yt_dlp/extractor/megaphone.py

   1 from .common import InfoExtractor
   2 from ..utils import js_to_json
   3
   4
   5 class MegaphoneIE(InfoExtractor):
   6     IE_NAME = 'megaphone.fm'
   7     IE_DESC = 'megaphone.fm embedded players'
   8     _VALID_URL = r'https?://player\.megaphone\.fm/(?P<id>[A-Z0-9]+)'
   9     _EMBED_REGEX = [rf'<iframe[^>]*?\ssrc=["\'](?P<url>{_VALID_URL})']
  10     _TEST = {
  11         'url': 'https://player.megaphone.fm/GLT9749789991',
  12         'md5': '4816a0de523eb3e972dc0dda2c191f96',
  13         'info_dict': {
  14             'id': 'GLT9749789991',
  15             'ext': 'mp3',
  16             'title': '#97 What Kind Of Idiot Gets Phished?',
  17             'thumbnail': r're:^https://.*\.png.*$',
  18             'duration': 1998.36,
  19             'creators': ['Reply All'],
  20         },
  21     }
  22
  23     def _real_extract(self, url):
  24         video_id = self._match_id(url)
  25         webpage = self._download_webpage(url, video_id)
  26
  27         title = self._og_search_property('audio:title', webpage)
  28         author = self._og_search_property('audio:artist', webpage)
  29         thumbnail = self._og_search_thumbnail(webpage)
  30
  31         episode_json = self._search_regex(r'(?s)var\s+episode\s*=\s*(\{.+?\});', webpage, 'episode JSON')
  32         episode_data = self._parse_json(episode_json, video_id, js_to_json)
  33         video_url = self._proto_relative_url(episode_data['mediaUrl'], 'https:')
  34
  35         formats = [{
  36             'url': video_url,
  37         }]
  38
  39         return {
  40             'id': video_id,
  41             'thumbnail': thumbnail,
  42             'title': title,
  43             'creators': [author] if author else None,
  44             'duration': episode_data['duration'],
  45             'formats': formats,
  46         }