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         }
  15     }
  16
  17     def _real_extract(self, url):
  18         mobj = re.match(self._VALID_URL, url)
  19
  20         video_id = mobj.group('id')
  21         video_extension = 'mp4'
  22         webpage = self._download_webpage(url, video_id)
  23
  24         self.report_extraction(video_id)
  25
  26         video_url = self._html_search_regex(
  27             r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
  28
  29         video_title = self._html_search_regex(
  30             r'<h1 class="videoTitle slidePanelMovable">(.+?)</h1>',
  31             webpage, u'title')
  32
  33         # No self-labeling, but they describe themselves as
  34         # "Home of Videos Porno"
  35         age_limit = 18
  36
  37         return {
  38             'id':        video_id,
  39             'url':       video_url,
  40             'ext':       video_extension,
  41             'title':     video_title,
  42             'age_limit': age_limit,
  43         }