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     int_or_none,
  11     OnDemandPagedList,
  12 )
  13
  14
  15 class ACastIE(InfoExtractor):
  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         cast_data = self._download_json(
  34             'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
  35         return {
  36             'id': compat_str(cast_data['id']),
  37             'display_id': display_id,
  38             'url': cast_data['blings'][0]['audio'],
  39             'title': cast_data['name'],
  40             'description': cast_data.get('description'),
  41             'thumbnail': cast_data.get('image'),
  42             'timestamp': int_or_none(cast_data.get('publishingDate')),
  43             'duration': int_or_none(cast_data.get('duration')),
  44         }
  45
  46
  47 class ACastChannelIE(InfoExtractor):
  48     IE_NAME = 'acast:channel'
  49     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  50     _TEST = {
  51         'url': 'https://www.acast.com/condenasttraveler',
  52         'info_dict': {
  53             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  54             'title': 'Condé Nast Traveler Podcast',
  55             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  56         },
  57         'playlist_mincount': 20,
  58     }
  59     _API_BASE_URL = 'https://www.acast.com/api/'
  60     _PAGE_SIZE = 10
  61
  62     @classmethod
  63     def suitable(cls, url):
  64         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  65
  66     def _fetch_page(self, channel_slug, page):
  67         casts = self._download_json(
  68             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
  69             channel_slug, note='Download page %d of channel data' % page)
  70         for cast in casts:
  71             yield self.url_result(
  72                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
  73                 'ACast', cast['id'])
  74
  75     def _real_extract(self, url):
  76         channel_slug = self._match_id(url)
  77         channel_data = self._download_json(
  78             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
  79         entries = OnDemandPagedList(functools.partial(
  80             self._fetch_page, channel_slug), self._PAGE_SIZE)
  81         return self.playlist_result(entries, compat_str(
  82             channel_data['id']), channel_data['name'], channel_data.get('description'))