about summary refs log tree commit diff
path: root/youtube_dl/extractor/youjizz.py
diff options
context:
space:
mode:
authorJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-13 12:07:07 +0200
committerJaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com>2013-07-13 12:07:07 +0200
commit2e78b2beadcdb1fc2cfa60789bb501cccd5dbce5 (patch)
treecab31317c6a3f9ae7daa8851fb8e98f9d4fa8829 /youtube_dl/extractor/youjizz.py
parentd8269e1dfbe06d4b373211e54476bcd326f69abe (diff)
downloadyoutube-dl-2e78b2beadcdb1fc2cfa60789bb501cccd5dbce5.tar.gz
youtube-dl-2e78b2beadcdb1fc2cfa60789bb501cccd5dbce5.tar.xz
youtube-dl-2e78b2beadcdb1fc2cfa60789bb501cccd5dbce5.zip
YouJizzIE: support videos that define the urls in a playlist page (closes #1037)
Diffstat (limited to 'youtube_dl/extractor/youjizz.py')
-rw-r--r--youtube_dl/extractor/youjizz.py16
1 files changed, 14 insertions, 2 deletions
diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py
index 6f022670c..1265639e8 100644
--- a/youtube_dl/extractor/youjizz.py
+++ b/youtube_dl/extractor/youjizz.py
@@ -40,8 +40,20 @@ class YouJizzIE(InfoExtractor):
         webpage = self._download_webpage(embed_page_url, video_id)
 
         # Get the video URL
-        video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
-            webpage, u'video URL')
+        m_playlist = re.search(r'so.addVariable\("playlist", ?"(?P<playlist>.+?)"\);', webpage)
+        if m_playlist is not None:
+            playlist_url = m_playlist.group('playlist')
+            playlist_page = self._download_webpage(playlist_url, video_id,
+                                                   u'Downloading playlist page')
+            m_levels = list(re.finditer(r'<level bitrate="(\d+?)" file="(.*?)"', playlist_page))
+            if len(m_levels) == 0:
+                raise ExtractorError(u'Unable to extract video url')
+            videos = [(int(m.group(1)), m.group(2)) for m in m_levels]
+            (_, video_url) = sorted(videos)[0]
+            video_url = video_url.replace('%252F', '%2F')
+        else:
+            video_url = self._search_regex(r'so.addVariable\("file",encodeURIComponent\("(?P<source>[^"]+)"\)\);',
+                                           webpage, u'video URL')
 
         info = {'id': video_id,
                 'url': video_url,