Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/worldstarhiphop.py

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class WorldStarHipHopIE(InfoExtractor):
   7     _VALID_URL = r'https?://(?:www|m)\.worldstar(?:candy|hiphop)\.com/videos/video\.php\?v=(?P<id>.*)'
   8     _TEST = {
   9         "url": "http://www.worldstarhiphop.com/videos/video.php?v=wshh6a7q1ny0G34ZwuIO",
  10         "file": "wshh6a7q1ny0G34ZwuIO.mp4",
  11         "md5": "9d04de741161603bf7071bbf4e883186",
  12         "info_dict": {
  13             "title": "Video: KO Of The Week: MMA Fighter Gets Knocked Out By Swift Head Kick!"
  14         }
  15     }
  16
  17
  18     def _real_extract(self, url):
  19         m = re.match(self._VALID_URL, url)
  20         video_id = m.group('id')
  21
  22         webpage_src = self._download_webpage(url, video_id)
  23
  24         m_vevo_id = re.search(r'videoId=(.*?)&amp?',
  25             webpage_src)
  26
  27         if m_vevo_id is not None:
  28             self.to_screen(u'Vevo video detected:')
  29             return self.url_result('vevo:%s' % m_vevo_id.group(1), ie='Vevo')
  30
  31         video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
  32             webpage_src, u'video URL')
  33
  34         if 'youtube' in video_url:
  35             self.to_screen(u'Youtube video detected:')
  36             return self.url_result(video_url, ie='Youtube')
  37
  38         if 'mp4' in video_url:
  39             ext = 'mp4'
  40         else:
  41             ext = 'flv'
  42
  43         video_title = self._html_search_regex(r"<title>(.*)</title>",
  44             webpage_src, u'title')
  45
  46         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  47         thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
  48             webpage_src, u'thumbnail', fatal=False)
  49
  50         if not thumbnail:
  51             _title = r"""candytitles.*>(.*)</span>"""
  52             mobj = re.search(_title, webpage_src)
  53             if mobj is not None:
  54                 video_title = mobj.group(1)
  55
  56         results = [{
  57                     'id': video_id,
  58                     'url' : video_url,
  59                     'title' : video_title,
  60                     'thumbnail' : thumbnail,
  61                     'ext' : ext,
  62                     }]
  63         return results