yt_dlp/extractor/pornez.py

   1 from .common import InfoExtractor
   2 from ..utils import int_or_none
   3
   4
   5 class PornezIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?pornez\.net/video(?P<id>[0-9]+)/'
   7     _TEST = {
   8         'url': 'https://pornez.net/video344819/mistresst-funny_penis_names-wmv/',
   9         'md5': '2e19a0a1cff3a5dbea0ef1b9e80bcbbc',
  10         'info_dict': {
  11             'id': '344819',
  12             'ext': 'mp4',
  13             'title': r'mistresst funny_penis_names wmv',
  14             'thumbnail': r're:^https?://.*\.jpg$',
  15             'age_limit': 18,
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         video_id = self._match_id(url)
  21         webpage = self._download_webpage(url, video_id)
  22         iframe_src = self._html_search_regex(
  23             r'<iframe[^>]+src="(https?://pornez\.net/player/\?[^"]+)"', webpage, 'iframe', fatal=True)
  24         title = self._html_search_meta(['name', 'twitter:title', 'og:title'], webpage, 'title', default=None)
  25         if title is None:
  26             title = self._search_regex(r'<h1>(.*?)</h1>', webpage, 'title', fatal=True)
  27         thumbnail = self._html_search_meta(['thumbnailUrl'], webpage, 'title', default=None)
  28         webpage = self._download_webpage(iframe_src, video_id)
  29         entries = self._parse_html5_media_entries(iframe_src, webpage, video_id)[0]
  30         for format in entries['formats']:
  31             height = self._search_regex(r'_(\d+)\.m3u8', format['url'], 'height')
  32             format['format_id'] = '%sp' % height
  33             format['height'] = int_or_none(height)
  34
  35         entries.update({
  36             'id': video_id,
  37             'title': title,
  38             'thumbnail': thumbnail,
  39             'age_limit': 18
  40         })
  41         return entries