3 from .common import InfoExtractor
6 class WorldStarHipHopIE(InfoExtractor):
7 _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
9 "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
10 "file": "wshh6a7q1ny0G34ZwuIO.mp4",
11 "md5": "9d04de741161603bf7071bbf4e883186",
13 "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
18 def _real_extract(self, url):
19 m = re.match(self._VALID_URL, url)
20 video_id = m.group('id')
22 webpage_src = self._download_webpage(url, video_id)
24 video_url = self._search_regex('videoId=(.*?)&?',
25 webpage_src, u'video URL', fatal=False)
28 self.to_screen(u'Vevo video detected:')
29 vevo_id = 'vevo:%s' video_url
30 self.url_result(vevo_id)
32 video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
33 webpage_src, u'video URL')
35 if 'youtube' in video_url:
36 self.to_screen(u'Youtube video detected:')
37 return self.url_result(video_url, ie='Youtube')
39 if 'mp4' in video_url:
44 video_title = self._html_search_regex(r"<title>(.*)</title>",
45 webpage_src, u'title')
47 # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
48 thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
49 webpage_src, u'thumbnail', fatal=False)
52 _title = r"""candytitles.*>(.*)</span>"""
53 mobj = re.search(_title, webpage_src)
55 video_title = mobj.group(1)
60 'title' : video_title,
61 'thumbnail' : thumbnail,