Merge pull request #3 from unit193/master

[youtubedl] / youtube_dl / extractor / kankan.py

diff --git a/youtube_dl/extractor/kankan.py b/youtube_dl/extractor/kankan.py
index 23103b163fea1ed6a27cb44dadcf231b478edcdb..a677ff44712794ef54f53a1afe9c55fbacad91e2 100644 (file)
--- a/youtube_dl/extractor/kankan.py
+++ b/youtube_dl/extractor/kankan.py
@@ -10,25 +10,25 @@ _md5 = lambda s: hashlib.md5(s.encode('utf-8')).hexdigest()
 
 class KankanIE(InfoExtractor):
     _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'
 
 class KankanIE(InfoExtractor):
     _VALID_URL = r'https?://(?:.*?\.)?kankan\.com/.+?/(?P<id>\d+)\.shtml'

-    
+

     _TEST = {
         'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',
     _TEST = {
         'url': 'http://yinyue.kankan.com/vod/48/48863.shtml',

-        'file': '48863.flv',

         'md5': '29aca1e47ae68fc28804aca89f29507e',
         'info_dict': {
         'md5': '29aca1e47ae68fc28804aca89f29507e',
         'info_dict': {

+            'id': '48863',
+            'ext': 'flv',

             'title': 'Ready To Go',
         },
         'skip': 'Only available from China',
     }
 
     def _real_extract(self, url):
             'title': 'Ready To Go',
         },
         'skip': 'Only available from China',
     }
 
     def _real_extract(self, url):

-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
+        video_id = self._match_id(url)

         webpage = self._download_webpage(url, video_id)
 
         title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
         surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)
         webpage = self._download_webpage(url, video_id)
 
         title = self._search_regex(r'(?:G_TITLE=|G_MOVIE_TITLE = )[\'"](.+?)[\'"]', webpage, 'video title')
         surls = re.search(r'surls:\[\'.+?\'\]|lurl:\'.+?\.flv\'', webpage).group(0)

-        gcids = re.findall(r"http://.+?/.+?/(.+?)/", surls)
+        gcids = re.findall(r'http://.+?/.+?/(.+?)/', surls)

         gcid = gcids[-1]
 
         info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid
         gcid = gcids[-1]
 
         info_url = 'http://p2s.cl.kankan.com/getCdnresource_flv?gcid=%s' % gcid