fix: support YouTube 2024+ data formats for playlists, podcasts and channels

- Add PODCAST content type support in lockupViewModel extraction
- Extract thumbnails and episode count from thumbnail overlay badges
- Migrate playlist page fetching from pbj=1 to innertube API (youtubei/v1/browse)
- Support new pageHeaderRenderer format in playlist metadata extraction
- Fix subscriber count extraction when YouTube returns handle instead of count
- Hide "None subscribers" in template when data is unavailable

1 files changed, 86 insertions, 26 deletions

diff --git a/youtube/yt_data_extract/everything_else.py b/youtube/yt_data_extract/everything_else.py
index 0f64649..5930111 100644
--- a/youtube/yt_data_extract/everything_else.py
+++ b/youtube/yt_data_extract/everything_else.py
@@ -218,39 +218,99 @@ def extract_playlist_metadata(polymer_json):
         return {'error': err}
 
     metadata = {'error': None}
+    metadata['title'] = None
+    metadata['first_video_id'] = None
+    metadata['thumbnail'] = None
+    metadata['video_count'] = None
+    metadata['description'] = ''
+    metadata['author'] = None
+    metadata['author_id'] = None
+    metadata['author_url'] = None
+    metadata['view_count'] = None
+    metadata['like_count'] = None
+    metadata['time_published'] = None
+
     header = deep_get(response, 'header', 'playlistHeaderRenderer', default={})
-    metadata['title'] = extract_str(header.get('title'))
 
-    metadata['first_video_id'] = deep_get(header, 'playEndpoint', 'watchEndpoint', 'videoId')
-    first_id = re.search(r'([a-z_\-]{11})', deep_get(header,
-        'thumbnail', 'thumbnails', 0, 'url', default=''))
-    if first_id:
-        conservative_update(metadata, 'first_video_id', first_id.group(1))
-    if metadata['first_video_id'] is None:
-        metadata['thumbnail'] = None
+    if header:
+        # Classic playlistHeaderRenderer format
+        metadata['title'] = extract_str(header.get('title'))
+        metadata['first_video_id'] = deep_get(header, 'playEndpoint', 'watchEndpoint', 'videoId')
+        first_id = re.search(r'([a-z_\-]{11})', deep_get(header,
+            'thumbnail', 'thumbnails', 0, 'url', default=''))
+        if first_id:
+            conservative_update(metadata, 'first_video_id', first_id.group(1))
+
+        metadata['video_count'] = extract_int(header.get('numVideosText'))
+        metadata['description'] = extract_str(header.get('descriptionText'), default='')
+        metadata['author'] = extract_str(header.get('ownerText'))
+        metadata['author_id'] = multi_deep_get(header,
+            ['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
+            ['ownerEndpoint', 'browseEndpoint', 'browseId'])
+        metadata['view_count'] = extract_int(header.get('viewCountText'))
+        metadata['like_count'] = extract_int(header.get('likesCountWithoutLikeText'))
+        for stat in header.get('stats', ()):
+            text = extract_str(stat)
+            if 'videos' in text or 'episodes' in text:
+                conservative_update(metadata, 'video_count', extract_int(text))
+            elif 'views' in text:
+                conservative_update(metadata, 'view_count', extract_int(text))
+            elif 'updated' in text:
+                metadata['time_published'] = extract_date(text)
     else:
-        metadata['thumbnail'] = f"https://i.ytimg.com/vi/{metadata['first_video_id']}/hqdefault.jpg"
+        # New pageHeaderRenderer format (YouTube 2024+)
+        page_header = deep_get(response, 'header', 'pageHeaderRenderer', default={})
+        metadata['title'] = page_header.get('pageTitle')
+        view_model = deep_get(page_header, 'content', 'pageHeaderViewModel', default={})
+
+        # Extract title from viewModel if not found
+        if not metadata['title']:
+            metadata['title'] = deep_get(view_model,
+                'title', 'dynamicTextViewModel', 'text', 'content')
+
+        # Extract metadata from rows (author, video count, views, etc.)
+        meta_rows = deep_get(view_model,
+            'metadata', 'contentMetadataViewModel', 'metadataRows', default=[])
+        for row in meta_rows:
+            for part in row.get('metadataParts', []):
+                text_content = deep_get(part, 'text', 'content', default='')
+                # Author from avatarStack
+                avatar_stack = deep_get(part, 'avatarStack', 'avatarStackViewModel', default={})
+                if avatar_stack:
+                    author_text = deep_get(avatar_stack, 'text', 'content')
+                    if author_text:
+                        metadata['author'] = author_text
+                    # Extract author_id from commandRuns
+                    for run in deep_get(avatar_stack, 'text', 'commandRuns', default=[]):
+                        browse_id = deep_get(run, 'onTap', 'innertubeCommand',
+                            'browseEndpoint', 'browseId')
+                        if browse_id:
+                            metadata['author_id'] = browse_id
+                # Video/episode count
+                if text_content and ('video' in text_content.lower() or 'episode' in text_content.lower()):
+                    conservative_update(metadata, 'video_count', extract_int(text_content))
+                # View count
+                elif text_content and 'view' in text_content.lower():
+                    conservative_update(metadata, 'view_count', extract_int(text_content))
+                # Last updated
+                elif text_content and 'updated' in text_content.lower():
+                    metadata['time_published'] = extract_date(text_content)
+
+        # Extract description from sidebar if available
+        sidebar = deep_get(response, 'sidebar', 'playlistSidebarRenderer', 'items', default=[])
+        for sidebar_item in sidebar:
+            desc = deep_get(sidebar_item, 'playlistSidebarPrimaryInfoRenderer',
+                'description', 'simpleText')
+            if desc:
+                metadata['description'] = desc
 
-    metadata['video_count'] = extract_int(header.get('numVideosText'))
-    metadata['description'] = extract_str(header.get('descriptionText'), default='')
-    metadata['author'] = extract_str(header.get('ownerText'))
-    metadata['author_id'] = multi_deep_get(header,
-        ['ownerText', 'runs', 0, 'navigationEndpoint', 'browseEndpoint', 'browseId'],
-        ['ownerEndpoint', 'browseEndpoint', 'browseId'])
     if metadata['author_id']:
         metadata['author_url'] = 'https://www.youtube.com/channel/' + metadata['author_id']
+
+    if metadata['first_video_id'] is None:
+        metadata['thumbnail'] = None
     else:
-        metadata['author_url'] = None
-    metadata['view_count'] = extract_int(header.get('viewCountText'))
-    metadata['like_count'] = extract_int(header.get('likesCountWithoutLikeText'))
-    for stat in header.get('stats', ()):
-        text = extract_str(stat)
-        if 'videos' in text:
-            conservative_update(metadata, 'video_count', extract_int(text))
-        elif 'views' in text:
-            conservative_update(metadata, 'view_count', extract_int(text))
-        elif 'updated' in text:
-            metadata['time_published'] = extract_date(text)
+        metadata['thumbnail'] = f"https://i.ytimg.com/vi/{metadata['first_video_id']}/hqdefault.jpg"
 
     microformat = deep_get(response, 'microformat', 'microformatDataRenderer',
                            default={})