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     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     _TESTS = [{
  20         # test with one bling
  21         'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
  22         'md5': 'ada3de5a1e3a2a381327d749854788bb',
  23         'info_dict': {
  24             'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
  25             'ext': 'mp3',
  26             'title': '"Where Are You?": Taipei 101, Taiwan',
  27             'timestamp': 1196172000,
  28             'upload_date': '20071127',
  29             'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
  30             'duration': 211,
  31         }
  32     }, {
  33         # test with multiple blings
  34         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  35         'md5': '55c0097badd7095f494c99a172f86501',
  36         'info_dict': {
  37             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  38             'ext': 'mp3',
  39             'title': '2. Raggarmordet - Röster ur det förflutna',
  40             'timestamp': 1477346700,
  41             'upload_date': '20161024',
  42             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  43             'duration': 2797,
  44         }
  45     }]
  46
  47     def _real_extract(self, url):
  48         channel, display_id = re.match(self._VALID_URL, url).groups()
  49         cast_data = self._download_json(
  50             'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
  51         return {
  52             'id': compat_str(cast_data['id']),
  53             'display_id': display_id,
  54             'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
  55             'title': cast_data['name'],
  56             'description': cast_data.get('description'),
  57             'thumbnail': cast_data.get('image'),
  58             'timestamp': parse_iso8601(cast_data.get('publishingDate')),
  59             'duration': int_or_none(cast_data.get('duration')),
  60         }
  61
  62
  63 class ACastChannelIE(InfoExtractor):
  64     IE_NAME = 'acast:channel'
  65     _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
  66     _TEST = {
  67         'url': 'https://www.acast.com/condenasttraveler',
  68         'info_dict': {
  69             'id': '50544219-29bb-499e-a083-6087f4cb7797',
  70             'title': 'Condé Nast Traveler Podcast',
  71             'description': 'md5:98646dee22a5b386626ae31866638fbd',
  72         },
  73         'playlist_mincount': 20,
  74     }
  75     _API_BASE_URL = 'https://www.acast.com/api/'
  76     _PAGE_SIZE = 10
  77
  78     @classmethod
  79     def suitable(cls, url):
  80         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
  81
  82     def _fetch_page(self, channel_slug, page):
  83         casts = self._download_json(
  84             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
  85             channel_slug, note='Download page %d of channel data' % page)
  86         for cast in casts:
  87             yield self.url_result(
  88                 'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
  89                 'ACast', cast['id'])
  90
  91     def _real_extract(self, url):
  92         channel_slug = self._match_id(url)
  93         channel_data = self._download_json(
  94             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
  95         entries = OnDemandPagedList(functools.partial(
  96             self._fetch_page, channel_slug), self._PAGE_SIZE)
  97         return self.playlist_result(entries, compat_str(
  98             channel_data['id']), channel_data['name'], channel_data.get('description'))