yt_dlp/extractor/slutload.py

   1 from .common import InfoExtractor
   2
   3
   4 class SlutloadIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:\w+\.)?slutload\.com/(?:video/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
   6     _TESTS = [{
   7         'url': 'http://www.slutload.com/video/virginie-baisee-en-cam/TD73btpBqSxc/',
   8         'md5': '868309628ba00fd488cf516a113fd717',
   9         'info_dict': {
  10             'id': 'TD73btpBqSxc',
  11             'ext': 'mp4',
  12             'title': 'virginie baisee en cam',
  13             'age_limit': 18,
  14             'thumbnail': r're:https?://.*?\.jpg',
  15         },
  16     }, {
  17         # mobile site
  18         'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
  19         'only_matching': True,
  20     }, {
  21         'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/',
  22         'only_matching': True,
  23     }, {
  24         'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html',
  25         'only_matching': True,
  26     }]
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         embed_page = self._download_webpage(
  32             f'http://www.slutload.com/embed_player/{video_id}', video_id,
  33             'Downloading embed page', fatal=False)
  34
  35         if embed_page:
  36             def extract(what):
  37                 return self._html_search_regex(
  38                     rf'data-video-{what}=(["\'])(?P<url>(?:(?!\1).)+)\1',
  39                     embed_page, f'video {what}', default=None, group='url')
  40
  41             video_url = extract('url')
  42             if video_url:
  43                 title = self._html_search_regex(
  44                     r'<title>([^<]+)', embed_page, 'title', default=video_id)
  45                 return {
  46                     'id': video_id,
  47                     'url': video_url,
  48                     'title': title,
  49                     'thumbnail': extract('preview'),
  50                     'age_limit': 18,
  51                 }
  52
  53         webpage = self._download_webpage(
  54             f'http://www.slutload.com/video/_/{video_id}/', video_id)
  55         title = self._html_search_regex(
  56             r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip()
  57         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
  58         info.update({
  59             'id': video_id,
  60             'title': title,
  61             'age_limit': 18,
  62         })
  63         return info