yt_dlp/extractor/cliphunter.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     url_or_none,
   5 )
   6
   7
   8 class CliphunterIE(InfoExtractor):
   9     IE_NAME = 'cliphunter'
  10
  11     _VALID_URL = r'''(?x)https?://(?:www\.)?cliphunter\.com/w/
  12         (?P<id>[0-9]+)/
  13         (?P<seo>.+?)(?:$|[#\?])
  14     '''
  15     _TESTS = [{
  16         'url': 'http://www.cliphunter.com/w/1012420/Fun_Jynx_Maze_solo',
  17         'md5': 'b7c9bbd4eb3a226ab91093714dcaa480',
  18         'info_dict': {
  19             'id': '1012420',
  20             'ext': 'flv',
  21             'title': 'Fun Jynx Maze solo',
  22             'thumbnail': r're:^https?://.*\.jpg$',
  23             'age_limit': 18,
  24         },
  25         'skip': 'Video gone',
  26     }, {
  27         'url': 'http://www.cliphunter.com/w/2019449/ShesNew__My_booty_girlfriend_Victoria_Paradices_pussy_filled_with_jizz',
  28         'md5': '55a723c67bfc6da6b0cfa00d55da8a27',
  29         'info_dict': {
  30             'id': '2019449',
  31             'ext': 'mp4',
  32             'title': 'ShesNew - My booty girlfriend, Victoria Paradice\'s pussy filled with jizz',
  33             'thumbnail': r're:^https?://.*\.jpg$',
  34             'age_limit': 18,
  35         },
  36     }]
  37
  38     def _real_extract(self, url):
  39         video_id = self._match_id(url)
  40         webpage = self._download_webpage(url, video_id)
  41
  42         video_title = self._search_regex(
  43             r'mediaTitle = "([^"]+)"', webpage, 'title')
  44
  45         gexo_files = self._parse_json(
  46             self._search_regex(
  47                 r'var\s+gexoFiles\s*=\s*({.+?});', webpage, 'gexo files'),
  48             video_id)
  49
  50         formats = []
  51         for format_id, f in gexo_files.items():
  52             video_url = url_or_none(f.get('url'))
  53             if not video_url:
  54                 continue
  55             fmt = f.get('fmt')
  56             height = f.get('h')
  57             format_id = '%s_%sp' % (fmt, height) if fmt and height else format_id
  58             formats.append({
  59                 'url': video_url,
  60                 'format_id': format_id,
  61                 'width': int_or_none(f.get('w')),
  62                 'height': int_or_none(height),
  63                 'tbr': int_or_none(f.get('br')),
  64             })
  65
  66         thumbnail = self._search_regex(
  67             r"var\s+mov_thumb\s*=\s*'([^']+)';",
  68             webpage, 'thumbnail', fatal=False)
  69
  70         return {
  71             'id': video_id,
  72             'title': video_title,
  73             'formats': formats,
  74             'age_limit': self._rta_search(webpage),
  75             'thumbnail': thumbnail,
  76         }