youtube_dl/extractor/spankbang.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import ExtractorError
   7
   8
   9 class SpankBangIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:(?:www|m|[a-z]{2})\.)?spankbang\.com/(?P<id>[\da-z]+)/video'
  11     _TESTS = [{
  12         'url': 'http://spankbang.com/3vvn/video/fantasy+solo',
  13         'md5': '1cc433e1d6aa14bc376535b8679302f7',
  14         'info_dict': {
  15             'id': '3vvn',
  16             'ext': 'mp4',
  17             'title': 'fantasy solo',
  18             'description': 'Watch fantasy solo free HD porn video - 05 minutes -  Babe,Masturbation,Solo,Toy  - dillion harper masturbates on a bed free adult movies sexy clips.',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'uploader': 'silly2587',
  21             'age_limit': 18,
  22         }
  23     }, {
  24         # 480p only
  25         'url': 'http://spankbang.com/1vt0/video/solvane+gangbang',
  26         'only_matching': True,
  27     }, {
  28         # no uploader
  29         'url': 'http://spankbang.com/lklg/video/sex+with+anyone+wedding+edition+2',
  30         'only_matching': True,
  31     }, {
  32         # mobile page
  33         'url': 'http://m.spankbang.com/1o2de/video/can+t+remember+her+name',
  34         'only_matching': True,
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39         webpage = self._download_webpage(url, video_id)
  40
  41         if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
  42             raise ExtractorError(
  43                 'Video %s is not available' % video_id, expected=True)
  44
  45         stream_key = self._html_search_regex(
  46             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
  47             webpage, 'stream key')
  48
  49         formats = [{
  50             'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
  51             'ext': 'mp4',
  52             'format_id': '%sp' % height,
  53             'height': int(height),
  54         } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
  55         self._check_formats(formats, video_id)
  56         self._sort_formats(formats)
  57
  58         title = self._html_search_regex(
  59             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
  60         description = self._og_search_description(webpage)
  61         thumbnail = self._og_search_thumbnail(webpage)
  62         uploader = self._search_regex(
  63             r'class="user"[^>]*><img[^>]+>([^<]+)',
  64             webpage, 'uploader', default=None)
  65
  66         age_limit = self._rta_search(webpage)
  67
  68         return {
  69             'id': video_id,
  70             'title': title,
  71             'description': description,
  72             'thumbnail': thumbnail,
  73             'uploader': uploader,
  74             'formats': formats,
  75             'age_limit': age_limit,
  76         }