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         # md5 varies from time to time, as in
  12         # https://travis-ci.org/rg3/youtube-dl/jobs/14052463#L295
  13         #u'md5': u'7b8c22b5e7098a3e1c09709df1126d2d',
  14         u'info_dict': {
  15             u"title": u"Sucked on a toilet",
  16             u"age_limit": 18,
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22
  23         video_id = mobj.group('id')
  24         video_extension = 'mp4'
  25         webpage = self._download_webpage(url, video_id)
  26
  27         self.report_extraction(video_id)
  28
  29         video_url = self._html_search_regex(
  30             r'<source src="(.+?)" type="video/mp4">', webpage, u'video URL')
  31
  32         video_title = self._html_search_regex(
  33             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
  34             webpage, u'title')
  35
  36         video_thumbnail = self._html_search_regex(
  37             r'playerInnerHTML.+?<img\s+src="(.+?)"',
  38             webpage, u'thumbnail', fatal=False)
  39
  40         # No self-labeling, but they describe themselves as
  41         # "Home of Videos Porno"
  42         age_limit = 18
  43
  44         return {
  45             'id':        video_id,
  46             'url':       video_url,
  47             'ext':       video_extension,
  48             'title':     video_title,
  49             'thumbnail': video_thumbnail,
  50             'age_limit': age_limit,
  51         }