yt_dlp/extractor/pornflip.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none, parse_duration, parse_iso8601
   3
   4
   5 class PornFlipIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?pornflip\.com/(?:(embed|sv|v)/)?(?P<id>[^/]+)'
   7     _TESTS = [
   8         {
   9             'url': 'https://www.pornflip.com/dzv9Mtw1qj2/sv/brazzers-double-dare-two-couples-fucked-jenna-reid-maya-bijou',
  10             'info_dict': {
  11                 'id': 'dzv9Mtw1qj2',
  12                 'ext': 'mp4',
  13                 'title': 'Brazzers - Double Dare Two couples fucked Jenna Reid Maya Bijou',
  14                 'description': 'md5:d2b69e6cc743c5fd158e162aa7f05821',
  15                 'duration': 476,
  16                 'like_count': int,
  17                 'dislike_count': int,
  18                 'view_count': int,
  19                 'timestamp': 1617846819,
  20                 'upload_date': '20210408',
  21                 'uploader': 'Brazzers',
  22                 'age_limit': 18,
  23             },
  24             'params': {
  25                 'skip_download': True,
  26             },
  27         },
  28         {
  29             'url': 'https://www.pornflip.com/v/IrJEC40i21L',
  30             'only_matching': True,
  31         },
  32         {
  33             'url': 'https://www.pornflip.com/Z3jzbChC5-P/sexintaxi-e-sereyna-gomez-czech-naked-couple',
  34             'only_matching': True,
  35         },
  36         {
  37             'url': 'https://www.pornflip.com/embed/bLcDFxnrZnU',
  38             'only_matching': True,
  39         },
  40     ]
  41     _HOST = 'www.pornflip.com'
  42
  43     def _real_extract(self, url):
  44         video_id = self._match_id(url)
  45         webpage = self._download_webpage(
  46             'https://{}/sv/{}'.format(self._HOST, video_id), video_id, headers={'host': self._HOST})
  47         description = self._html_search_regex(r'&p\[summary\]=(.*?)\s*&p', webpage, 'description', fatal=False)
  48         duration = self._search_regex(r'"duration":\s+"([^"]+)",', webpage, 'duration', fatal=False)
  49         view_count = self._search_regex(r'"interactionCount":\s+"([^"]+)"', webpage, 'view_count', fatal=False)
  50         title = self._html_search_regex(r'id="mediaPlayerTitleLink"[^>]*>(.+)</a>', webpage, 'title', fatal=False)
  51         uploader = self._html_search_regex(r'class="title-chanel"[^>]*>[^<]*<a[^>]*>([^<]+)<', webpage, 'uploader', fatal=False)
  52         upload_date = self._search_regex(r'"uploadDate":\s+"([^"]+)",', webpage, 'upload_date', fatal=False)
  53         likes = self._html_search_regex(
  54             r'class="btn btn-up-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'like_count', fatal=False)
  55         dislikes = self._html_search_regex(
  56             r'class="btn btn-down-rating[^>]*>[^<]*<i[^>]*>[^<]*</i>[^>]*<span[^>]*>[^0-9]*([0-9]+)[^<0-9]*<', webpage, 'dislike_count', fatal=False)
  57         mpd_url = self._search_regex(r'"([^"]+userscontent.net/dash/[0-9]+/manifest.mpd[^"]*)"', webpage, 'mpd_url').replace('&amp;', '&')
  58         formats = self._extract_mpd_formats(mpd_url, video_id, mpd_id='dash')
  59
  60         return {
  61             'age_limit': 18,
  62             'description': description,
  63             'dislike_count': int_or_none(dislikes),
  64             'duration': parse_duration(duration),
  65             'formats': formats,
  66             'id': video_id,
  67             'like_count': int_or_none(likes),
  68             'timestamp': parse_iso8601(upload_date),
  69             'thumbnail': self._og_search_thumbnail(webpage),
  70             'title': title,
  71             'uploader': uploader,
  72             'view_count': int_or_none(view_count),
  73         }