yt_dlp/extractor/noodlemagazine.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     parse_duration,
   4     parse_count,
   5     unified_strdate
   6 )
   7
   8
   9 class NoodleMagazineIE(InfoExtractor):
  10     _VALID_URL = r'https?://(?:www|adult\.)?noodlemagazine\.com/watch/(?P<id>[0-9-_]+)'
  11     _TEST = {
  12         'url': 'https://adult.noodlemagazine.com/watch/-67421364_456239604',
  13         'md5': '9e02aa763612929d0b4b850591a9248b',
  14         'info_dict': {
  15             'id': '-67421364_456239604',
  16             'title': 'Aria alexander manojob',
  17             'thumbnail': r're:^https://.*\.jpg',
  18             'ext': 'mp4',
  19             'duration': 903,
  20             'view_count': int,
  21             'like_count': int,
  22             'description': 'Aria alexander manojob',
  23             'tags': ['aria', 'alexander', 'manojob'],
  24             'upload_date': '20190218',
  25             'age_limit': 18
  26         }
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32         title = self._og_search_title(webpage)
  33         duration = parse_duration(self._html_search_meta('video:duration', webpage, 'duration', default=None))
  34         description = self._og_search_property('description', webpage, default='').replace(' watch online hight quality video', '')
  35         tags = self._html_search_meta('video:tag', webpage, default='').split(', ')
  36         view_count = parse_count(self._html_search_meta('ya:ovs:views_total', webpage, default=None))
  37         like_count = parse_count(self._html_search_meta('ya:ovs:likes', webpage, default=None))
  38         upload_date = unified_strdate(self._html_search_meta('ya:ovs:upload_date', webpage, default=''))
  39
  40         key = self._html_search_regex(rf'/{video_id}\?(?:.*&)?m=([^&"\'\s,]+)', webpage, 'key')
  41         playlist_info = self._download_json(f'https://adult.noodlemagazine.com/playlist/{video_id}?m={key}', video_id)
  42         thumbnail = self._og_search_property('image', webpage, default=None) or playlist_info.get('image')
  43
  44         formats = [{
  45             'url': source.get('file'),
  46             'quality': source.get('label'),
  47             'ext': source.get('type'),
  48         } for source in playlist_info.get('sources')]
  49
  50         return {
  51             'id': video_id,
  52             'formats': formats,
  53             'title': title,
  54             'thumbnail': thumbnail,
  55             'duration': duration,
  56             'description': description,
  57             'tags': tags,
  58             'view_count': view_count,
  59             'like_count': like_count,
  60             'upload_date': upload_date,
  61             'age_limit': 18
  62         }