Merge branch 'fstirlitz-filmon'

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 630586796694f963d0c19473ccd97c23b8c2ccf0..f2f75110445a6bad461fcd92d4ae3d26dd456d69 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -1028,8 +1028,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
     def _parse_sig_js(self, jscode):
         funcname = self._search_regex(
-            r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
-            'Initial JS player signature function name')
+            (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
+             r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\('),
+            jscode, 'Initial JS player signature function name', group='sig')
 
         jsi = JSInterpreter(jscode)
         initial_function = jsi.extract_function(funcname)
@@ -1050,6 +1051,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
 
         if player_url.startswith('//'):
             player_url = 'https:' + player_url
+        elif not re.match(r'https?://', player_url):
+            player_url = compat_urlparse.urljoin(
+                'https://www.youtube.com', player_url)
         try:
             player_id = (player_url, self._signature_cache_id(s))
             if player_id not in self._player_cache:
@@ -1853,13 +1857,13 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
                             youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
                         )
                         (
-                            (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
+                            (?:PL|LL|EC|UU|FL|RD|UL|TL)?[0-9A-Za-z-_]{10,}
                             # Top tracks, they can also include dots
                             |(?:MC)[\w\.]*
                         )
                         .*
                      |
-                        ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
+                        ((?:PL|LL|EC|UU|FL|RD|UL|TL)[0-9A-Za-z-_]{10,})
                      )"""
     _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
     _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&amp;[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
@@ -1981,6 +1985,9 @@ class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
     }, {
         'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
         'only_matching': True,
+    }, {
+        'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
+        'only_matching': True,
     }]
 
     def _real_initialize(self):
@@ -2341,18 +2348,18 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
         videos = []
         limit = n
 
+        url_query = {
+            'search_query': query.encode('utf-8'),
+        }
+        url_query.update(self._EXTRA_QUERY_ARGS)
+        result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
+
         for pagenum in itertools.count(1):
-            url_query = {
-                'search_query': query.encode('utf-8'),
-                'page': pagenum,
-                'spf': 'navigate',
-            }
-            url_query.update(self._EXTRA_QUERY_ARGS)
-            result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
             data = self._download_json(
                 result_url, video_id='query "%s"' % query,
                 note='Downloading page %s' % pagenum,
-                errnote='Unable to download API page')
+                errnote='Unable to download API page',
+                query={'spf': 'navigate'})
             html_content = data[1]['body']['content']
 
             if 'class="search-message' in html_content:
@@ -2364,6 +2371,12 @@ class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
             videos += new_videos
             if not new_videos or len(videos) > limit:
                 break
+            next_link = self._html_search_regex(
+                r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
+                html_content, 'next link', default=None)
+            if next_link is None:
+                break
+            result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
 
         if len(videos) > n:
             videos = videos[:n]