_ 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
  30         embed_page = self._download_webpage(
  31             re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
  32         cast_data = self._parse_json(self._search_regex(
  33             r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
  34             display_id)['GetAcast/%s/%s' % (channel, display_id)]
  35
  36         return {
  37             'id': compat_str(cast_data['id']),
  38             'display_id': display_id,
  39             'url': cast_data['blings'][0]['audio'],
  40             'title': cast_data['name'],
  41             'description': cast_data.get('description'),
  42             'thumbnail': cast_data.get('image'),
  43             'timestamp': int_or_none(cast_data.get('publishingDate')),
  44             'duration': int_or_none(cast_data.get('duration')),
  45         }
  46
  47
  48 class ACastChannelIE(InfoExtractor):
  49     IE_NAME = 'acast:channel'
  50     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  51     _TEST = {
  52         'url': 'https://www.acast.com/condenasttraveler',
  53         'info_dict': {
  54             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  55             'title': 'Condé Nast Traveler Podcast',
  56             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  57         },
  58         'playlist_mincount': 20,
  59     }
  60     _API_BASE_URL = 'https://www.acast.com/api/'
  61
  62     @classmethod
  63     def suitable(cls, url):
  64         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  65
  66     def _real_extract(self, url):
  67         display_id = self._match_id(url)
  68         channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
  69         casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
  70         entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
  71
  72         return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))