_ 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 ACastBaseIE(InfoExtractor):
  12     _API_BASE_URL = 'https://www.acast.com/api/'
  13
  14
  15 class ACastIE(ACastBaseIE):
  16     IE_NAME = 'acast'
  17     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
  18     _TEST = {
  19         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  20         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  21         'info_dict': {
  22             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  23             'ext': 'mp3',
  24             'title': '"Where Are You?": Taipei 101, Taiwan',
  25             'timestamp': 1196172000000,
  26             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  27             'duration': 211,
  28         }
  29     }
  30
  31     def _real_extract(self, url):
  32         channel, display_id = re.match(self._VALID_URL, url).groups()
  33
  34         embed_page = self._download_webpage(
  35             re.sub('(?:www\.)?acast\.com', 'embedcdn.acast.com', url), display_id)
  36         cast_data = self._parse_json(self._search_regex(
  37             r'window\[\'acast/queries\'\]\s*=\s*([^;]+);', embed_page, 'acast data'),
  38             display_id)['GetAcast/%s/%s' % (channel, display_id)]
  39
  40         return {
  41             'id': compat_str(cast_data['id']),
  42             'display_id': display_id,
  43             'url': cast_data['blings'][0]['audio'],
  44             'title': cast_data['name'],
  45             'description': cast_data.get('description'),
  46             'thumbnail': cast_data.get('image'),
  47             'timestamp': int_or_none(cast_data.get('publishingDate')),
  48             'duration': int_or_none(cast_data.get('duration')),
  49         }
  50
  51
  52 class ACastChannelIE(ACastBaseIE):
  53     IE_NAME = 'acast:channel'
  54     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  55     _TEST = {
  56         'url': 'https://www.acast.com/condenasttraveler',
  57         'info_dict': {
  58             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  59             'title': 'Condé Nast Traveler Podcast',
  60             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  61         },
  62         'playlist_mincount': 20,
  63     }
  64
  65     @classmethod
  66     def suitable(cls, url):
  67         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  68
  69     def _real_extract(self, url):
  70         display_id = self._match_id(url)
  71         channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id)
  72         casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id)
  73         entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts]
  74
  75         return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description'))