[youtube] Fix extraction.

[youtube-dl] / youtube_dl / extractor / ku6.py

diff --git a/youtube_dl/extractor/ku6.py b/youtube_dl/extractor/ku6.py
index eecbe2696fd8ddfe718cb46452a584f70ec41edf..a574408e55b6a5ee251d94ca1d0346b9e34ac0b8 100644 (file)
--- a/youtube_dl/extractor/ku6.py
+++ b/youtube_dl/extractor/ku6.py
@@ -1,30 +1,27 @@
 from __future__ import unicode_literals
-import re
+
 from .common import InfoExtractor
 
+
 class Ku6IE(InfoExtractor):
-    _VALID_URL = r'http://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
+    _VALID_URL = r'https?://v\.ku6\.com/show/(?P<id>[a-zA-Z0-9\-\_]+)(?:\.)*html'
     _TEST = {
         'url': 'http://v.ku6.com/show/JG-8yS14xzBr4bCn1pu0xw...html',
+        'md5': '01203549b9efbb45f4b87d55bdea1ed1',
         'info_dict': {
             'id': 'JG-8yS14xzBr4bCn1pu0xw',
             'ext': 'f4v',
-            u'title': u'techniques test',
+            'title': 'techniques test',
         }
     }
 
-
-
     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._html_search_meta('title', webpage, 'title')
-        title = self._search_regex(r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
-        self.to_screen('title: '+title)
 
-        dataUrl = 'http://v.ku6.com/fetchVideo4Player/'+video_id+'.html'
+        title = self._html_search_regex(
+            r'<h1 title=.*>(.*?)</h1>', webpage, 'title')
+        dataUrl = 'http://v.ku6.com/fetchVideo4Player/%s.html' % video_id
         jsonData = self._download_json(dataUrl, video_id)
         downloadUrl = jsonData['data']['f']
 
@@ -32,7 +29,4 @@ class Ku6IE(InfoExtractor):
             'id': video_id,
             'title': title,
             'url': downloadUrl
-            # TODO more properties (see youtube_dl/extractor/common.py)
-
         }
-