yt_dlp/extractor/mofosex.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     str_to_int,
   5     unified_strdate,
   6 )
   7 from .keezmovies import KeezMoviesIE
   8
   9
  10 class MofosexIE(KeezMoviesIE):  # XXX: Do not subclass from concrete IE
  11     _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
  12     _TESTS = [{
  13         'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
  14         'md5': '558fcdafbb63a87c019218d6e49daf8a',
  15         'info_dict': {
  16             'id': '318131',
  17             'display_id': 'amateur-teen-playing-and-masturbating-318131',
  18             'ext': 'mp4',
  19             'title': 'amateur teen playing and masturbating',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'upload_date': '20121114',
  22             'view_count': int,
  23             'like_count': int,
  24             'dislike_count': int,
  25             'age_limit': 18,
  26         }
  27     }, {
  28         # This video is no longer available
  29         'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
  30         'only_matching': True,
  31     }]
  32
  33     def _real_extract(self, url):
  34         webpage, info = self._extract_info(url)
  35
  36         view_count = str_to_int(self._search_regex(
  37             r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
  38         like_count = int_or_none(self._search_regex(
  39             r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
  40             'like count', fatal=False))
  41         dislike_count = int_or_none(self._search_regex(
  42             r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
  43             'like count', fatal=False))
  44         upload_date = unified_strdate(self._html_search_regex(
  45             r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
  46
  47         info.update({
  48             'view_count': view_count,
  49             'like_count': like_count,
  50             'dislike_count': dislike_count,
  51             'upload_date': upload_date,
  52             'thumbnail': self._og_search_thumbnail(webpage),
  53         })
  54
  55         return info
  56
  57
  58 class MofosexEmbedIE(InfoExtractor):
  59     _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
  60     _EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)']
  61     _TESTS = [{
  62         'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
  63         'only_matching': True,
  64     }]
  65
  66     def _real_extract(self, url):
  67         video_id = self._match_id(url)
  68         return self.url_result(
  69             'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id),
  70             ie=MofosexIE.ie_key(), video_id=video_id)