -268,10 +274,8 @@ class GoogleDriveIE(InfoExtractor):
         subtitles_id = None
         ttsurl = get_value('ttsurl')
         if ttsurl:
-            # the video Id for subtitles will be the last value in the ttsurl
-            # query string
-            subtitles_id = ttsurl.encode().decode(
-                'unicode_escape').split('=')[-1]
+            # the subtitles ID is the vid param of the ttsurl query
+            subtitles_id = parse_qs(ttsurl).get('vid', [None])[-1]
 
         self.cookiejar.clear(domain='.google.com', path='/', name='NID')
 

yt_dlp/extractor/itv.py

@@ -18,6 +18,7 @@ from ..utils import (
     url_or_none,
     urljoin,
 )
+from ..utils.traversal import traverse_obj
 
 
 class ITVIE(InfoExtractor):
@@ -223,6 +224,7 @@ class ITVBTCCIE(InfoExtractor):
         },
         'playlist_count': 12,
     }, {
+        # news page, can have absent `data` field
         'url': 'https://www.itv.com/news/2021-10-27/i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
         'info_dict': {
             'id': 'i-have-to-protect-the-country-says-rishi-sunak-as-uk-faces-interest-rate-hike',
@@ -243,7 +245,7 @@ class ITVBTCCIE(InfoExtractor):
 
         entries = []
         for video in json_map:
-            if not any(video['data'].get(attr) == 'Brightcove' for attr in ('name', 'type')):
+            if not any(traverse_obj(video, ('data', attr)) == 'Brightcove' for attr in ('name', 'type')):
                 continue
             video_id = video['data']['id']
             account_id = video['data']['accountId']

yt_dlp/extractor/kick.py

@@ -95,26 +95,47 @@ class KickVODIE(KickBaseIE):
     IE_NAME = 'kick:vod'
     _VALID_URL = r'https?://(?:www\.)?kick\.com/[\w-]+/videos/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
     _TESTS = [{
-        'url': 'https://kick.com/xqc/videos/8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
-        'md5': '3870f94153e40e7121a6e46c068b70cb',
+        # Regular VOD
+        'url': 'https://kick.com/xqc/videos/5c697a87-afce-4256-b01f-3c8fe71ef5cb',
         'info_dict': {
-            'id': '8dd97a8d-e17f-48fb-8bc3-565f88dbc9ea',
+            'id': '5c697a87-afce-4256-b01f-3c8fe71ef5cb',
             'ext': 'mp4',
-            'title': '18+ #ad 🛑LIVE🛑CLICK🛑DRAMA🛑NEWS🛑STUFF🛑REACT🛑GET IN HHERE🛑BOP BOP🛑WEEEE WOOOO🛑',
+            'title': '🐗LIVE🐗CLICK🐗HERE🐗DRAMA🐗ALL DAY🐗NEWS🐗VIDEOS🐗CLIPS🐗GAMES🐗STUFF🐗WOW🐗IM HERE🐗LETS GO🐗COOL🐗VERY NICE🐗',
             'description': 'THE BEST AT ABSOLUTELY EVERYTHING. THE JUICER. LEADER OF THE JUICERS.',
-            'channel': 'xqc',
-            'channel_id': '668',
             'uploader': 'xQc',
             'uploader_id': '676',
-            'upload_date': '20240909',
-            'timestamp': 1725919141,
-            'duration': 10155.0,
-            'thumbnail': r're:^https?://.*\.jpg',
+            'channel': 'xqc',
+            'channel_id': '668',
             'view_count': int,
-            'categories': ['Just Chatting'],
-            'age_limit': 0,
+            'age_limit': 18,
+            'duration': 22278.0,
+            'thumbnail': r're:^https?://.*\.jpg',
+            'categories': ['Deadlock'],
+            'timestamp': 1756082443,
+            'upload_date': '20250825',
         },
         'params': {'skip_download': 'm3u8'},
+    }, {
+        # VOD of ongoing livestream (at the time of writing the test, ID rotates every two days)
+        'url': 'https://kick.com/a-log-burner/videos/5230df84-ea38-46e1-be4f-f5949ae55641',
+        'info_dict': {
+            'id': '5230df84-ea38-46e1-be4f-f5949ae55641',
+            'ext': 'mp4',
+            'title': r're:😴 Cozy Fireplace ASMR 🔥 | Relax, Focus, Sleep 💤',
+            'description': 'md5:080bc713eac0321a7b376a1b53816d1b',
+            'uploader': 'A_Log_Burner',
+            'uploader_id': '65114691',
+            'channel': 'a-log-burner',
+            'channel_id': '63967687',
+            'view_count': int,
+            'age_limit': 18,
+            'thumbnail': r're:^https?://.*\.jpg',
+            'categories': ['Other, Watch Party'],
+            'timestamp': int,
+            'upload_date': str,
+            'live_status': 'is_live',
+        },
+        'skip': 'live',
     }]
 
     def _real_extract(self, url):
@@ -137,6 +158,7 @@ class KickVODIE(KickBaseIE):
                 'categories': ('livestream', 'categories', ..., 'name', {str}),
                 'view_count': ('views', {int_or_none}),
                 'age_limit': ('livestream', 'is_mature', {bool}, {lambda x: 18 if x else 0}),
+                'is_live': ('livestream', 'is_live', {bool}),
             }),
         }
 

yt_dlp/extractor/tver.py

@@ -45,6 +45,8 @@ class TVerIE(StreaksBaseIE):
             'release_timestamp': 1651453200,
             'release_date': '20220502',
             '_old_archive_ids': ['brightcovenew ref:baeebeac-a2a6-4dbf-9eb3-c40d59b40068'],
+            'series_id': 'sru35hwdd2',
+            'season_id': 'ss2lcn4af6',
         },
     }, {
         # via Brightcove backend (deprecated)
@@ -67,6 +69,8 @@ class TVerIE(StreaksBaseIE):
             'upload_date': '20220501',
             'release_timestamp': 1651453200,
             'release_date': '20220502',
+            'series_id': 'sru35hwdd2',
+            'season_id': 'ss2lcn4af6',
         },
         'params': {'extractor_args': {'tver': {'backend': ['brightcove']}}},
     }, {
@@ -202,6 +206,8 @@ class TVerIE(StreaksBaseIE):
                 'description': ('description', {str}),
                 'release_timestamp': ('viewStatus', 'startAt', {int_or_none}),
                 'episode_number': ('no', {int_or_none}),
+                'series_id': ('seriesID', {str}),
+                'season_id': ('seasonID', {str}),
             }),
         }