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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6
   7
   8 class SpankBangIE(InfoExtractor):
   9     _VALID_URL = r'https?://(?:(?:www|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
  10     _TESTS = [{
  11         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  12         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  13         'info_dict': {
  14             'id': '3vvn',
  15             'ext': 'mp4',
  16             'title': 'fantasy solo',
  17             'description': 'Watch fantasy solo free HD porn video - 05 minutes - dillion harper masturbates on a bed free adult movies.',
  18             'thumbnail': r're:^https?://.*\.jpg$',
  19             'uploader': 'silly2587',
  20             'age_limit': 18,
  21         }
  22     }, {
  23         # 480p only
  24         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  25         'only_matching': True,
  26     }, {
  27         # no uploader
  28         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         webpage = self._download_webpage(url, video_id)
  35
  36         stream_key = self._html_search_regex(
  37             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
  38             webpage, 'stream key')
  39
  40         formats = [{
  41             'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
  42             'ext': 'mp4',
  43             'format_id': '%sp' % height,
  44             'height': int(height),
  45         } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
  46         self._check_formats(formats, video_id)
  47         self._sort_formats(formats)
  48
  49         title = self._html_search_regex(
  50             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
  51         description = self._og_search_description(webpage)
  52         thumbnail = self._og_search_thumbnail(webpage)
  53         uploader = self._search_regex(
  54             r'class="user"[^>]*><img[^>]+>([^<]+)',
  55             webpage, 'uploader', default=None)
  56
  57         age_limit = self._rta_search(webpage)
  58
  59         return {
  60             'id': video_id,
  61             'title': title,
  62             'description': description,
  63             'thumbnail': thumbnail,
  64             'uploader': uploader,
  65             'formats': formats,
  66             'age_limit': age_limit,
  67         }