yt_dlp/extractor/megaphone.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import js_to_json
   5
   6
   7 class MegaphoneIE(InfoExtractor):
   8     IE_NAME = 'megaphone.fm'
   9     IE_DESC = 'megaphone.fm embedded players'
  10     _VALID_URL = r'https://player\.megaphone\.fm/(?P<id>[A-Z0-9]+)'
  11     _TEST = {
  12         'url': 'https://player.megaphone.fm/GLT9749789991?"',
  13         'md5': '4816a0de523eb3e972dc0dda2c191f96',
  14         'info_dict': {
  15             'id': 'GLT9749789991',
  16             'ext': 'mp3',
  17             'title': '#97 What Kind Of Idiot Gets Phished?',
  18             'thumbnail': r're:^https://.*\.png.*$',
  19             'duration': 1776.26375,
  20             'author': 'Reply All',
  21         },
  22     }
  23
  24     def _real_extract(self, url):
  25         video_id = self._match_id(url)
  26         webpage = self._download_webpage(url, video_id)
  27
  28         title = self._og_search_property('audio:title', webpage)
  29         author = self._og_search_property('audio:artist', webpage)
  30         thumbnail = self._og_search_thumbnail(webpage)
  31
  32         episode_json = self._search_regex(r'(?s)var\s+episode\s*=\s*(\{.+?\});', webpage, 'episode JSON')
  33         episode_data = self._parse_json(episode_json, video_id, js_to_json)
  34         video_url = self._proto_relative_url(episode_data['mediaUrl'], 'https:')
  35
  36         formats = [{
  37             'url': video_url,
  38         }]
  39
  40         return {
  41             'id': video_id,
  42             'thumbnail': thumbnail,
  43             'title': title,
  44             'author': author,
  45             'duration': episode_data['duration'],
  46             'formats': formats,
  47         }
  48
  49     @classmethod
  50     def _extract_urls(cls, webpage):
  51         return [m[0] for m in re.findall(
  52             r'<iframe[^>]*?\ssrc=["\'](%s)' % cls._VALID_URL, webpage)]