Raphaël G. Git Repositories - youtubedl/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     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?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
  21     _TESTS = [{
  22         # test with one bling
  23         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  24         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  25         'info_dict': {
  26             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  27             'ext': 'mp3',
  28             'title': '"Where Are You?": Taipei 101, Taiwan',
  29             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  30             'timestamp': 1196172000,
  31             'upload_date': '20071127',
  32             'duration': 211,
  33             'creator': 'Concierge',
  34             'series': 'Condé Nast Traveler Podcast',
  35             'episode': '"Where Are You?": Taipei 101, Taiwan',
  36         }
  37     }, {
  38         # test with multiple blings
  39         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  40         'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
  41         'info_dict': {
  42             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  43             'ext': 'mp3',
  44             'title': '2. Raggarmordet - Röster ur det förflutna',
  45             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  46             'timestamp': 1477346700,
  47             'upload_date': '20161024',
  48             'duration': 2766.602563,
  49             'creator': 'Anton Berg & Martin Johnson',
  50             'series': 'Spår',
  51             'episode': '2. Raggarmordet - Röster ur det förflutna',
  52         }
  53     }]
  54
  55     def _real_extract(self, url):
  56         channel, display_id = re.match(self._VALID_URL, url).groups()
  57         s = self._download_json(
  58             'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
  59             display_id)['result']
  60         media_url = s['url']
  61         cast_data = self._download_json(
  62             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
  63             display_id)['result']
  64         e = cast_data['episode']
  65         title = e['name']
  66         return {
  67             'id': compat_str(e['id']),
  68             'display_id': display_id,
  69             'url': media_url,
  70             'title': title,
  71             'description': e.get('description') or e.get('summary'),
  72             'thumbnail': e.get('image'),
  73             'timestamp': unified_timestamp(e.get('publishingDate')),
  74             'duration': float_or_none(s.get('duration') or e.get('duration')),
  75             'filesize': int_or_none(e.get('contentLength')),
  76             'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
  77             'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
  78             'season_number': int_or_none(e.get('seasonNumber')),
  79             'episode': title,
  80             'episode_number': int_or_none(e.get('episodeNumber')),
  81         }
  82
  83
  84 class ACastChannelIE(InfoExtractor):
  85     IE_NAME = 'acast:channel'
  86     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  87     _TEST = {
  88         'url': 'https://www.acast.com/condenasttraveler',
  89         'info_dict': {
  90             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  91             'title': 'Condé Nast Traveler Podcast',
  92             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  93         },
  94         'playlist_mincount': 20,
  95     }
  96     _API_BASE_URL = 'https://www.acast.com/api/'
  97     _PAGE_SIZE = 10
  98
  99     @classmethod
 100     def suitable(cls, url):
 101         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 102
 103     def _fetch_page(self, channel_slug, page):
 104         casts = self._download_json(
 105             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
 106             channel_slug, note='Download page %d of channel data' % page)
 107         for cast in casts:
 108             yield self.url_result(
 109                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
 110                 'ACast', cast['id'])
 111
 112     def _real_extract(self, url):
 113         channel_slug = self._match_id(url)
 114         channel_data = self._download_json(
 115             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
 116         entries = OnDemandPagedList(functools.partial(
 117             self._fetch_page, channel_slug), self._PAGE_SIZE)
 118         return self.playlist_result(entries, compat_str(
 119             channel_data['id']), channel_data['name'], channel_data.get('description'))