yt_dlp/extractor/radiode.py

   1 from .common import InfoExtractor
   2
   3
   4 class RadioDeIE(InfoExtractor):
   5     _WORKING = False
   6     IE_NAME = 'radio.de'
   7     _VALID_URL = r'https?://(?P<id>.+?)\.(?:radio\.(?:de|at|fr|pt|es|pl|it)|rad\.io)'
   8     _TEST = {
   9         'url': 'http://ndr2.radio.de/',
  10         'info_dict': {
  11             'id': 'ndr2',
  12             'ext': 'mp3',
  13             'title': 're:^NDR 2 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
  14             'description': 'md5:591c49c702db1a33751625ebfb67f273',
  15             'thumbnail': r're:^https?://.*\.png',
  16             'is_live': True,
  17         },
  18         'params': {
  19             'skip_download': True,
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         radio_id = self._match_id(url)
  25         webpage = self._download_webpage(url, radio_id)
  26         jscode = self._search_regex(
  27             r"'components/station/stationService':\s*\{\s*'?station'?:\s*(\{.*?\s*\}),\n",
  28             webpage, 'broadcast')
  29
  30         broadcast = self._parse_json(jscode, radio_id)
  31         title = broadcast['name']
  32         description = broadcast.get('description') or broadcast.get('shortDescription')
  33         thumbnail = broadcast.get('picture4Url') or broadcast.get('picture4TransUrl') or broadcast.get('logo100x100')
  34
  35         formats = [{
  36             'url': stream['streamUrl'],
  37             'ext': stream['streamContentFormat'].lower(),
  38             'acodec': stream['streamContentFormat'],
  39             'abr': stream['bitRate'],
  40             'asr': stream['sampleRate'],
  41         } for stream in broadcast['streamUrls']]
  42
  43         return {
  44             'id': radio_id,
  45             'title': title,
  46             'description': description,
  47             'thumbnail': thumbnail,
  48             'is_live': True,
  49             'formats': formats,
  50         }