| 
									
										
										
										
											2013-06-23 22:04:08 +02:00
										 |  |  | import re | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | from .common import InfoExtractor | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  | class WorldStarHipHopIE(InfoExtractor): | 
					
						
							|  |  |  |     _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)' | 
					
						
							| 
									
										
										
										
											2013-06-27 18:28:45 +02:00
										 |  |  |     _TEST = { | 
					
						
							|  |  |  |         "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO", | 
					
						
							|  |  |  |         "file": "wshh6a7q1ny0G34ZwuIO.mp4", | 
					
						
							|  |  |  |         "md5": "9d04de741161603bf7071bbf4e883186", | 
					
						
							|  |  |  |         "info_dict": { | 
					
						
							|  |  |  |             "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!" | 
					
						
							|  |  |  |         } | 
					
						
							|  |  |  |     } | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2013-06-23 22:04:08 +02:00
										 |  |  | 
 | 
					
						
							|  |  |  |     def _real_extract(self, url): | 
					
						
							|  |  |  |         m = re.match(self._VALID_URL, url) | 
					
						
							|  |  |  |         video_id = m.group('id') | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         webpage_src = self._download_webpage(url, video_id) | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2013-07-30 11:10:17 +02:00
										 |  |  |         m_vevo_id = re.search(r'videoId=(.*?)&?', | 
					
						
							| 
									
										
										
										
											2013-07-29 14:39:14 -07:00
										 |  |  |             webpage_src) | 
					
						
							| 
									
										
										
										
											2013-07-29 12:24:26 -07:00
										 |  |  |          | 
					
						
							| 
									
										
										
										
											2013-07-30 11:10:17 +02:00
										 |  |  |         if m_vevo_id is not None: | 
					
						
							| 
									
										
										
										
											2013-07-29 12:11:57 -07:00
										 |  |  |             self.to_screen(u'Vevo video detected:') | 
					
						
							| 
									
										
										
										
											2013-07-30 11:10:17 +02:00
										 |  |  |             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo') | 
					
						
							| 
									
										
										
										
											2013-07-29 12:11:57 -07:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2013-06-23 22:04:08 +02:00
										 |  |  |         video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)', | 
					
						
							|  |  |  |             webpage_src, u'video URL') | 
					
						
							|  |  |  | 
 | 
					
						
							| 
									
										
										
										
											2013-06-24 18:58:49 -07:00
										 |  |  |         if 'youtube' in video_url: | 
					
						
							|  |  |  |             self.to_screen(u'Youtube video detected:') | 
					
						
							| 
									
										
										
										
											2013-06-25 22:07:31 +02:00
										 |  |  |             return self.url_result(video_url, ie='Youtube') | 
					
						
							| 
									
										
										
										
											2013-06-24 18:58:49 -07:00
										 |  |  | 
 | 
					
						
							| 
									
										
										
										
											2013-06-23 22:04:08 +02:00
										 |  |  |         if 'mp4' in video_url: | 
					
						
							|  |  |  |             ext = 'mp4' | 
					
						
							|  |  |  |         else: | 
					
						
							|  |  |  |             ext = 'flv' | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         video_title = self._html_search_regex(r"<title>(.*)</title>", | 
					
						
							|  |  |  |             webpage_src, u'title') | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         # 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, u'thumbnail', fatal=False) | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         if not thumbnail: | 
					
						
							|  |  |  |             _title = r"""candytitles.*>(.*)</span>""" | 
					
						
							|  |  |  |             mobj = re.search(_title, webpage_src) | 
					
						
							|  |  |  |             if mobj is not None: | 
					
						
							|  |  |  |                 video_title = mobj.group(1) | 
					
						
							|  |  |  | 
 | 
					
						
							|  |  |  |         results = [{ | 
					
						
							|  |  |  |                     'id': video_id, | 
					
						
							|  |  |  |                     'url' : video_url, | 
					
						
							|  |  |  |                     'title' : video_title, | 
					
						
							|  |  |  |                     'thumbnail' : thumbnail, | 
					
						
							|  |  |  |                     'ext' : ext, | 
					
						
							|  |  |  |                     }] | 
					
						
							|  |  |  |         return results |