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

   1 from __future__ import unicode_literals
   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         'url': 'http://www.redtube.com/66418',
  10         'info_dict': {
  11             'id': '66418',
  12             'ext': 'mp4',
  13             "title": "Sucked on a toilet",
  14             "age_limit": 18,
  15         }
  16     }
  17
  18     def _real_extract(self, url):
  19         video_id = self._match_id(url)
  20         webpage = self._download_webpage(url, video_id)
  21
  22         video_url = self._html_search_regex(
  23             r'<source src="(.+?)" type="video/mp4">', webpage, 'video URL')
  24         video_title = self._html_search_regex(
  25             r'<h1 class="videoTitle[^"]*">(.+?)</h1>',
  26             webpage, 'title')
  27         video_thumbnail = self._og_search_thumbnail(webpage)
  28
  29         # No self-labeling, but they describe themselves as
  30         # "Home of Videos Porno"
  31         age_limit = 18
  32
  33         return {
  34             'id': video_id,
  35             'url': video_url,
  36             'ext': 'mp4',
  37             'title': video_title,
  38             'thumbnail': video_thumbnail,
  39             'age_limit': age_limit,
  40         }