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

   1 import re
   2
   3 from .common import InfoExtractor
   4
   5
   6 class RedTubeIE(InfoExtractor):
   7     _VALID_URL = r'(?:http://)?(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
   8     _TEST = {
   9         u'url': u'http://www.redtube.com/66418',
  10         u'file': u'66418.mp4',
  11         u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
  12         u'info_dict': {
  13             u"title": u"Sucked on a toilet",
  14             u"age_limit": 18,
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         mobj = re.match(self._VALID_URL, url)
  20
  21         video_id = mobj.group('id')
  22         video_extension = 'mp4'
  23         webpage = self._download_webpage(url, video_id)
  24
  25         self.report_extraction(video_id)
  26
  27         video_url = self._html_search_regex(
  28             r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
  29
  30         video_title = self._html_search_regex(
  31             r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
  32             webpage, u'title')
  33
  34         # No self-labeling, but they describe themselves as
  35         # "Home of Videos Porno"
  36         age_limit = 18
  37
  38         return {
  39             'id':        video_id,
  40             'url':       video_url,
  41             'ext':       video_extension,
  42             'title':     video_title,
  43             'age_limit': age_limit,
  44         }