[youtube] Fix sigfunc name extraction (closes #23819)

[youtube-dl] / youtube_dl / extractor / youtube.py

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index f002d870e1fea8e5830208e1e6be0e16e499465c..eacaa5ecdb70d2a16748b4c2e58edc14d7d69484 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -69,7 +69,7 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
     # If True it will raise an error if no login info is provided
     _LOGIN_REQUIRED = False
 
-    _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
+    _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
 
     def _set_language(self):
         self._set_cookie(
@@ -372,7 +372,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
     _VALID_URL = r"""(?x)^
                      (
                          (?:https?://|//)                                    # http(s):// or protocol-independent URL
-                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
+                         (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
                             (?:www\.)?pwnyoutube\.com/|
                             (?:www\.)?hooktube\.com/|
@@ -383,19 +383,21 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:(?:www|no)\.)?invidiou\.sh/|
                             (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
                             (?:www\.)?invidious\.kabi\.tk/|
-                            (?:www\.)?invidious\.enkirton\.net/|
                             (?:www\.)?invidious\.13ad\.de/|
                             (?:www\.)?invidious\.mastodon\.host/|
                             (?:www\.)?invidious\.nixnet\.xyz/|
+                            (?:www\.)?invidious\.drycat\.fr/|
                             (?:www\.)?tube\.poal\.co/|
                             (?:www\.)?vid\.wxzm\.sx/|
                             (?:www\.)?yt\.elukerio\.org/|
+                            (?:www\.)?yt\.lelux\.fi/|
                             (?:www\.)?kgg2m7yk5aybusll\.onion/|
                             (?:www\.)?qklhadlycap4cnod\.onion/|
                             (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
                             (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
                             (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
                             (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
+                            (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
                          (?:                                                  # the various things that can precede the ID:
@@ -1222,6 +1224,10 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                 'skip_download': True,
             },
         },
+        {
+            'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
+            'only_matching': True,
+        },
     ]
 
     def __init__(self, *args, **kwargs):
@@ -1337,6 +1343,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         funcname = self._search_regex(
             (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
              r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
              # Obsolete patterns
              r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
@@ -2463,7 +2470,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                         (?:\w+\.)?
                         (?:
                             (?:
-                                youtube\.com|
+                                youtube(?:kids)?\.com|
                                 invidio\.us
                             )
                             /
@@ -2475,7 +2482,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                             youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
                         )
                         (
-                            (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
+                            (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
                             # Top tracks, they can also include dots
                             |(?:MC)[\w\.]*
                         )
@@ -2645,6 +2652,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
     }, {
         'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
+        'only_matching': True,
     }]
 
     def _real_initialize(self):
@@ -2740,7 +2750,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
             page, 'title', default=None)
 
         _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
-        uploader = self._search_regex(
+        uploader = self._html_search_regex(
             r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
             page, 'uploader', default=None)
         mobj = re.search(
@@ -2815,7 +2825,7 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
 
 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
     IE_DESC = 'YouTube.com channels'
-    _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
+    _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
     _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
     _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
     IE_NAME = 'youtube:channel'
@@ -2843,6 +2853,9 @@ class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
     }, {
         'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
         'only_matching': True,
+    }, {
+        'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
+        'only_matching': True,
     }]
 
     @classmethod