youtube_dl/extractor/applepodcasts.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     clean_podcast_url,
   7     int_or_none,
   8     parse_iso8601,
   9     try_get,
  10 )
  11
  12
  13 class ApplePodcastsIE(InfoExtractor):
  14     _VALID_URL = r'https?://podcasts\.apple\.com/(?:[^/]+/)?podcast(?:/[^/]+){1,2}.*?\bi=(?P<id>\d+)'
  15     _TESTS = [{
  16         'url': 'https://podcasts.apple.com/us/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
  17         'md5': 'df02e6acb11c10e844946a39e7222b08',
  18         'info_dict': {
  19             'id': '1000482637777',
  20             'ext': 'mp3',
  21             'title': '207 - Whitney Webb Returns',
  22             'description': 'md5:13a73bade02d2e43737751e3987e1399',
  23             'upload_date': '20200705',
  24             'timestamp': 1593921600,
  25             'duration': 6425,
  26             'series': 'The Tim Dillon Show',
  27         }
  28     }, {
  29         'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns/id1135137367?i=1000482637777',
  30         'only_matching': True,
  31     }, {
  32         'url': 'https://podcasts.apple.com/podcast/207-whitney-webb-returns?i=1000482637777',
  33         'only_matching': True,
  34     }, {
  35         'url': 'https://podcasts.apple.com/podcast/id1135137367?i=1000482637777',
  36         'only_matching': True,
  37     }]
  38
  39     def _real_extract(self, url):
  40         episode_id = self._match_id(url)
  41         webpage = self._download_webpage(url, episode_id)
  42         ember_data = self._parse_json(self._search_regex(
  43             r'id="shoebox-ember-data-store"[^>]*>\s*({.+?})\s*<',
  44             webpage, 'ember data'), episode_id)
  45         ember_data = ember_data.get(episode_id) or ember_data
  46         episode = ember_data['data']['attributes']
  47         description = episode.get('description') or {}
  48
  49         series = None
  50         for inc in (ember_data.get('included') or []):
  51             if inc.get('type') == 'media/podcast':
  52                 series = try_get(inc, lambda x: x['attributes']['name'])
  53
  54         return {
  55             'id': episode_id,
  56             'title': episode['name'],
  57             'url': clean_podcast_url(episode['assetUrl']),
  58             'description': description.get('standard') or description.get('short'),
  59             'timestamp': parse_iso8601(episode.get('releaseDateTime')),
  60             'duration': int_or_none(episode.get('durationInMilliseconds'), 1000),
  61             'series': series,
  62         }