yt_dlp/extractor/syvdk.py

   1 from .common import InfoExtractor
   2 from ..utils import traverse_obj
   3
   4
   5 class SYVDKIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?24syv\.dk/episode/(?P<id>[\w-]+)'
   7
   8     _TESTS = [{
   9         'url': 'https://24syv.dk/episode/isabella-arendt-stiller-op-for-de-konservative-2',
  10         'md5': '429ce5a423dd4b1e1d0bf3a569558089',
  11         'info_dict': {
  12             'id': '12215',
  13             'display_id': 'isabella-arendt-stiller-op-for-de-konservative-2',
  14             'ext': 'mp3',
  15             'title': 'Isabella Arendt stiller op for De Konservative',
  16             'description': 'md5:f5fa6a431813bf37284f3412ad7c6c06',
  17         },
  18     }]
  19
  20     def _real_extract(self, url):
  21         video_id = self._match_id(url)
  22         webpage = self._download_webpage(url, video_id)
  23         info_data = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['episodeDetails'][0]
  24
  25         return {
  26             'id': str(info_data['id']),
  27             'vcodec': 'none',
  28             'ext': 'mp3',
  29             'url': info_data['details']['enclosure'],
  30             'display_id': video_id,
  31             'title': traverse_obj(info_data, ('title', 'rendered')),
  32             'description': traverse_obj(info_data, ('details', 'post_title')),
  33         }