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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4
   5
   6 class SlutloadIE(InfoExtractor):
   7     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
   8     _TEST = {
   9         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
  10         'md5': '868309628ba00fd488cf516a113fd717',
  11         'info_dict': {
  12             'id': 'TD73btpBqSxc',
  13             'ext': 'mp4',
  14             'title': 'virginie baisee en cam',
  15             'age_limit': 18,
  16             'thumbnail': 're:https?://.*?\.jpg'
  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         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
  25                                               webpage, 'title').strip()
  26
  27         video_url = self._html_search_regex(
  28             r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
  29             webpage, 'video URL')
  30         thumbnail = self._html_search_regex(
  31             r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
  32             webpage, 'thumbnail', fatal=False)
  33
  34         return {
  35             'id': video_id,
  36             'url': video_url,
  37             'title': video_title,
  38             'thumbnail': thumbnail,
  39             'age_limit': 18
  40         }