Merge f2a095884c293ebffd2363dc5b24c644bf6f4837 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/xvideos.py

@@ -10,6 +10,8 @@ from ..utils import (
     ExtractorError,
     int_or_none,
     parse_duration,
+    str_to_int,
+    urljoin,
 )
 
 
@@ -25,14 +27,21 @@ class XVideosIE(InfoExtractor):
                         (?P<id>[0-9]+)
                     '''
     _TESTS = [{
-        'url': 'http://www.xvideos.com/video4588838/biker_takes_his_girl',
-        'md5': '14cea69fcb84db54293b1e971466c2e1',
+        'url': 'https://www.xvideos.com/video50011247/when_girls_play_-_adriana_chechik_abella_danger_-_tradimento_-_twistys',
+        'md5': 'aa54f96311768b3a8bfe54b8c8fda070',
         'info_dict': {
-            'id': '4588838',
+            'id': '50011247',
             'ext': 'mp4',
-            'title': 'Biker Takes his Girl',
-            'duration': 108,
+            'title': 'When Girls Play - (Adriana Chechik, Abella Danger) - Betrayal - Twistys',
+            'duration': 720,
             'age_limit': 18,
+            'tags': ['lesbian', 'teen', 'hardcore', 'latina', 'rough', 'squirt', 'big-ass', 'cheater', 'twistys', 'cheat', 'ass-play', 'when-girls-play'],
+            'creator': 'Twistys',
+            'uploader': 'Twistys',
+            'uploader_id': 'Twistys',
+            'uploader_url': '/channels/twistys1',
+            'actors': [{'given_name': 'Adriana Chechik', 'url': 'https://www.xvideos.com/pornstars/adriana-chechik'}, {'given_name': 'Abella Danger', 'url': 'https://www.xvideos.com/pornstars/abella-danger'}],
+            'view_count': int,
         }
     }, {
         'url': 'https://flashservice.xvideos.com/embedframe/4588838',
@@ -137,6 +146,25 @@ class XVideosIE(InfoExtractor):
 
         self._sort_formats(formats)
 
+        tags = self._search_regex(r'<meta name="keywords" content="xvideos,xvideos\.com, x videos,x video,porn,video,videos,(?P<tag>.+?)"', webpage, 'tags', group='tag', default='').split(',')
+
+        creator_data = re.findall(r'<a href="(?P<creator_url>.+?)" class="btn btn-default label main uploader-tag hover-name"><span class="name">(?P<creator>.+?)<', webpage)
+        creator = None
+        uploader_url = None
+        if creator_data != []:
+            uploader_url, creator = creator_data[0][0:2]
+
+        actors_data = re.findall(r'href="(?P<actor_url>/pornstars/.+?)" class="btn btn-default label profile hover-name"><span class="name">(?P<actor_name>.+?)</span>', webpage)
+        actors = []
+        if actors_data != []:
+            for actor_tuple in actors_data:
+                actors.append({
+                    'given_name': actor_tuple[1],
+                    'url': urljoin(url, actor_tuple[0]),
+                })
+
+        views = self._search_regex(r'<strong class="mobile-hide">(?P<views>.+?)<', webpage, 'views', group='views', default=None)
+
         return {
             'id': video_id,
             'formats': formats,
@@ -144,4 +172,11 @@ class XVideosIE(InfoExtractor):
             'duration': duration,
             'thumbnails': thumbnails,
             'age_limit': 18,
+            'tags': tags,
+            'creator': creator,
+            'uploader': creator,
+            'uploader_id': creator,
+            'uploader_url': uploader_url,
+            'actors': actors,
+            'view_count': str_to_int(views),
         }

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: