X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fyoutube.py;h=762611b89f5982c2c8273a07ffedfae0cba813c2;hb=ba036333bf4ebcba70deb51e77e81dca723fb54d;hp=963c73a2d9cafb3c26e8e5b8bd3c9b52d76b2f44;hpb=bf3c9326634f4a918d0336b2c5f104ac492b5510;p=youtube-dl

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 963c73a2d..762611b89 100644
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -27,6 +27,7 @@ from ..compat import (
     compat_str,
 )
 from ..utils import (
+    bool_or_none,
     clean_html,
     dict_get,
     error_to_compat_str,
@@ -116,6 +117,8 @@ class YoutubeBaseInfoExtractor(InfoExtractor):
                 'f.req': json.dumps(f_req),
                 'flowName': 'GlifWebSignIn',
                 'flowEntry': 'ServiceLogin',
+                # TODO: reverse actual botguard identifier generation algo
+                'bgRequest': '["identifier",""]',
             })
             return self._download_json(
                 url, None, note=note, errnote=errnote,
@@ -368,10 +371,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
                             (?:www\.)?hooktube\.com/|
                             (?:www\.)?yourepeat\.com/|
                             tube\.majestyc\.net/|
+                            # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
                             (?:(?:www|dev)\.)?invidio\.us/|
-                            (?:www\.)?invidiou\.sh/|
-                            (?:www\.)?invidious\.snopyta\.org/|
+                            (?:(?:www|no)\.)?invidiou\.sh/|
+                            (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
                             (?:www\.)?invidious\.kabi\.tk/|
+                            (?:www\.)?invidious\.enkirton\.net/|
+                            (?:www\.)?invidious\.13ad\.de/|
+                            (?:www\.)?tube\.poal\.co/|
                             (?:www\.)?vid\.wxzm\.sx/|
                             youtube\.googleapis\.com/)                        # the various hostnames, with wildcard subdomains
                          (?:.*?\#/)?                                          # handle anchor (#/) redirect urls
@@ -500,6 +507,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         # RTMP (unnamed)
         '_rtmp': {'protocol': 'rtmp'},
+
+        # av01 video only formats sometimes served with "unknown" codecs
+        '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
+        '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
     }
     _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
 
@@ -1306,11 +1319,18 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+            (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'(?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$]+)\(',
              r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
-             r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
+             r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
             jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
@@ -1575,8 +1595,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         return video_id
 
     def _extract_annotations(self, video_id):
-        url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
-        return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
+        return self._download_webpage(
+            'https://www.youtube.com/annotations_invideo', video_id,
+            note='Downloading annotations',
+            errnote='Unable to download video annotations', fatal=False,
+            query={
+                'features': 1,
+                'legacy': 1,
+                'video_id': video_id,
+            })
 
     @staticmethod
     def _extract_chapters(description, duration):
@@ -1868,6 +1895,11 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
         if view_count is None and video_details:
             view_count = int_or_none(video_details.get('viewCount'))
 
+        if is_live is None:
+            is_live = bool_or_none(dict_get(
+                video_details, ('isLive', 'isLiveContent'),
+                skip_false_values=False))
+
         # Check for "rental" videos
         if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
             raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)