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     IE_NAME = u'WorldStarHipHop'
   9
  10     def _real_extract(self, url):
  11         m = re.match(self._VALID_URL, url)
  12         video_id = m.group('id')
  13
  14         webpage_src = self._download_webpage(url, video_id)
  15
  16         video_url = self._search_regex(r'so\.addVariable\("file","(.*?)"\)',
  17             webpage_src, u'video URL')
  18
  19         if 'youtube' in video_url:
  20             self.to_screen(u'Youtube video detected:')
  21             return self.url_result(video_url, ie='Youtube')
  22
  23         if 'mp4' in video_url:
  24             ext = 'mp4'
  25         else:
  26             ext = 'flv'
  27
  28         video_title = self._html_search_regex(r"<title>(.*)</title>",
  29             webpage_src, u'title')
  30
  31         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  32         thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
  33             webpage_src, u'thumbnail', fatal=False)
  34
  35         if not thumbnail:
  36             _title = r"""candytitles.*>(.*)</span>"""
  37             mobj = re.search(_title, webpage_src)
  38             if mobj is not None:
  39                 video_title = mobj.group(1)
  40
  41         results = [{
  42                     'id': video_id,
  43                     'url' : video_url,
  44                     'title' : video_title,
  45                     'thumbnail' : thumbnail,
  46                     'ext' : ext,
  47                     }]
  48         return results