_ Git - youtube-dl/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     _TEST = {
  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': 'dillion harper masturbates on a bed',
  18             'thumbnail': 're:^https?://.*\.jpg$',
  19             'uploader': 'silly2587',
  20             'age_limit': 18,
  21         }
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         stream_key = self._html_search_regex(
  29             r'''var\s+stream_key\s*=\s*['"](.+?)['"]''',
  30             webpage, 'stream key')
  31
  32         formats = [{
  33             'url': 'http://spankbang.com/_%s/%s/title/%sp__mp4' % (video_id, stream_key, height),
  34             'ext': 'mp4',
  35             'format_id': '%sp' % height,
  36             'height': int(height),
  37         } for height in re.findall(r'<(?:span|li|p)[^>]+[qb]_(\d+)p', webpage)]
  38         self._check_formats(formats, video_id)
  39         self._sort_formats(formats)
  40
  41         title = self._html_search_regex(
  42             r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
  43         description = self._search_regex(
  44             r'class="desc"[^>]*>([^<]+)',
  45             webpage, 'description', default=None)
  46         thumbnail = self._og_search_thumbnail(webpage)
  47         uploader = self._search_regex(
  48             r'class="user"[^>]*>([^<]+)',
  49             webpage, 'uploader', fatal=False)
  50
  51         age_limit = self._rta_search(webpage)
  52
  53         return {
  54             'id': video_id,
  55             'title': title,
  56             'description': description,
  57             'thumbnail': thumbnail,
  58             'uploader': uploader,
  59             'formats': formats,
  60             'age_limit': age_limit,
  61         }