youtube_dl/extractor/acast.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5 import functools
   6
   7 from .common import InfoExtractor
   8 from ..compat import compat_str
   9 from ..utils import (
  10     float_or_none,
  11     int_or_none,
  12     try_get,
  13     unified_timestamp,
  14     OnDemandPagedList,
  15 )
  16
  17
  18 class ACastIE(InfoExtractor):
  19     IE_NAME = 'acast'
  20     _VALID_URL = r'https?://(?:(?:embed|www)\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
  21     _TESTS = [{
  22         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  23         'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
  24         'info_dict': {
  25             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  26             'ext': 'mp3',
  27             'title': '2. Raggarmordet - Röster ur det förflutna',
  28             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  29             'timestamp': 1477346700,
  30             'upload_date': '20161024',
  31             'duration': 2766.602563,
  32             'creator': 'Anton Berg & Martin Johnson',
  33             'series': 'Spår',
  34             'episode': '2. Raggarmordet - Röster ur det förflutna',
  35         }
  36     }, {
  37         'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
  38         'only_matching': True,
  39     }]
  40
  41     def _real_extract(self, url):
  42         channel, display_id = re.match(self._VALID_URL, url).groups()
  43         s = self._download_json(
  44             'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
  45             display_id)['result']
  46         media_url = s['url']
  47         cast_data = self._download_json(
  48             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
  49             display_id)['result']
  50         e = cast_data['episode']
  51         title = e['name']
  52         return {
  53             'id': compat_str(e['id']),
  54             'display_id': display_id,
  55             'url': media_url,
  56             'title': title,
  57             'description': e.get('description') or e.get('summary'),
  58             'thumbnail': e.get('image'),
  59             'timestamp': unified_timestamp(e.get('publishingDate')),
  60             'duration': float_or_none(s.get('duration') or e.get('duration')),
  61             'filesize': int_or_none(e.get('contentLength')),
  62             'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
  63             'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
  64             'season_number': int_or_none(e.get('seasonNumber')),
  65             'episode': title,
  66             'episode_number': int_or_none(e.get('episodeNumber')),
  67         }
  68
  69
  70 class ACastChannelIE(InfoExtractor):
  71     IE_NAME = 'acast:channel'
  72     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  73     _TEST = {
  74         'url': 'https://www.acast.com/condenasttraveler',
  75         'info_dict': {
  76             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  77             'title': 'Condé Nast Traveler Podcast',
  78             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  79         },
  80         'playlist_mincount': 20,
  81     }
  82     _API_BASE_URL = 'https://www.acast.com/api/'
  83     _PAGE_SIZE = 10
  84
  85     @classmethod
  86     def suitable(cls, url):
  87         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  88
  89     def _fetch_page(self, channel_slug, page):
  90         casts = self._download_json(
  91             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
  92             channel_slug, note='Download page %d of channel data' % page)
  93         for cast in casts:
  94             yield self.url_result(
  95                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
  96                 'ACast', cast['id'])
  97
  98     def _real_extract(self, url):
  99         channel_slug = self._match_id(url)
 100         channel_data = self._download_json(
 101             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
 102         entries = OnDemandPagedList(functools.partial(
 103             self._fetch_page, channel_slug), self._PAGE_SIZE)
 104         return self.playlist_result(entries, compat_str(
 105             channel_data['id']), channel_data['name'], channel_data.get('description'))