yt_dlp/extractor/rbmaradio.py

   1 from __future__ import unicode_literals
   2
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     clean_html,
   8     int_or_none,
   9     unified_timestamp,
  10     update_url_query,
  11 )
  12
  13
  14 class RBMARadioIE(InfoExtractor):
  15     _VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
  16     _TEST = {
  17         'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
  18         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
  19         'info_dict': {
  20             'id': 'ford-lopatin-live-at-primavera-sound-2011',
  21             'ext': 'mp3',
  22             'title': 'Main Stage - Ford & Lopatin at Primavera Sound',
  23             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  24             'thumbnail': r're:^https?://.*\.jpg',
  25             'duration': 2452,
  26             'timestamp': 1307103164,
  27             'upload_date': '20110603',
  28         },
  29     }
  30
  31     def _real_extract(self, url):
  32         mobj = self._match_valid_url(url)
  33         show_id = mobj.group('show_id')
  34         episode_id = mobj.group('id')
  35
  36         webpage = self._download_webpage(url, episode_id)
  37
  38         episode = self._parse_json(
  39             self._search_regex(
  40                 r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
  41                 webpage, 'json data'),
  42             episode_id)['episodes'][show_id][episode_id]
  43
  44         title = episode['title']
  45
  46         show_title = episode.get('showTitle')
  47         if show_title:
  48             title = '%s - %s' % (show_title, title)
  49
  50         formats = [{
  51             'url': update_url_query(episode['audioURL'], query={'cbr': abr}),
  52             'format_id': compat_str(abr),
  53             'abr': abr,
  54             'vcodec': 'none',
  55         } for abr in (96, 128, 192, 256)]
  56         self._check_formats(formats, episode_id)
  57
  58         description = clean_html(episode.get('longTeaser'))
  59         thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
  60         duration = int_or_none(episode.get('duration'))
  61         timestamp = unified_timestamp(episode.get('publishedAt'))
  62
  63         return {
  64             'id': episode_id,
  65             'title': title,
  66             'description': description,
  67             'thumbnail': thumbnail,
  68             'duration': duration,
  69             'timestamp': timestamp,
  70             'formats': formats,
  71         }