yt_dlp/extractor/rinsefm.py

   1 from .common import InfoExtractor
   2 from ..utils import format_field, parse_iso8601
   3
   4
   5 class RinseFMIE(InfoExtractor):
   6     _VALID_URL = r'https?://(?:www\.)?rinse\.fm/episodes/(?P<id>[^/?#]+)'
   7     _TESTS = [{
   8         'url': 'https://rinse.fm/episodes/club-glow-15-12-2023-2000/',
   9         'md5': '76ee0b719315617df42e15e710f46c7b',
  10         'info_dict': {
  11             'id': '1536535',
  12             'ext': 'mp3',
  13             'title': 'Club Glow - 15/12/2023 - 20:00',
  14             'thumbnail': r're:^https://.+\.(?:jpg|JPG)$',
  15             'release_timestamp': 1702598400,
  16             'release_date': '20231215'
  17         }
  18     }]
  19
  20     def _real_extract(self, url):
  21         display_id = self._match_id(url)
  22         webpage = self._download_webpage(url, display_id)
  23         entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
  24
  25         return {
  26             'id': entry['id'],
  27             'title': entry.get('title'),
  28             'url': entry['fileUrl'],
  29             'vcodec': 'none',
  30             'release_timestamp': parse_iso8601(entry.get('episodeDate')),
  31             'thumbnail': format_field(
  32                 entry, [('featuredImage', 0, 'filename')], 'https://rinse.imgix.net/media/%s', default=None),
  33         }