Imported Upstream version 2013.08.29

[youtubedl] / youtube_dl / extractor / youjizz.py

diff --git a/youtube_dl/extractor/youjizz.py b/youtube_dl/extractor/youjizz.py
index d9efac76eb7707d622fc3c4e499e380521cd40fb..1265639e821bd873b74aeea08811f8c22e966ba1 100644 (file)
--- a/youtube_dl/extractor/youjizz.py
+++ b/youtube_dl/extractor/youjizz.py
@@ -8,6 +8,14 @@ from ..utils import (
 
 class YouJizzIE(InfoExtractor):
     _VALID_URL = r'^(?:https?://)?(?:\w+\.)?youjizz\.com/videos/(?P<videoid>[^.]+).html$'
+    _TEST = {
+        u'url': u'http://www.youjizz.com/videos/zeichentrick-1-2189178.html',
+        u'file': u'2189178.flv',
+        u'md5': u'07e15fa469ba384c7693fd246905547c',
+        u'info_dict': {
+            u"title": u"Zeichentrick 1"
+        }
+    }
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -32,8 +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,