_ Git - youtube-dl/blob - 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     unified_timestamp,
  12     OnDemandPagedList,
  13 )
  14
  15
  16 class ACastIE(InfoExtractor):
  17     IE_NAME = 'acast'
  18     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
  19     _TESTS = [{
  20         # test with one bling
  21         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  22         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  23         'info_dict': {
  24             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  25             'ext': 'mp3',
  26             'title': '"Where Are You?": Taipei 101, Taiwan',
  27             'timestamp': 1196172000,
  28             'upload_date': '20071127',
  29             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  30             'duration': 211,
  31         }
  32     }, {
  33         # test with multiple blings
  34         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  35         'md5': 'e87d5b8516cd04c0d81b6ee1caca28d0',
  36         'info_dict': {
  37             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  38             'ext': 'mp3',
  39             'title': '2. Raggarmordet - Röster ur det förflutna',
  40             'timestamp': 1477346700,
  41             'upload_date': '20161024',
  42             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  43             'duration': 2766,
  44         }
  45     }]
  46
  47     def _real_extract(self, url):
  48         channel, display_id = re.match(self._VALID_URL, url).groups()
  49         s = self._download_json(
  50             'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
  51             display_id)['result']
  52         media_url = s['url']
  53         cast_data = self._download_json(
  54             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id), display_id)
  55         e = cast_data['result']['episode']
  56         return {
  57             'id': compat_str(e['id']),
  58             'display_id': display_id,
  59             'url': media_url,
  60             'title': e['name'],
  61             'description': e.get('description'),
  62             'thumbnail': e.get('image'),
  63             'timestamp': unified_timestamp(e.get('publishingDate')),
  64             'duration': float_or_none(s.get('duration') or e.get('duration')),
  65         }
  66
  67
  68 class ACastChannelIE(InfoExtractor):
  69     IE_NAME = 'acast:channel'
  70     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  71     _TEST = {
  72         'url': 'https://www.acast.com/condenasttraveler',
  73         'info_dict': {
  74             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  75             'title': 'Condé Nast Traveler Podcast',
  76             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  77         },
  78         'playlist_mincount': 20,
  79     }
  80     _API_BASE_URL = 'https://www.acast.com/api/'
  81     _PAGE_SIZE = 10
  82
  83     @classmethod
  84     def suitable(cls, url):
  85         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  86
  87     def _fetch_page(self, channel_slug, page):
  88         casts = self._download_json(
  89             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
  90             channel_slug, note='Download page %d of channel data' % page)
  91         for cast in casts:
  92             yield self.url_result(
  93                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
  94                 'ACast', cast['id'])
  95
  96     def _real_extract(self, url):
  97         channel_slug = self._match_id(url)
  98         channel_data = self._download_json(
  99             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
 100         entries = OnDemandPagedList(functools.partial(
 101             self._fetch_page, channel_slug), self._PAGE_SIZE)
 102         return self.playlist_result(entries, compat_str(
 103             channel_data['id']), channel_data['name'], channel_data.get('description'))