yt_dlp/extractor/acast.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_html,
   9     clean_podcast_url,
  10     int_or_none,
  11     parse_iso8601,
  12 )
  13
  14
  15 class ACastBaseIE(InfoExtractor):
  16     def _extract_episode(self, episode, show_info):
  17         title = episode['title']
  18         info = {
  19             'id': episode['id'],
  20             'display_id': episode.get('episodeUrl'),
  21             'url': clean_podcast_url(episode['url']),
  22             'title': title,
  23             'description': clean_html(episode.get('description') or episode.get('summary')),
  24             'thumbnail': episode.get('image'),
  25             'timestamp': parse_iso8601(episode.get('publishDate')),
  26             'duration': int_or_none(episode.get('duration')),
  27             'filesize': int_or_none(episode.get('contentLength')),
  28             'season_number': int_or_none(episode.get('season')),
  29             'episode': title,
  30             'episode_number': int_or_none(episode.get('episode')),
  31         }
  32         info.update(show_info)
  33         return info
  34
  35     def _extract_show_info(self, show):
  36         return {
  37             'creator': show.get('author'),
  38             'series': show.get('title'),
  39         }
  40
  41     def _call_api(self, path, video_id, query=None):
  42         return self._download_json(
  43             'https://feeder.acast.com/api/v1/shows/' + path, video_id, query=query)
  44
  45
  46 class ACastIE(ACastBaseIE):
  47     IE_NAME = 'acast'
  48     _VALID_URL = r'''(?x)
  49                     https?://
  50                         (?:
  51                             (?:(?:embed|www)\.)?acast\.com/|
  52                             play\.acast\.com/s/
  53                         )
  54                         (?P<channel>[^/]+)/(?P<id>[^/#?]+)
  55                     '''
  56     _TESTS = [{
  57         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  58         'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
  59         'info_dict': {
  60             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  61             'ext': 'mp3',
  62             'title': '2. Raggarmordet - Röster ur det förflutna',
  63             'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
  64             'timestamp': 1477346700,
  65             'upload_date': '20161024',
  66             'duration': 2766,
  67             'creator': 'Anton Berg & Martin Johnson',
  68             'series': 'Spår',
  69             'episode': '2. Raggarmordet - Röster ur det förflutna',
  70         }
  71     }, {
  72         'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
  73         'only_matching': True,
  74     }, {
  75         'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
  76         'only_matching': True,
  77     }, {
  78         'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
  79         'only_matching': True,
  80     }]
  81
  82     def _real_extract(self, url):
  83         channel, display_id = re.match(self._VALID_URL, url).groups()
  84         episode = self._call_api(
  85             '%s/episodes/%s' % (channel, display_id),
  86             display_id, {'showInfo': 'true'})
  87         return self._extract_episode(
  88             episode, self._extract_show_info(episode.get('show') or {}))
  89
  90
  91 class ACastChannelIE(ACastBaseIE):
  92     IE_NAME = 'acast:channel'
  93     _VALID_URL = r'''(?x)
  94                     https?://
  95                         (?:
  96                             (?:www\.)?acast\.com/|
  97                             play\.acast\.com/s/
  98                         )
  99                         (?P<id>[^/#?]+)
 100                     '''
 101     _TESTS = [{
 102         'url': 'https://www.acast.com/todayinfocus',
 103         'info_dict': {
 104             'id': '4efc5294-5385-4847-98bd-519799ce5786',
 105             'title': 'Today in Focus',
 106             'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
 107         },
 108         'playlist_mincount': 200,
 109     }, {
 110         'url': 'http://play.acast.com/s/ft-banking-weekly',
 111         'only_matching': True,
 112     }]
 113
 114     @classmethod
 115     def suitable(cls, url):
 116         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 117
 118     def _real_extract(self, url):
 119         show_slug = self._match_id(url)
 120         show = self._call_api(show_slug, show_slug)
 121         show_info = self._extract_show_info(show)
 122         entries = []
 123         for episode in (show.get('episodes') or []):
 124             entries.append(self._extract_episode(episode, show_info))
 125         return self.playlist_result(
 126             entries, show.get('id'), show.get('title'), show.get('description'))