working - worldstarhiphop IE

[youtube-dl] / youtube_dl / InfoExtractors.py

diff --git a/youtube_dl/InfoExtractors.py b/youtube_dl/InfoExtractors.py
index 8be2f160c1092cbfd0593431dfaaade6268a4827..f69bad4f3a77d49be2d8b9cac3c6c256f4ee9898 100755 (executable)
--- a/youtube_dl/InfoExtractors.py
+++ b/youtube_dl/InfoExtractors.py
@@ -2557,7 +2557,7 @@ class EscapistIE(InfoExtractor):
             'uploader': showName,
             'upload_date': None,
             'title': showName,
-            'ext': 'flv',
+            'ext': 'mp4',
             'thumbnail': imgUrl,
             'description': description,
             'player_url': playerUrl,
@@ -3655,24 +3655,23 @@ class UstreamIE(InfoExtractor):
         return [info]
 
 class WorldStarHipHopIE(InfoExtractor):
-    _VALID_URL = r"""(http://(?:www|m).worldstar(?:candy|hiphop)\.com.*)"""
+    _VALID_URL = r'http://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
     IE_NAME = u'WorldStarHipHop'
 
     def _real_extract(self, url):
-        results = []
-
         _src_url = r"""(http://hw-videos.*(?:mp4|flv))"""
 
         webpage_src = compat_urllib_request.urlopen(str(url)).read()
+        webpage_src = webpage_src.decode('utf-8')
 
         mobj = re.search(_src_url, webpage_src)
 
         if mobj is not None:
             video_url = mobj.group()
             if 'mp4' in video_url:
-                ext = '.mp4'
+                ext = 'mp4'
             else:
-                ext = '.flv'
+                ext = 'flv'
         else:
             video_url = None
             ext = None
@@ -3683,16 +3682,10 @@ class WorldStarHipHopIE(InfoExtractor):
         
         if mobj is not None:
             title = mobj.group(1)
-            title = title.replace("&#039;", "")
-            title = title.replace("&#39;", "")
-            title = title.replace('Video: ', '')
-            title = title.replace('&quot;', '"')
-            title = title.replace('&amp;', 'n')
         else:
-            title = None
+            title = 'World Start Hip Hop - %s' % time.ctime()
 
         _thumbnail = r"""rel="image_src" href="(.*)" />"""
-
         mobj = re.search(_thumbnail, webpage_src)
 
         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
@@ -3705,13 +3698,16 @@ class WorldStarHipHopIE(InfoExtractor):
                 title = mobj.group(1)
             thumbnail = None
 
-        results.append({
-            'url' : video_url,
-            'title' : title,
-            'thumbnail' : thumbnail,
-            'ext' : ext
-            })
-
+        m = re.match(self._VALID_URL, url)
+        video_id = m.group('id')
+        
+        results = [{
+                    'id': video_id,
+                    'url' : video_url,
+                    'title' : title,
+                    'thumbnail' : thumbnail,
+                    'ext' : ext,
+                    }]
         return results
 
 class RBMARadioIE(InfoExtractor):