_ 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     int_or_none,
  11     parse_iso8601,
  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     _TEST = {
  20         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  21         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  22         'info_dict': {
  23             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  24             'ext': 'mp3',
  25             'title': '"Where Are You?": Taipei 101, Taiwan',
  26             'timestamp': 1196172000,
  27             'upload_date': '20071127',
  28             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  29             'duration': 211,
  30         }
  31     }
  32
  33     def _real_extract(self, url):
  34         channel, display_id = re.match(self._VALID_URL, url).groups()
  35         cast_data = self._download_json(
  36             'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
  37         return {
  38             'id': compat_str(cast_data['id']),
  39             'display_id': display_id,
  40             'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
  41             'title': cast_data['name'],
  42             'description': cast_data.get('description'),
  43             'thumbnail': cast_data.get('image'),
  44             'timestamp': parse_iso8601(cast_data.get('publishingDate')),
  45             'duration': int_or_none(cast_data.get('duration')),
  46         }
  47
  48
  49 class ACastChannelIE(InfoExtractor):
  50     IE_NAME = 'acast:channel'
  51     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  52     _TEST = {
  53         'url': 'https://www.acast.com/condenasttraveler',
  54         'info_dict': {
  55             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  56             'title': 'Condé Nast Traveler Podcast',
  57             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  58         },
  59         'playlist_mincount': 20,
  60     }
  61     _API_BASE_URL = 'https://www.acast.com/api/'
  62     _PAGE_SIZE = 10
  63
  64     @classmethod
  65     def suitable(cls, url):
  66         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  67
  68     def _fetch_page(self, channel_slug, page):
  69         casts = self._download_json(
  70             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
  71             channel_slug, note='Download page %d of channel data' % page)
  72         for cast in casts:
  73             yield self.url_result(
  74                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
  75                 'ACast', cast['id'])
  76
  77     def _real_extract(self, url):
  78         channel_slug = self._match_id(url)
  79         channel_data = self._download_json(
  80             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
  81         entries = OnDemandPagedList(functools.partial(
  82             self._fetch_page, channel_slug), self._PAGE_SIZE)
  83         return self.playlist_result(entries, compat_str(
  84             channel_data['id']), channel_data['name'], channel_data.get('description'))