yt_dlp/extractor/simplecast.py

   1 from .common import InfoExtractor
   2 from ..utils import (
   3     clean_podcast_url,
   4     int_or_none,
   5     parse_iso8601,
   6     strip_or_none,
   7     try_get,
   8     urlencode_postdata,
   9 )
  10
  11
  12 class SimplecastBaseIE(InfoExtractor):
  13     _UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
  14     _API_BASE = 'https://api.simplecast.com/'
  15
  16     def _call_api(self, path_tmpl, video_id):
  17         return self._download_json(
  18             self._API_BASE + path_tmpl % video_id, video_id)
  19
  20     def _call_search_api(self, resource, resource_id, resource_url):
  21         return self._download_json(
  22             f'https://api.simplecast.com/{resource}s/search', resource_id,
  23             data=urlencode_postdata({'url': resource_url}))
  24
  25     def _parse_episode(self, episode):
  26         episode_id = episode['id']
  27         title = episode['title'].strip()
  28         audio_file = episode.get('audio_file') or {}
  29         audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
  30
  31         season = episode.get('season') or {}
  32         season_href = season.get('href')
  33         season_id = None
  34         if season_href:
  35             season_id = self._search_regex(
  36                 rf'https?://api.simplecast.com/seasons/({self._UUID_REGEX})',
  37                 season_href, 'season id', default=None)
  38
  39         webpage_url = episode.get('episode_url')
  40         channel_url = None
  41         if webpage_url:
  42             channel_url = self._search_regex(
  43                 r'(https?://[^/]+\.simplecast\.com)',
  44                 webpage_url, 'channel url', default=None)
  45
  46         return {
  47             'id': episode_id,
  48             'display_id': episode.get('slug'),
  49             'title': title,
  50             'url': clean_podcast_url(audio_file_url),
  51             'webpage_url': webpage_url,
  52             'channel_url': channel_url,
  53             'series': try_get(episode, lambda x: x['podcast']['title']),
  54             'season_number': int_or_none(season.get('number')),
  55             'season_id': season_id,
  56             'thumbnail': episode.get('image_url'),
  57             'episode_id': episode_id,
  58             'episode_number': int_or_none(episode.get('number')),
  59             'description': strip_or_none(episode.get('description')),
  60             'timestamp': parse_iso8601(episode.get('published_at')),
  61             'duration': int_or_none(episode.get('duration')),
  62             'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
  63         }
  64
  65
  66 class SimplecastIE(SimplecastBaseIE):
  67     IE_NAME = 'simplecast'
  68     _VALID_URL = rf'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>{SimplecastBaseIE._UUID_REGEX})'
  69     _EMBED_REGEX = [rf'''(?x)<iframe[^>]+src=["\']
  70         (?P<url>https?://(?:
  71             embed\.simplecast\.com/[0-9a-f]{8}|
  72             player\.simplecast\.com/{SimplecastBaseIE._UUID_REGEX}
  73         ))''']
  74     _COMMON_TEST_INFO = {
  75         'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
  76         'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
  77         'ext': 'mp3',
  78         'title': 'Errant Signal - Chris Franklin & New Wave Video Essays',
  79         'episode_number': 1,
  80         'episode_id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
  81         'description': 'md5:34752789d3d2702e2d2c975fbd14f357',
  82         'season_number': 1,
  83         'season_id': 'e23df0da-bae4-4531-8bbf-71364a88dc13',
  84         'series': 'The RE:BIND.io Podcast',
  85         'duration': 5343,
  86         'timestamp': 1580979475,
  87         'upload_date': '20200206',
  88         'webpage_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
  89         'channel_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com$',
  90     }
  91     _TESTS = [{
  92         'url': 'https://api.simplecast.com/episodes/b6dc49a2-9404-4853-9aa9-9cfc097be876',
  93         'md5': '8c93be7be54251bf29ee97464eabe61c',
  94         'info_dict': _COMMON_TEST_INFO,
  95     }, {
  96         'url': 'https://player.simplecast.com/b6dc49a2-9404-4853-9aa9-9cfc097be876',
  97         'only_matching': True,
  98     }]
  99
 100     def _real_extract(self, url):
 101         episode_id = self._match_id(url)
 102         episode = self._call_api('episodes/%s', episode_id)
 103         return self._parse_episode(episode)
 104
 105
 106 class SimplecastEpisodeIE(SimplecastBaseIE):
 107     IE_NAME = 'simplecast:episode'
 108     _VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
 109     _TEST = {
 110         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
 111         'md5': '8c93be7be54251bf29ee97464eabe61c',
 112         'info_dict': SimplecastIE._COMMON_TEST_INFO,
 113     }
 114
 115     def _real_extract(self, url):
 116         mobj = self._match_valid_url(url)
 117         episode = self._call_search_api(
 118             'episode', mobj.group(1), mobj.group(0))
 119         return self._parse_episode(episode)
 120
 121
 122 class SimplecastPodcastIE(SimplecastBaseIE):
 123     IE_NAME = 'simplecast:podcast'
 124     _VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
 125     _TESTS = [{
 126         'url': 'https://the-re-bind-io-podcast.simplecast.com',
 127         'playlist_mincount': 33,
 128         'info_dict': {
 129             'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
 130             'title': 'The RE:BIND.io Podcast',
 131         },
 132     }, {
 133         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
 134         'only_matching': True,
 135     }]
 136
 137     def _real_extract(self, url):
 138         subdomain = self._match_id(url)
 139         site = self._call_search_api('site', subdomain, url)
 140         podcast = site['podcast']
 141         podcast_id = podcast['id']
 142         podcast_title = podcast.get('title')
 143
 144         def entries():
 145             episodes = self._call_api('podcasts/%s/episodes', podcast_id)
 146             for episode in (episodes.get('collection') or []):
 147                 info = self._parse_episode(episode)
 148                 info['series'] = podcast_title
 149                 yield info
 150
 151         return self.playlist_result(entries(), podcast_id, podcast_title)