_ Git - youtube-dl/blob - youtube_dl/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 ..compat import compat_str
   8 from ..utils import int_or_none
   9
  10
  11 class ACastIE(InfoExtractor):
  12     IE_NAME = 'acast'
  13     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
  14     _TEST = {
  15         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  16         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  17         'info_dict': {
  18             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  19             'ext': 'mp3',
  20             'title': '"Where Are You?": Taipei 101, Taiwan',
  21             'timestamp': 1196172000000,
  22             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  23             'duration': 211,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         channel, display_id = re.match(self._VALID_URL, url).groups()
  29         cast_data = self._download_json('https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
  30         return {
  31             'id': compat_str(cast_data['id']),
  32             'display_id': display_id,
  33             'url': cast_data['blings'][0]['audio'],
  34             'title': cast_data['name'],
  35             'description': cast_data.get('description'),
  36             'thumbnail': cast_data.get('image'),
  37             'timestamp': int_or_none(cast_data.get('publishingDate')),
  38             'duration': int_or_none(cast_data.get('duration')),
  39         }
  40
  41
  42 class ACastChannelIE(InfoExtractor):
  43     IE_NAME = 'acast:channel'
  44     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  45     _TEST = {
  46         'url': 'https://www.acast.com/condenasttraveler',
  47         'info_dict': {
  48             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  49             'title': 'Condé Nast Traveler Podcast',
  50             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  51         },
  52         'playlist_mincount': 20,
  53     }
  54     _API_BASE_URL = 'https://www.acast.com/api/'
  55
  56     @classmethod
  57     def suitable(cls, url):
  58         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  59
  60     def _real_extract(self, url):
  61         display_id = self._match_id(url)
  62         channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
  63         casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
  64         entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
  65
  66         return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))