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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import ExtractorError
   5
   6
   7 class RedTubeIE(InfoExtractor):
   8     _VALID_URL = r'http://(?:www\.)?redtube\.com/(?P<id>[0-9]+)'
   9     _TEST = {
  10         'url': 'http://www.redtube.com/66418',
  11         'md5': '7b8c22b5e7098a3e1c09709df1126d2d',
  12         'info_dict': {
  13             'id': '66418',
  14             'ext': 'mp4',
  15             'title': 'Sucked on a toilet',
  16             'age_limit': 18,
  17         }
  18     }
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23
  24         if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
  25             raise ExtractorError('Video %s has been removed' % video_id, expected=True)
  26
  27         video_url = self._html_search_regex(
  28             r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
  29         video_title = self._html_search_regex(
  30             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
  31             webpage, 'title')
  32         video_thumbnail = self._og_search_thumbnail(webpage)
  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': 'mp4',
  42             'title': video_title,
  43             'thumbnail': video_thumbnail,
  44             'age_limit': age_limit,
  45         }