_ Git - youtube-dl/blob - youtube_dl/extractor/yourporn.py

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_duration,
   6     urljoin,
   7 )
   8
   9
  10 class YourPornIE(InfoExtractor):
  11     _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)'
  12     _TEST = {
  13         'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
  14         'md5': '6f8682b6464033d87acaa7a8ff0c092e',
  15         'info_dict': {
  16             'id': '57ffcb2e1179b',
  17             'ext': 'mp4',
  18             'title': 'md5:c9f43630bd968267672651ba905a7d35',
  19             'thumbnail': r're:^https?://.*\.jpg$',
  20             'duration': 165,
  21             'age_limit': 18,
  22         },
  23         'params': {
  24             'skip_download': True,
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(url, video_id)
  32
  33         video_url = urljoin(url, self._parse_json(
  34             self._search_regex(
  35                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
  36                 group='data'),
  37             video_id)[video_id]).replace('/cdn/', '/cdn4/')
  38
  39         title = (self._search_regex(
  40             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
  41             default=None) or self._og_search_description(webpage)).strip()
  42         thumbnail = self._og_search_thumbnail(webpage)
  43         duration = parse_duration(self._search_regex(
  44             r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
  45             default=None))
  46
  47         return {
  48             'id': video_id,
  49             'url': video_url,
  50             'title': title,
  51             'thumbnail': thumbnail,
  52             'duration': duration,
  53             'age_limit': 18,
  54         }