yt_dlp/extractor/xanimu.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import int_or_none
   5
   6
   7 class XanimuIE(InfoExtractor):
   8     _VALID_URL = r'https?://(?:www\.)?xanimu\.com/(?P<id>[^/]+)/?'
   9     _TESTS = [{
  10         'url': 'https://xanimu.com/51944-the-princess-the-frog-hentai/',
  11         'md5': '899b88091d753d92dad4cb63bbf357a7',
  12         'info_dict': {
  13             'id': '51944-the-princess-the-frog-hentai',
  14             'ext': 'mp4',
  15             'title': 'The Princess + The Frog Hentai',
  16             'thumbnail': 'https://xanimu.com/storage/2020/09/the-princess-and-the-frog-hentai.jpg',
  17             'description': r're:^Enjoy The Princess \+ The Frog Hentai',
  18             'duration': 207.0,
  19             'age_limit': 18,
  20         },
  21     }, {
  22         'url': 'https://xanimu.com/huge-expansion/',
  23         'only_matching': True,
  24     }]
  25
  26     def _real_extract(self, url):
  27         video_id = self._match_id(url)
  28         webpage = self._download_webpage(url, video_id)
  29
  30         formats = []
  31         for format_id in ['videoHigh', 'videoLow']:
  32             format_url = self._search_json(
  33                 rf'var\s+{re.escape(format_id)}\s*=', webpage, format_id,
  34                 video_id, default=None, contains_pattern=r'[\'"]([^\'"]+)[\'"]')
  35             if format_url:
  36                 formats.append({
  37                     'url': format_url,
  38                     'format_id': format_id,
  39                     'quality': -2 if format_id.endswith('Low') else None,
  40                 })
  41
  42         return {
  43             'id': video_id,
  44             'formats': formats,
  45             'title': self._search_regex(r'[\'"]headline[\'"]:\s*[\'"]([^"]+)[\'"]', webpage,
  46                                         'title', default=None) or self._html_extract_title(webpage),
  47             'thumbnail': self._html_search_meta('thumbnailUrl', webpage, default=None),
  48             'description': self._html_search_meta('description', webpage, default=None),
  49             'duration': int_or_none(self._search_regex(r'duration:\s*[\'"]([^\'"]+?)[\'"]',
  50                                     webpage, 'duration', fatal=False)),
  51             'age_limit': 18,
  52         }