Merge tag 'upstream/2014.11.21'

[youtubedl] / youtube_dl / extractor / worldstarhiphop.py

diff --git a/youtube_dl/extractor/worldstarhiphop.py b/youtube_dl/extractor/worldstarhiphop.py
index 4e89acd81bbb5ddfb97b1da3381b1b9f25873c96..bda3870db9f16e12c721c361696656df8be8a1b3 100644 (file)
--- a/youtube_dl/extractor/worldstarhiphop.py
+++ b/youtube_dl/extractor/worldstarhiphop.py
@@ -13,37 +13,35 @@ class WorldStarHipHopIE(InfoExtractor):
         "info_dict": {
             "id": "wshh6a7q1ny0G34ZwuIO",
             "ext": "mp4",
         "info_dict": {
             "id": "wshh6a7q1ny0G34ZwuIO",
             "ext": "mp4",

-            "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
+            "title": "KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"

         }
     }
 
     def _real_extract(self, url):
         }
     }
 
     def _real_extract(self, url):

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

 
 

-        webpage_src = self._download_webpage(url, video_id)
-
-        m_vevo_id = re.search(r'videoId=(.*?)&amp?',
-                              webpage_src)
+        m_vevo_id = re.search(r'videoId=(.*?)&amp?', webpage)

         if m_vevo_id is not None:
             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
 
         video_url = self._search_regex(
         if m_vevo_id is not None:
             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
 
         video_url = self._search_regex(

-            r'so\.addVariable\("file","(.*?)"\)', webpage_src, 'video URL')
+            r'so\.addVariable\("file","(.*?)"\)', webpage, 'video URL')

 
         if 'youtube' in video_url:
             return self.url_result(video_url, ie='Youtube')
 
         video_title = self._html_search_regex(
 
         if 'youtube' in video_url:
             return self.url_result(video_url, ie='Youtube')
 
         video_title = self._html_search_regex(

-            r"<title>(.*)</title>", webpage_src, 'title')
+            r'(?s)<div class="content-heading">\s*<h1>(.*?)</h1>',
+            webpage, 'title')

 
         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
         thumbnail = self._html_search_regex(
 
         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
         thumbnail = self._html_search_regex(

-            r'rel="image_src" href="(.*)" />', webpage_src, 'thumbnail',
+            r'rel="image_src" href="(.*)" />', webpage, 'thumbnail',

             fatal=False)
         if not thumbnail:
             fatal=False)
         if not thumbnail:

-            _title = r"""candytitles.*>(.*)</span>"""
-            mobj = re.search(_title, webpage_src)
+            _title = r'candytitles.*>(.*)</span>'
+            mobj = re.search(_title, webpage)

             if mobj is not None:
                 video_title = mobj.group(1)
 
             if mobj is not None:
                 video_title = mobj.group(1)