[youtube] Fix youtube mix playlist extraction (closes #26509, closes …

…#26390, closes #25465)
glumia · Sep 6, 2020 · 1b7ae78 · 1b7ae78 · bvdeenen · Oct 10, 2020
1 parent d51e23d
commit 1b7ae78
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 4 deletions.
diff --git a/test/test_youtube_lists.py b/test/test_youtube_lists.py
@@ -45,8 +45,8 @@ def test_youtube_mix(self):
         result = ie.extract('https://www.youtube.com/watch?v=W01L70IGBgE&index=2&list=RDOQpdSVF_k_w')
         entries = result['entries']
         self.assertTrue(len(entries) >= 50)
-        original_video = entries[0]
-        self.assertEqual(original_video['id'], 'OQpdSVF_k_w')
+        original_video_id = 'OQpdSVF_k_w'
+        self.assertTrue(original_video_id in {entry['id'] for entry in entries})
 
     def test_youtube_toptracks(self):
         print('Skipping: The playlist page gives error 500')

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
@@ -2781,8 +2781,7 @@ def _extract_mix(self, playlist_id):
             webpage = self._download_webpage(
                 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
             new_ids = orderedSet(re.findall(
-                r'''(?xs)data-video-username=".*?".*?
-                           href="/watch\?v=([0-9A-Za-z_-]{11})&amp;[^"]*?list=%s''' % re.escape(playlist_id),
+                r'[\'"]/watch\?v=([0-9A-Za-z_-]{11})(?:&amp;|\\u0026)[^"]*?list=%s' % re.escape(playlist_id),
                 webpage))
             # Fetch new pages until all the videos are repeated, it seems that
             # there are always 51 unique videos.