youtube_dlc/extractor/simplecast.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     clean_podcast_url,
   9     int_or_none,
  10     parse_iso8601,
  11     strip_or_none,
  12     try_get,
  13     urlencode_postdata,
  14 )
  15
  16
  17 class SimplecastBaseIE(InfoExtractor):
  18     _UUID_REGEX = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
  19     _API_BASE = 'https://api.simplecast.com/'
  20
  21     def _call_api(self, path_tmpl, video_id):
  22         return self._download_json(
  23             self._API_BASE + path_tmpl % video_id, video_id)
  24
  25     def _call_search_api(self, resource, resource_id, resource_url):
  26         return self._download_json(
  27             'https://api.simplecast.com/%ss/search' % resource, resource_id,
  28             data=urlencode_postdata({'url': resource_url}))
  29
  30     def _parse_episode(self, episode):
  31         episode_id = episode['id']
  32         title = episode['title'].strip()
  33         audio_file = episode.get('audio_file') or {}
  34         audio_file_url = audio_file.get('url') or episode.get('audio_file_url') or episode['enclosure_url']
  35
  36         season = episode.get('season') or {}
  37         season_href = season.get('href')
  38         season_id = None
  39         if season_href:
  40             season_id = self._search_regex(
  41                 r'https?://api.simplecast.com/seasons/(%s)' % self._UUID_REGEX,
  42                 season_href, 'season id', default=None)
  43
  44         webpage_url = episode.get('episode_url')
  45         channel_url = None
  46         if webpage_url:
  47             channel_url = self._search_regex(
  48                 r'(https?://[^/]+\.simplecast\.com)',
  49                 webpage_url, 'channel url', default=None)
  50
  51         return {
  52             'id': episode_id,
  53             'display_id': episode.get('slug'),
  54             'title': title,
  55             'url': clean_podcast_url(audio_file_url),
  56             'webpage_url': webpage_url,
  57             'channel_url': channel_url,
  58             'series': try_get(episode, lambda x: x['podcast']['title']),
  59             'season_number': int_or_none(season.get('number')),
  60             'season_id': season_id,
  61             'thumbnail': episode.get('image_url'),
  62             'episode_id': episode_id,
  63             'episode_number': int_or_none(episode.get('number')),
  64             'description': strip_or_none(episode.get('description')),
  65             'timestamp': parse_iso8601(episode.get('published_at')),
  66             'duration': int_or_none(episode.get('duration')),
  67             'filesize': int_or_none(audio_file.get('size') or episode.get('audio_file_size')),
  68         }
  69
  70
  71 class SimplecastIE(SimplecastBaseIE):
  72     IE_NAME = 'simplecast'
  73     _VALID_URL = r'https?://(?:api\.simplecast\.com/episodes|player\.simplecast\.com)/(?P<id>%s)' % SimplecastBaseIE._UUID_REGEX
  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     @staticmethod
 101     def _extract_urls(webpage):
 102         return re.findall(
 103             r'''(?x)<iframe[^>]+src=["\']
 104                 (
 105                     https?://(?:embed\.simplecast\.com/[0-9a-f]{8}|
 106                     player\.simplecast\.com/%s
 107                 ))''' % SimplecastBaseIE._UUID_REGEX, webpage)
 108
 109     def _real_extract(self, url):
 110         episode_id = self._match_id(url)
 111         episode = self._call_api('episodes/%s', episode_id)
 112         return self._parse_episode(episode)
 113
 114
 115 class SimplecastEpisodeIE(SimplecastBaseIE):
 116     IE_NAME = 'simplecast:episode'
 117     _VALID_URL = r'https?://(?!api\.)[^/]+\.simplecast\.com/episodes/(?P<id>[^/?&#]+)'
 118     _TEST = {
 119         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes/errant-signal-chris-franklin-new-wave-video-essays',
 120         'md5': '8c93be7be54251bf29ee97464eabe61c',
 121         'info_dict': SimplecastIE._COMMON_TEST_INFO,
 122     }
 123
 124     def _real_extract(self, url):
 125         mobj = re.match(self._VALID_URL, url)
 126         episode = self._call_search_api(
 127             'episode', mobj.group(1), mobj.group(0))
 128         return self._parse_episode(episode)
 129
 130
 131 class SimplecastPodcastIE(SimplecastBaseIE):
 132     IE_NAME = 'simplecast:podcast'
 133     _VALID_URL = r'https?://(?!(?:api|cdn|embed|feeds|player)\.)(?P<id>[^/]+)\.simplecast\.com(?!/episodes/[^/?&#]+)'
 134     _TESTS = [{
 135         'url': 'https://the-re-bind-io-podcast.simplecast.com',
 136         'playlist_mincount': 33,
 137         'info_dict': {
 138             'id': '07d28d26-7522-42eb-8c53-2bdcfc81c43c',
 139             'title': 'The RE:BIND.io Podcast',
 140         },
 141     }, {
 142         'url': 'https://the-re-bind-io-podcast.simplecast.com/episodes',
 143         'only_matching': True,
 144     }]
 145
 146     def _real_extract(self, url):
 147         subdomain = self._match_id(url)
 148         site = self._call_search_api('site', subdomain, url)
 149         podcast = site['podcast']
 150         podcast_id = podcast['id']
 151         podcast_title = podcast.get('title')
 152
 153         def entries():
 154             episodes = self._call_api('podcasts/%s/episodes', podcast_id)
 155             for episode in (episodes.get('collection') or []):
 156                 info = self._parse_episode(episode)
 157                 info['series'] = podcast_title
 158                 yield info
 159
 160         return self.playlist_result(entries(), podcast_id, podcast_title)