Merge 223b3b75ef into 6ae3543d5a

yt_dlp/extractor/youtube/_video.py

@@ -1666,6 +1666,46 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
             'view_count': int,
         },
         'params': {'skip_download': True},
+    }, {
+        # Youtube Music Auto-generated description with dot in artist name
+        'url': 'https://music.youtube.com/watch?v=DbCvuSGfR3Y',
+        'info_dict': {
+            'id': 'DbCvuSGfR3Y',
+            'ext': 'mp4',
+            'title': 'Back Around',
+            'artists': ['half·alive'],
+            'track': 'Back Around',
+            'album': 'Conditions Of A Punk',
+            'release_date': '20221202',
+            'release_year': 2021,
+            'alt_title': 'Back Around',
+            'description': 'md5:bfc0e2b3cc903a608d8a85a13cb50f95',
+            'media_type': 'video',
+            'uploader': 'half•alive',
+            'channel': 'half•alive',
+            'channel_id': 'UCYQrYophdVI3nVDPOnXyIng',
+            'channel_url': 'https://www.youtube.com/channel/UCYQrYophdVI3nVDPOnXyIng',
+            'channel_is_verified': True,
+            'channel_follower_count': int,
+            'comment_count': int,
+            'view_count': int,
+            'like_count': int,
+            'age_limit': 0,
+            'duration': 223,
+            'thumbnail': 'https://i.ytimg.com/vi_webp/DbCvuSGfR3Y/maxresdefault.webp',
+            'heatmap': 'count:100',
+            'categories': ['Music'],
+            'tags': ['half·alive', 'Conditions Of A Punk', 'Back Around'],
+            'creators': ['half·alive'],
+            'timestamp': 1669889281,
+            'upload_date': '20221201',
+            'playable_in_embed': True,
+            'availability': 'public',
+            'live_status': 'not_live',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }]
     _WEBPAGE_TESTS = [{
         # <object>
@@ -4194,20 +4234,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # Youtube Music Auto-generated description
         if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
-            # XXX: Causes catastrophic backtracking if description has "·"
-            # E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
-            # Simulating atomic groups:  (?P<a>[^xy]+)x  =>  (?=(?P<a>[^xy]+))(?P=a)x
-            # reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
             mobj = re.search(
                 r'''(?xs)
-                    (?=(?P<track>[^\n·]+))(?P=track)·
-                    (?=(?P<artist>[^\n]+))(?P=artist)\n+
-                    (?=(?P<album>[^\n]+))(?P=album)\n
-                    (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
-                    (?:.+?Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
-                    (.+?\nArtist\s*:\s*
-                        (?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
-                    )?.+\nAuto-generated\ by\ YouTube\.\s*$
+                    (?:\n|^)(?P<track>[^\n·]+)\ ·\ (?P<artist>[^\n]+)\n+
+                    (?P<album>[^\n]+)\n+
+                    (?:℗\s*(?P<release_year>\d{4}))?
+                    (?:.+?\nReleased\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
+                    (?:.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+)\n)?
+                    .+\nAuto-generated\ by\ YouTube\.\s*$
                 ''', video_description)
             if mobj:
                 release_year = mobj.group('release_year')