yt_dlp/extractor/groupon.py

   1 from .common import InfoExtractor
   2
   3
   4 class GrouponIE(InfoExtractor):
   5     _VALID_URL = r'https?://(?:www\.)?groupon\.com/deals/(?P<id>[^/?#&]+)'
   6
   7     _TEST = {
   8         'url': 'https://www.groupon.com/deals/bikram-yoga-huntington-beach-2#ooid=tubGNycTo_9Uxg82uESj4i61EYX8nyuf',
   9         'info_dict': {
  10             'id': 'bikram-yoga-huntington-beach-2',
  11             'title': '$49 for 10 Yoga Classes or One Month of Unlimited Classes at Bikram Yoga Huntington Beach ($180 Value)',
  12             'description': 'Studio kept at 105 degrees and 40% humidity with anti-microbial and anti-slip Flotex flooring; certified instructors',
  13         },
  14         'playlist': [{
  15             'md5': '42428ce8a00585f9bc36e49226eae7a1',
  16             'info_dict': {
  17                 'id': 'fk6OhWpXgIQ',
  18                 'ext': 'mp4',
  19                 'title': 'Bikram Yoga Huntington Beach | Orange County !tubGNycTo@9Uxg82uESj4i61EYX8nyuf',
  20                 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  21                 'duration': 45,
  22                 'upload_date': '20160405',
  23                 'uploader_id': 'groupon',
  24                 'uploader': 'Groupon',
  25             },
  26             'add_ie': ['Youtube'],
  27         }],
  28         'params': {
  29             'skip_download': True,
  30         },
  31     }
  32
  33     _PROVIDERS = {
  34         'youtube': ('%s', 'Youtube'),
  35     }
  36
  37     def _real_extract(self, url):
  38         playlist_id = self._match_id(url)
  39         webpage = self._download_webpage(url, playlist_id)
  40
  41         payload = self._parse_json(self._search_regex(
  42             r'(?:var\s+|window\.)payload\s*=\s*(.*?);\n', webpage, 'payload'), playlist_id)
  43         videos = payload['carousel'].get('dealVideos', [])
  44         entries = []
  45         for v in videos:
  46             provider = v.get('provider')
  47             video_id = v.get('media') or v.get('id') or v.get('baseURL')
  48             if not provider or not video_id:
  49                 continue
  50             url_pattern, ie_key = self._PROVIDERS.get(provider.lower())
  51             if not url_pattern:
  52                 self.report_warning(
  53                     f'{playlist_id}: Unsupported video provider {provider}, skipping video')
  54                 continue
  55             entries.append(self.url_result(url_pattern % video_id, ie_key))
  56
  57         return {
  58             '_type': 'playlist',
  59             'id': playlist_id,
  60             'entries': entries,
  61             'title': self._og_search_title(webpage),
  62             'description': self._og_search_description(webpage),
  63         }