yt_dlp/extractor/rbmaradio.py

   1 from .common import InfoExtractor
   2 from ..compat import compat_str
   3 from ..utils import (
   4     clean_html,
   5     int_or_none,
   6     unified_timestamp,
   7     update_url_query,
   8 )
   9
  10
  11 class RBMARadioIE(InfoExtractor):
  12     _VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
  13     _TEST = {
  14         'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
  15         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
  16         'info_dict': {
  17             'id': 'ford-lopatin-live-at-primavera-sound-2011',
  18             'ext': 'mp3',
  19             'title': 'Main Stage - Ford & Lopatin at Primavera Sound',
  20             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  21             'thumbnail': r're:^https?://.*\.jpg',
  22             'duration': 2452,
  23             'timestamp': 1307103164,
  24             'upload_date': '20110603',
  25         },
  26     }
  27
  28     def _real_extract(self, url):
  29         mobj = self._match_valid_url(url)
  30         show_id = mobj.group('show_id')
  31         episode_id = mobj.group('id')
  32
  33         webpage = self._download_webpage(url, episode_id)
  34
  35         episode = self._parse_json(
  36             self._search_regex(
  37                 r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
  38                 webpage, 'json data'),
  39             episode_id)['episodes'][show_id][episode_id]
  40
  41         title = episode['title']
  42
  43         show_title = episode.get('showTitle')
  44         if show_title:
  45             title = '%s - %s' % (show_title, title)
  46
  47         formats = [{
  48             'url': update_url_query(episode['audioURL'], query={'cbr': abr}),
  49             'format_id': compat_str(abr),
  50             'abr': abr,
  51             'vcodec': 'none',
  52         } for abr in (96, 128, 192, 256)]
  53         self._check_formats(formats, episode_id)
  54
  55         description = clean_html(episode.get('longTeaser'))
  56         thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
  57         duration = int_or_none(episode.get('duration'))
  58         timestamp = unified_timestamp(episode.get('publishedAt'))
  59
  60         return {
  61             'id': episode_id,
  62             'title': title,
  63             'description': description,
  64             'thumbnail': thumbnail,
  65             'duration': duration,
  66             'timestamp': timestamp,
  67             'formats': formats,
  68         }