yt_dlp/extractor/simplecast.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     clean_podcast_url,
   6     int_or_none,
   7     parse_iso8601,
   8     strip_or_none,
   9     try_get,
  10     urlencode_postdata,
  11 )
  12
  13
  14 class SimplecastBaseIE(InfoExtractor):
  15     _UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
  16     _API_BASE = 'https://api.simplecast.com/'
  17
  18     def _call_api(self, path_tmpl, video_id):
  19         return self._download_json(
  20             self._API_BASE + path_tmpl % video_id, video_id)
  21
  22     def _call_search_api(self, resource, resource_id, resource_url):
  23         return self._download_json(
  24             'https://api.simplecast.com/%ss/search' % resource, resource_id,
  25             data=urlencode_postdata({'url': resource_url}))
  26
  27     def _parse_episode(self, episode):
  28         episode_id = episode['id']
  29         title = episode['title'].strip()
  30         audio_file = episode.get('audio_file') or {}
  31         audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
  32
  33         season = episode.get('season') or {}
  34         season_href = season.get('href')
  35         season_id = None
  36         if season_href:
  37             season_id = self._search_regex(
  38                 r'https?://api.simplecast.com/seasons/(%s)' % self._UUID_REGEX,
  39                 season_href, 'season id', default=None)
  40
  41         webpage_url = episode.get('episode_url')
  42         channel_url = None
  43         if webpage_url:
  44             channel_url = self._search_regex(
  45                 r'(https?://[^/]+\.simplecast\.com)',
  46                 webpage_url, 'channel url', default=None)
  47
  48         return {
  49             'id': episode_id,
  50             'display_id': episode.get('slug'),
  51             'title': title,
  52             'url': clean_podcast_url(audio_file_url),
  53             'webpage_url': webpage_url,
  54             'channel_url': channel_url,
  55             'series': try_get(episode, lambda x: x['podcast']['title']),
  56             'season_number': int_or_none(season.get('number')),
  57             'season_id': season_id,
  58             'thumbnail': episode.get('image_url'),
  59             'episode_id': episode_id,
  60             'episode_number': int_or_none(episode.get('number')),
  61             'description': strip_or_none(episode.get('description')),
  62             'timestamp': parse_iso8601(episode.get('published_at')),
  63             'duration': int_or_none(episode.get('duration')),
  64             'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
  65         }
  66
  67
  68 class SimplecastIE(SimplecastBaseIE):
  69     IE_NAME = 'simplecast'
  70     _VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
  71     _COMMON_TEST_INFO = {
  72         'display_id': 'errant-signal-chris-franklin-new-wave-video-essays',
  73         'id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
  74         'ext': 'mp3',
  75         'title': 'Errant Signal - Chris Franklin & New Wave Video Essays',
  76         'episode_number': 1,
  77         'episode_id': 'b6dc49a2-9404-4853-9aa9-9cfc097be876',
  78         'description': 'md5:34752789d3d2702e2d2c975fbd14f357',
  79         'season_number': 1,
  80         'season_id': 'e23df0da-bae4-4531-8bbf-71364a88dc13',
  81         'series': 'The RE:BIND.io Podcast',
  82         'duration': 5343,
  83         'timestamp': 1580979475,
  84         'upload_date': '20200206',
  85         'webpage_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
  86         'channel_url': r're:^https?://the-re-bind-io-podcast\.simplecast\.com$',
  87     }
  88     _TESTS = [{
  89         'url': 'https://api.simplecast.com/episodes/b6dc49a2-9404-4853-9aa9-9cfc097be876',
  90         'md5': '8c93be7be54251bf29ee97464eabe61c',
  91         'info_dict': _COMMON_TEST_INFO,
  92     }, {
  93         'url': 'https://player.simplecast.com/b6dc49a2-9404-4853-9aa9-9cfc097be876',
  94         'only_matching': True,
  95     }]
  96
  97     @staticmethod
  98     def _extract_urls(webpage):
  99         return re.findall(
 100             r'''(?x)<iframe[^>]+src=["\']
 101                 (
 102                     https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
 103                     player\.simplecast\.com/%s
 104                 ))''' % SimplecastBaseIE._UUID_REGEX, webpage)
 105
 106     def _real_extract(self, url):
 107         episode_id = self._match_id(url)
 108         episode = self._call_api('episodes/%s', episode_id)
 109         return self._parse_episode(episode)
 110
 111
 112 class SimplecastEpisodeIE(SimplecastBaseIE):
 113     IE_NAME = 'simplecast:episode'
 114     _VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
 115     _TEST = {
 116         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
 117         'md5': '8c93be7be54251bf29ee97464eabe61c',
 118         'info_dict': SimplecastIE._COMMON_TEST_INFO,
 119     }
 120
 121     def _real_extract(self, url):
 122         mobj = self._match_valid_url(url)
 123         episode = self._call_search_api(
 124             'episode', mobj.group(1), mobj.group(0))
 125         return self._parse_episode(episode)
 126
 127
 128 class SimplecastPodcastIE(SimplecastBaseIE):
 129     IE_NAME = 'simplecast:podcast'
 130     _VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
 131     _TESTS = [{
 132         'url': 'https://the-re-bind-io-podcast.simplecast.com',
 133         'playlist_mincount': 33,
 134         'info_dict': {
 135             'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
 136             'title': 'The RE:BIND.io Podcast',
 137         },
 138     }, {
 139         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
 140         'only_matching': True,
 141     }]
 142
 143     def _real_extract(self, url):
 144         subdomain = self._match_id(url)
 145         site = self._call_search_api('site', subdomain, url)
 146         podcast = site['podcast']
 147         podcast_id = podcast['id']
 148         podcast_title = podcast.get('title')
 149
 150         def entries():
 151             episodes = self._call_api('podcasts/%s/episodes', podcast_id)
 152             for episode in (episodes.get('collection') or []):
 153                 info = self._parse_episode(episode)
 154                 info['series'] = podcast_title
 155                 yield info
 156
 157         return self.playlist_result(entries(), podcast_id, podcast_title)