Merge remote-tracking branch 'drags/yt-feed-loadmore'

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

diff --git a/youtube_dl/extractor/youtube.py b/youtube_dl/extractor/youtube.py
index 70f670682e837745da6b181cc4d06e2970d78e89..e28db2b5a57c7208ac61ab90a026b0d26e050ba5 100644 (file)
--- a/youtube_dl/extractor/youtube.py
+++ b/youtube_dl/extractor/youtube.py
@@ -199,7 +199,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
     IE_DESC = u'YouTube.com'
     _VALID_URL = r"""(?x)^
                      (
-                         (?:https?://|//)?                                    # http(s):// or protocol-independent URL (optional)
+                         (?:https?://|//)                                    # http(s):// or protocol-independent URL
                          (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
                             (?:www\.)?deturl\.com/www\.youtube\.com/|
                             (?:www\.)?pwnyoutube\.com/|
@@ -217,7 +217,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor, SubtitlesInfoExtractor):
                              )
                          ))
                          |youtu\.be/                                          # just youtu.be/xxxx
-                         |https?://(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
+                         |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
                          )
                      )?                                                       # all until now is optional -> you can pass the naked ID
                      ([0-9A-Za-z_-]{11})                                      # here is it! the YouTube video ID
@@ -1397,6 +1397,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                                           u'%s feed' % self._FEED_NAME,
                                           u'Downloading page %s' % i)
             feed_html = info.get('feed_html') or info.get('content_html')
+            load_more_widget_html = info.get('load_more_widget_html') or feed_html
             m_ids = re.finditer(r'"/watch\?v=(.*?)["&]', feed_html)
             ids = orderedSet(m.group(1) for m in m_ids)
             feed_entries.extend(
@@ -1404,7 +1405,7 @@ class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
                 for video_id in ids)
             mobj = re.search(
                 r'data-uix-load-more-href="/?[^"]+paging=(?P<paging>\d+)',
-                feed_html)
+                load_more_widget_html)
             if mobj is None:
                 break
             paging = mobj.group('paging')