Merge b91bbb8084ca39edebcfbc472e15a43ce584fdd0 into 673277e510ebd996b62a2fcc76169bf3cce29910

* [YouTube] Extract playlist items from LOCKUP_VIEW_MODEL_...
* resolves #33073
* thx seproDev (yt-dlp/yt-dlp#11615)

Co-authored-by: sepro <sepro@sepr0.com>

youtube_dl/extractor/acast.py

@@ -48,9 +48,9 @@ class ACastIE(ACastBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:(?:embed|www)\.)?acast\.com/|
-                            play\.acast\.com/s/
-                        )
+                            (?:(?:(?P<embed>embed)|www|shows)\.)?acast\.com|
+                            play\.acast\.com/s
+                        )/(?(embed)(?:$/)?)
                         (?P<channel>[^/]+)/(?P<id>[^/#?]+)
                     '''
     _TESTS = [{
@@ -77,6 +77,9 @@ class ACastIE(ACastBaseIE):
     }, {
         'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
         'only_matching': True,
+    }, {
+        'url': 'https://shows.acast.com/611233d8767fdf0012f22cb6/episodes/611233e4988b6a001394b5cf',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -93,7 +96,7 @@ class ACastChannelIE(ACastBaseIE):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:www\.)?acast\.com/|
+                            (?:(?:www|shows)\.)?acast\.com/|
                             play\.acast\.com/s/
                         )
                         (?P<id>[^/#?]+)
@@ -104,11 +107,22 @@ class ACastChannelIE(ACastBaseIE):
             'id': '4efc5294-5385-4847-98bd-519799ce5786',
             'title': 'Today in Focus',
             'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
+            'skip': 'Error 404'
         },
         'playlist_mincount': 200,
     }, {
         'url': 'http://play.acast.com/s/ft-banking-weekly',
         'only_matching': True,
+    }, {
+        'url': 'https://shows.acast.com/611233d8767fdf0012f22cb6',
+        'only_matching': True,
+    }, {
+        'url': 'https://play.acast.com/s/getthebeltpod',
+        'info_dict': {
+            'id': '4caac858-3cda-44e6-b684-50d88b909c18',
+            'title': 'Get The Belt'
+        },
+        'playlist_mincount': 138,
     }]
 
     @classmethod

youtube_dl/extractor/youtube.py

@@ -27,6 +27,7 @@ from ..compat import (
 )
 from ..jsinterp import JSInterpreter
 from ..utils import (
+    bug_reports_message,
     clean_html,
     dict_get,
     error_to_compat_str,
@@ -65,6 +66,7 @@ from ..utils import (
     url_or_none,
     urlencode_postdata,
     urljoin,
+    variadic,
 )
 
 
@@ -460,6 +462,26 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
             'uploader': uploader,
         }
 
+    @staticmethod
+    def _extract_thumbnails(data, *path_list, **kw_final_key):
+        """
+        Extract thumbnails from thumbnails dict
+        @param path_list: path list to level that contains 'thumbnails' key
+        """
+        final_key = kw_final_key.get('final_key', 'thumbnails')
+
+        return traverse_obj(data, ((
+            tuple(variadic(path) + (final_key, Ellipsis)
+                  for path in path_list or [()])), {
+            'url': ('url', T(url_or_none),
+                    # Sometimes youtube gives a wrong thumbnail URL. See:
+                    # https://github.com/yt-dlp/yt-dlp/issues/233
+                    # https://github.com/ytdl-org/youtube-dl/issues/28023
+                    T(lambda u: update_url(u, query=None) if u and 'maxresdefault' in u else u)),
+            'height': ('height', T(int_or_none)),
+            'width': ('width', T(int_or_none)),
+        }, T(lambda t: t if t.get('url') else None)))
+
     def _search_results(self, query, params):
         data = {
             'context': {
@@ -3183,8 +3205,12 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
             expected_type=txt_or_none)
 
     def _grid_entries(self, grid_renderer):
-        for item in grid_renderer['items']:
-            if not isinstance(item, dict):
+        for item in traverse_obj(grid_renderer, ('items', Ellipsis, T(dict))):
+            lockup_view_model = traverse_obj(item, ('lockupViewModel', T(dict)))
+            if lockup_view_model:
+                entry = self._extract_lockup_view_model(lockup_view_model)
+                if entry:
+                    yield entry
                 continue
             renderer = self._extract_grid_item_renderer(item)
             if not isinstance(renderer, dict):
@@ -3268,6 +3294,25 @@ class YoutubeTabIE(YoutubeBaseInfoExtractor):
                 continue
             yield self._extract_video(renderer)
 
+    def _extract_lockup_view_model(self, view_model):
+        content_id = view_model.get('contentId')
+        if not content_id:
+            return
+        content_type = view_model.get('contentType')
+        if content_type not in ('LOCKUP_CONTENT_TYPE_PLAYLIST', 'LOCKUP_CONTENT_TYPE_PODCAST'):
+            self.report_warning(
+                'Unsupported lockup view model content type "{0}"{1}'.format(content_type, bug_reports_message()), only_once=True)
+            return
+        return merge_dicts(self.url_result(
+            update_url_query('https://www.youtube.com/playlist', {'list': content_id}),
+            ie=YoutubeTabIE.ie_key(), video_id=content_id), {
+                'title': traverse_obj(view_model, (
+                    'metadata', 'lockupMetadataViewModel', 'title', 'content', T(compat_str))),
+                'thumbnails': self._extract_thumbnails(view_model, (
+                    'contentImage', 'collectionThumbnailViewModel', 'primaryThumbnail',
+                    'thumbnailViewModel', 'image'), final_key='sources'),
+        })
+
     def _video_entry(self, video_renderer):
         video_id = video_renderer.get('videoId')
         if video_id: