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

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