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 'mp4' in video_url:
  20             ext = 'mp4'
  21         else:
  22             ext = 'flv'
  23
  24         video_title = self._html_search_regex(r"<title>(.*)</title>",
  25             webpage_src, u'title')
  26
  27         # Getting thumbnail and if not thumbnail sets correct title for WSHH candy video.
  28         thumbnail = self._html_search_regex(r'rel="image_src" href="(.*)" />',
  29             webpage_src, u'thumbnail', fatal=False)
  30
  31         if not thumbnail:
  32             _title = r"""candytitles.*>(.*)</span>"""
  33             mobj = re.search(_title, webpage_src)
  34             if mobj is not None:
  35                 video_title = mobj.group(1)
  36
  37         results = [{
  38                     'id': video_id,
  39                     'url' : video_url,
  40                     'title' : video_title,
  41                     'thumbnail' : thumbnail,
  42                     'ext' : ext,
  43                     }]
  44         return results