yt_dlp/extractor/mofosex.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     int_or_none,
   6     str_to_int,
   7     unified_strdate,
   8 )
   9 from .keezmovies import KeezMoviesIE
  10
  11
  12 class MofosexIE(KeezMoviesIE):
  13     _VALID_URL = r'https?://(?:www\.)?mofosex\.com/videos/(?P<id>\d+)/(?P<display_id>[^/?#&.]+)\.html'
  14     _TESTS = [{
  15         'url': 'http://www.mofosex.com/videos/318131/amateur-teen-playing-and-masturbating-318131.html',
  16         'md5': '558fcdafbb63a87c019218d6e49daf8a',
  17         'info_dict': {
  18             'id': '318131',
  19             'display_id': 'amateur-teen-playing-and-masturbating-318131',
  20             'ext': 'mp4',
  21             'title': 'amateur teen playing and masturbating',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'upload_date': '20121114',
  24             'view_count': int,
  25             'like_count': int,
  26             'dislike_count': int,
  27             'age_limit': 18,
  28         }
  29     }, {
  30         # This video is no longer available
  31         'url': 'http://www.mofosex.com/videos/5018/japanese-teen-music-video.html',
  32         'only_matching': True,
  33     }]
  34
  35     def _real_extract(self, url):
  36         webpage, info = self._extract_info(url)
  37
  38         view_count = str_to_int(self._search_regex(
  39             r'VIEWS:</span>\s*([\d,.]+)', webpage, 'view count', fatal=False))
  40         like_count = int_or_none(self._search_regex(
  41             r'id=["\']amountLikes["\'][^>]*>(\d+)', webpage,
  42             'like count', fatal=False))
  43         dislike_count = int_or_none(self._search_regex(
  44             r'id=["\']amountDislikes["\'][^>]*>(\d+)', webpage,
  45             'like count', fatal=False))
  46         upload_date = unified_strdate(self._html_search_regex(
  47             r'Added:</span>([^<]+)', webpage, 'upload date', fatal=False))
  48
  49         info.update({
  50             'view_count': view_count,
  51             'like_count': like_count,
  52             'dislike_count': dislike_count,
  53             'upload_date': upload_date,
  54             'thumbnail': self._og_search_thumbnail(webpage),
  55         })
  56
  57         return info
  58
  59
  60 class MofosexEmbedIE(InfoExtractor):
  61     _VALID_URL = r'https?://(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=(?P<id>\d+)'
  62     _TESTS = [{
  63         'url': 'https://www.mofosex.com/embed/?videoid=318131&referrer=KM',
  64         'only_matching': True,
  65     }]
  66
  67     @staticmethod
  68     def _extract_urls(webpage):
  69         return re.findall(
  70             r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?mofosex\.com/embed/?\?.*?\bvideoid=\d+)',
  71             webpage)
  72
  73     def _real_extract(self, url):
  74         video_id = self._match_id(url)
  75         return self.url_result(
  76             'http://www.mofosex.com/videos/{0}/{0}.html'.format(video_id),
  77             ie=MofosexIE.ie_key(), video_id=video_id)