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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..compat import compat_str
   5 from ..utils import (
   6     parse_duration,
   7     urljoin,
   8 )
   9
  10
  11 class YourPornIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
  13     _TESTS = [{
  14         'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
  15         'md5': '6f8682b6464033d87acaa7a8ff0c092e',
  16         'info_dict': {
  17             'id': '57ffcb2e1179b',
  18             'ext': 'mp4',
  19             'title': 'md5:c9f43630bd968267672651ba905a7d35',
  20             'thumbnail': r're:^https?://.*\.jpg$',
  21             'duration': 165,
  22             'age_limit': 18,
  23         },
  24         'params': {
  25             'skip_download': True,
  26         },
  27     }, {
  28         'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
  29         'only_matching': True,
  30     }]
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34
  35         webpage = self._download_webpage(url, video_id)
  36
  37         parts = self._parse_json(
  38             self._search_regex(
  39                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
  40                 group='data'),
  41             video_id)[video_id].split('/')
  42
  43         num = 0
  44         for c in parts[6] + parts[7]:
  45             if c.isnumeric():
  46                 num += int(c)
  47         parts[5] = compat_str(int(parts[5]) - num)
  48         parts[1] += '8'
  49         video_url = urljoin(url, '/'.join(parts))
  50
  51         title = (self._search_regex(
  52             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
  53             default=None) or self._og_search_description(webpage)).strip()
  54         thumbnail = self._og_search_thumbnail(webpage)
  55         duration = parse_duration(self._search_regex(
  56             r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
  57             default=None))
  58
  59         return {
  60             'id': video_id,
  61             'url': video_url,
  62             'title': title,
  63             'thumbnail': thumbnail,
  64             'duration': duration,
  65             'age_limit': 18,
  66             'ext': 'mp4',
  67         }