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/[^/]+|embed_player|watch)/(?P<id>[^/]+)'
   8     _TESTS = [{
   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': r're:https?://.*?\.jpg'
  17         },
  18     }, {
  19         # mobile site
  20         'url': 'http://mobile.slutload.com/video/masturbation-solo/fviFLmc6kzJ/',
  21         'only_matching': True,
  22     }, {
  23         'url': 'http://www.slutload.com/embed_player/TD73btpBqSxc/',
  24         'only_matching': True,
  25     }, {
  26         'url': 'http://www.slutload.com/watch/TD73btpBqSxc/Virginie-Baisee-En-Cam.html',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         video_id = self._match_id(url)
  32
  33         embed_page = self._download_webpage(
  34             'http://www.slutload.com/embed_player/%s' % video_id, video_id,
  35             'Downloading embed page', fatal=False)
  36
  37         if embed_page:
  38             def extract(what):
  39                 return self._html_search_regex(
  40                     r'data-video-%s=(["\'])(?P<url>(?:(?!\1).)+)\1' % what,
  41                     embed_page, 'video %s' % what, default=None, group='url')
  42
  43             video_url = extract('url')
  44             if video_url:
  45                 title = self._html_search_regex(
  46                     r'<title>([^<]+)', embed_page, 'title', default=video_id)
  47                 return {
  48                     'id': video_id,
  49                     'url': video_url,
  50                     'title': title,
  51                     'thumbnail': extract('preview'),
  52                     'age_limit': 18
  53                 }
  54
  55         webpage = self._download_webpage(
  56             'http://www.slutload.com/video/_/%s/' % video_id, video_id)
  57         title = self._html_search_regex(
  58             r'<h1><strong>([^<]+)</strong>', webpage, 'title').strip()
  59         info = self._parse_html5_media_entries(url, webpage, video_id)[0]
  60         info.update({
  61             'id': video_id,
  62             'title': title,
  63             'age_limit': 18,
  64         })
  65         return info