youtube_dl/extractor/rbmaradio.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..compat import compat_str
   7 from ..utils import (
   8     clean_html,
   9     int_or_none,
  10     unified_timestamp,
  11     update_url_query,
  12 )
  13
  14
  15 class RBMARadioIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?(?:rbmaradio|redbullradio)\.com/shows/(?P<show_id>[^/]+)/episodes/(?P<id>[^/?#&]+)'
  17     _TEST = {
  18         'url': 'https://www.rbmaradio.com/shows/main-stage/episodes/ford-lopatin-live-at-primavera-sound-2011',
  19         'md5': '6bc6f9bcb18994b4c983bc3bf4384d95',
  20         'info_dict': {
  21             'id': 'ford-lopatin-live-at-primavera-sound-2011',
  22             'ext': 'mp3',
  23             'title': 'Main Stage - Ford & Lopatin at Primavera Sound',
  24             'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
  25             'thumbnail': r're:^https?://.*\.jpg',
  26             'duration': 2452,
  27             'timestamp': 1307103164,
  28             'upload_date': '20110603',
  29         },
  30     }
  31
  32     def _real_extract(self, url):
  33         mobj = re.match(self._VALID_URL, url)
  34         show_id = mobj.group('show_id')
  35         episode_id = mobj.group('id')
  36
  37         webpage = self._download_webpage(url, episode_id)
  38
  39         episode = self._parse_json(
  40             self._search_regex(
  41                 r'__INITIAL_STATE__\s*=\s*({.+?})\s*</script>',
  42                 webpage, 'json data'),
  43             episode_id)['episodes'][show_id][episode_id]
  44
  45         title = episode['title']
  46
  47         show_title = episode.get('showTitle')
  48         if show_title:
  49             title = '%s - %s' % (show_title, title)
  50
  51         formats = [{
  52             'url': update_url_query(episode['audioURL'], query={'cbr': abr}),
  53             'format_id': compat_str(abr),
  54             'abr': abr,
  55             'vcodec': 'none',
  56         } for abr in (96, 128, 192, 256)]
  57         self._check_formats(formats, episode_id)
  58
  59         description = clean_html(episode.get('longTeaser'))
  60         thumbnail = self._proto_relative_url(episode.get('imageURL', {}).get('landscape'))
  61         duration = int_or_none(episode.get('duration'))
  62         timestamp = unified_timestamp(episode.get('publishedAt'))
  63
  64         return {
  65             'id': episode_id,
  66             'title': title,
  67             'description': description,
  68             'thumbnail': thumbnail,
  69             'duration': duration,
  70             'timestamp': timestamp,
  71             'formats': formats,
  72         }