yt_dlp/extractor/noodlemagazine.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     int_or_none,
   4     parse_count,
   5     parse_duration,
   6     unified_strdate,
   7     urljoin,
   8 )
   9 from ..utils.traversal import traverse_obj
  10
  11
  12 class NoodleMagazineIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www|adult\.)?noodlemagazine\.com/watch/(?P<id>[0-9-_]+)'
  14     _TEST = {
  15         'url': 'https://adult.noodlemagazine.com/watch/-67421364_456239604',
  16         'md5': '9e02aa763612929d0b4b850591a9248b',
  17         'info_dict': {
  18             'id': '-67421364_456239604',
  19             'title': 'Aria alexander manojob',
  20             'thumbnail': r're:^https://.*\.jpg',
  21             'ext': 'mp4',
  22             'duration': 903,
  23             'view_count': int,
  24             'like_count': int,
  25             'description': 'Aria alexander manojob',
  26             'tags': ['aria', 'alexander', 'manojob'],
  27             'upload_date': '20190218',
  28             'age_limit': 18,
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         video_id = self._match_id(url)
  34         webpage = self._download_webpage(url, video_id)
  35         title = self._og_search_title(webpage)
  36         duration = parse_duration(self._html_search_meta('video:duration', webpage, 'duration', default=None))
  37         description = self._og_search_property('description', webpage, default='').replace(' watch online hight quality video', '')
  38         tags = self._html_search_meta('video:tag', webpage, default='').split(', ')
  39         view_count = parse_count(self._html_search_meta('ya:ovs:views_total', webpage, default=None))
  40         like_count = parse_count(self._html_search_meta('ya:ovs:likes', webpage, default=None))
  41         upload_date = unified_strdate(self._html_search_meta('ya:ovs:upload_date', webpage, default=''))
  42
  43         def build_url(url_or_path):
  44             return urljoin('https://adult.noodlemagazine.com', url_or_path)
  45
  46         headers = {'Referer': url}
  47         player_path = self._html_search_regex(
  48             r'<iframe[^>]+\bid="iplayer"[^>]+\bsrc="([^"]+)"', webpage, 'player path')
  49         player_iframe = self._download_webpage(
  50             build_url(player_path), video_id, 'Downloading iframe page', headers=headers)
  51         playlist_url = self._search_regex(
  52             r'window\.playlistUrl\s*=\s*["\']([^"\']+)["\']', player_iframe, 'playlist url')
  53         playlist_info = self._download_json(build_url(playlist_url), video_id, headers=headers)
  54
  55         formats = []
  56         for source in traverse_obj(playlist_info, ('sources', lambda _, v: v['file'])):
  57             if source.get('type') == 'hls':
  58                 formats.extend(self._extract_m3u8_formats(
  59                     build_url(source['file']), video_id, 'mp4', fatal=False, m3u8_id='hls'))
  60             else:
  61                 formats.append(traverse_obj(source, {
  62                     'url': ('file', {build_url}),
  63                     'format_id': 'label',
  64                     'height': ('label', {int_or_none}),
  65                     'ext': 'type',
  66                 }))
  67
  68         return {
  69             'id': video_id,
  70             'formats': formats,
  71             'title': title,
  72             'thumbnail': self._og_search_property('image', webpage, default=None) or playlist_info.get('image'),
  73             'duration': duration,
  74             'description': description,
  75             'tags': tags,
  76             'view_count': view_count,
  77             'like_count': like_count,
  78             'upload_date': upload_date,
  79             'age_limit': 18,
  80         }