_ Git - youtube-dl/blob - youtube_dl/extractor/slutload.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6 )
   7
   8 class SlutloadIE(InfoExtractor):
   9     _VALID_URL = r'^https?://(?:\w+\.)?slutload\.com/video/[^/]+/(?P<videoid>[^/]+)/?$'
  10     _TEST = {
  11         u'url': u'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
  12         u'file': u'TD73btpBqSxc.mp4',
  13         u'md5': u'0cf531ae8006b530bd9df947a6a0df77',
  14         u'info_dict': {
  15             u"title": u"virginie baisee en cam",
  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('videoid')
  24
  25         # Get webpage content
  26         webpage = self._download_webpage(url, video_id)
  27
  28         # Get the video title
  29         video_title = self._html_search_regex(r'<h1><strong>([^<]+)</strong>',
  30             webpage, u'title').strip()
  31
  32         # Get the video url
  33         result = re.compile(r'<div id="vidPlayer"\s+data-url="([^"]+)"\s+previewer-file="([^"]+)"', re.S).search(webpage)
  34         if result is None:
  35             raise ExtractorError(u'ERROR: unable to extract video_url')
  36
  37         video_url, video_thumb = result.group(1,2)
  38
  39         info = {'id': video_id,
  40                 'url': video_url,
  41                 'title': video_title,
  42                 'thumbnail': video_thumb,
  43                 'ext': 'mp4',
  44                 'age_limit': 18}
  45
  46         return [info]