[extractor/youtube] Handle incomplete initial data from watch page (#6510)

Authored by: coletdjnz

yt_dlp/dependencies/Cryptodome.py

@@ -1,4 +1,4 @@
-import types
+from ..compat.compat_utils import passthrough_module
 
 try:
     import Cryptodome as _parent
@@ -6,9 +6,11 @@ except ImportError:
     try:
         import Crypto as _parent
     except (ImportError, SyntaxError):  # Old Crypto gives SyntaxError in newer Python
-        _parent = types.ModuleType('no_Cryptodome')
+        _parent = passthrough_module(__name__, 'no_Cryptodome')
         __bool__ = lambda: False
 
+del passthrough_module
+
 __version__ = ''
 AES = PKCS1_v1_5 = Blowfish = PKCS1_OAEP = SHA1 = CMAC = RSA = None
 try:

yt_dlp/extractor/nebula.py

@@ -5,7 +5,7 @@ import urllib.error
 from .common import InfoExtractor
 from ..utils import ExtractorError, parse_iso8601
 
-_BASE_URL_RE = r'https?://(?:www\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
+_BASE_URL_RE = r'https?://(?:www\.|beta\.)?(?:watchnebula\.com|nebula\.app|nebula\.tv)'
 
 
 class NebulaBaseIE(InfoExtractor):
@@ -183,6 +183,10 @@ class NebulaIE(NebulaBaseIE):
             'url': 'https://watchnebula.com/videos/money-episode-1-the-draw',
             'only_matching': True,
         },
+        {
+            'url': 'https://beta.nebula.tv/videos/money-episode-1-the-draw',
+            'only_matching': True,
+        },
     ]
 
     def _fetch_video_metadata(self, slug):

yt_dlp/extractor/youtube.py

@@ -4254,12 +4254,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         initial_data = None
         if webpage:
             initial_data = self.extract_yt_initial_data(video_id, webpage, fatal=False)
+            if not traverse_obj(initial_data, 'contents'):
+                self.report_warning('Incomplete data received in embedded initial data; re-fetching using API.')
+                initial_data = None
         if not initial_data:
             query = {'videoId': video_id}
             query.update(self._get_checkok_params())
             initial_data = self._extract_response(
                 item_id=video_id, ep='next', fatal=False,
-                ytcfg=master_ytcfg, query=query,
+                ytcfg=master_ytcfg, query=query, check_get_keys='contents',
                 headers=self.generate_api_headers(ytcfg=master_ytcfg),
                 note='Downloading initial data API JSON')