Merge edb1ec29858255f29da9aad12e143e59dc68193c 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/captiongenerator.py

@@ -0,0 +1,64 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class CaptionGeneratorIE(InfoExtractor):
+    _VALID_URL = r'(?:https?://(?:www\.)?captiongenerator\.com/(?P<id>[0-9]+))'
+    _TESTS = [{
+        'url': 'https://www.captiongenerator.com/128/Team-building',
+        'info_dict': {
+            'id': '128',
+            'ext': 'mp4',
+            'title': 'Team building...',
+            'http_headers': {'Referer': 'https://www.captiongenerator.com/'}
+        },
+    }, {
+        'url': 'https://www.captiongenerator.com/2153287/Man-finds-phone',
+        'info_dict': {
+            'id': '2153287',
+            'ext': 'mp4',
+            'title': 'Man finds phone',
+            'http_headers': {'Referer': 'https://www.captiongenerator.com/'}
+        },
+    }, {
+        'url': 'https://www.captiongenerator.com/2140517/Haavisto-Pietarissa',
+        'info_dict': {
+            'id': '2140517',
+            'ext': 'mp4',
+            'title': 'Haavisto Pietarissa',
+            'http_headers': {'Referer': 'https://www.captiongenerator.com/'}
+        },
+    }, {
+        'url': 'https://www.captiongenerator.com/2153147/81-Pay',
+        'info_dict': {
+            'id': '2153147',
+            'ext': 'mp4',
+            'title': '81 Pay',
+            'http_headers': {'Referer': 'https://www.captiongenerator.com/'}
+        },
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        video_url = self._html_search_regex(r'(https?://[a-z0-9]+\.cloudfront\.net/.+?\.mp4)', webpage, 'videoUrl')
+        print(video_url)
+
+        vtt_page = self._download_webpage('https://www.captiongenerator.com/videos/%s.vtt' % video_id, video_id)
+
+        vtt_captions = open("128.vtt", "w")
+        vtt_captions.write(vtt_page)
+        vtt_captions.close()
+
+        title = self._html_search_regex(r'<title>(.*)</title>', webpage, 'videoTitle')
+
+        return {
+            'id': video_id,
+            'title': title,
+            'url': video_url,
+            'http_headers': {"Referer": "https://www.captiongenerator.com/"}
+        }

youtube_dl/extractor/extractors.py

@@ -180,6 +180,7 @@ from .carambatv import (
     CarambaTVIE,
     CarambaTVPageIE,
 )
+from .captiongenerator import CaptionGeneratorIE
 from .cartoonnetwork import CartoonNetworkIE
 from .cbc import (
     CBCIE,

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: