youtube_dl/extractor/slutload.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class SlutloadIE(InfoExtractor):
   9     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<id>[^/]+)/?$'
  10     _TEST = {
  11         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
  12         'md5': '0cf531ae8006b530bd9df947a6a0df77',
  13         'info_dict': {
  14             'id': 'TD73btpBqSxc',
  15             'ext': 'mp4',
  16             "title": "virginie baisee en cam",
  17             "age_limit": 18,
  18             'thumbnail': 're:https?://.*?\.jpg'
  19         }
  20     }
  21
  22     def _real_extract(self, url):
  23         mobj = re.match(self._VALID_URL, url)
  24         video_id = mobj.group('id')
  25
  26         webpage = self._download_webpage(url, video_id)
  27
  28         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
  29                                               webpage, 'title').strip()
  30
  31         video_url = self._html_search_regex(
  32             r'(?s)<div id="vidPlayer"\s+data-url="([^"]+)"',
  33             webpage, 'video URL')
  34         thumbnail = self._html_search_regex(
  35             r'(?s)<div id="vidPlayer"\s+.*?previewer-file="([^"]+)"',
  36             webpage, 'thumbnail', fatal=False)
  37
  38         return {
  39             'id': video_id,
  40             'url': video_url,
  41             'title': video_title,
  42             'thumbnail': thumbnail,
  43             'age_limit': 18
  44         }