_ Git - youtube-dl/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     clean_html,
  11     float_or_none,
  12     int_or_none,
  13     try_get,
  14     unified_timestamp,
  15     OnDemandPagedList,
  16 )
  17
  18
  19 class ACastIE(InfoExtractor):
  20     IE_NAME = 'acast'
  21     _VALID_URL = r'''(?x)
  22                     https?://
  23                         (?:
  24                             (?:(?:embed|www)\.)?acast\.com/|
  25                             play\.acast\.com/s/
  26                         )
  27                         (?P<channel>[^/]+)/(?P<id>[^/#?]+)
  28                     '''
  29     _TESTS = [{
  30         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  31         'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
  32         'info_dict': {
  33             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  34             'ext': 'mp3',
  35             'title': '2. Raggarmordet - Röster ur det förflutna',
  36             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  37             'timestamp': 1477346700,
  38             'upload_date': '20161024',
  39             'duration': 2766.602563,
  40             'creator': 'Anton Berg & Martin Johnson',
  41             'series': 'Spår',
  42             'episode': '2. Raggarmordet - Röster ur det förflutna',
  43         }
  44     }, {
  45         'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
  46         'only_matching': True,
  47     }, {
  48         'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
  49         'only_matching': True,
  50     }, {
  51         'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
  52         'only_matching': True,
  53     }]
  54
  55     def _real_extract(self, url):
  56         channel, display_id = re.match(self._VALID_URL, url).groups()
  57         s = self._download_json(
  58             'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
  59             display_id)
  60         media_url = s['url']
  61         if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
  62             episode_url = s.get('episodeUrl')
  63             if episode_url:
  64                 display_id = episode_url
  65             else:
  66                 channel, display_id = re.match(self._VALID_URL, s['link']).groups()
  67         cast_data = self._download_json(
  68             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
  69             display_id)['result']
  70         e = cast_data['episode']
  71         title = e.get('name') or s['title']
  72         return {
  73             'id': compat_str(e['id']),
  74             'display_id': display_id,
  75             'url': media_url,
  76             'title': title,
  77             'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
  78             'thumbnail': e.get('image'),
  79             'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
  80             'duration': float_or_none(e.get('duration') or s.get('duration')),
  81             'filesize': int_or_none(e.get('contentLength')),
  82             'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
  83             'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
  84             'season_number': int_or_none(e.get('seasonNumber')),
  85             'episode': title,
  86             'episode_number': int_or_none(e.get('episodeNumber')),
  87         }
  88
  89
  90 class ACastChannelIE(InfoExtractor):
  91     IE_NAME = 'acast:channel'
  92     _VALID_URL = r'''(?x)
  93                     https?://
  94                         (?:
  95                             (?:www\.)?acast\.com/|
  96                             play\.acast\.com/s/
  97                         )
  98                         (?P<id>[^/#?]+)
  99                     '''
 100     _TESTS = [{
 101         'url': 'https://www.acast.com/todayinfocus',
 102         'info_dict': {
 103             'id': '4efc5294-5385-4847-98bd-519799ce5786',
 104             'title': 'Today in Focus',
 105             'description': 'md5:9ba5564de5ce897faeb12963f4537a64',
 106         },
 107         'playlist_mincount': 35,
 108     }, {
 109         'url': 'http://play.acast.com/s/ft-banking-weekly',
 110         'only_matching': True,
 111     }]
 112     _API_BASE_URL = 'https://play.acast.com/api/'
 113     _PAGE_SIZE = 10
 114
 115     @classmethod
 116     def suitable(cls, url):
 117         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 118
 119     def _fetch_page(self, channel_slug, page):
 120         casts = self._download_json(
 121             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
 122             channel_slug, note='Download page %d of channel data' % page)
 123         for cast in casts:
 124             yield self.url_result(
 125                 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']),
 126                 'ACast', cast['id'])
 127
 128     def _real_extract(self, url):
 129         channel_slug = self._match_id(url)
 130         channel_data = self._download_json(
 131             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
 132         entries = OnDemandPagedList(functools.partial(
 133             self._fetch_page, channel_slug), self._PAGE_SIZE)
 134         return self.playlist_result(entries, compat_str(
 135             channel_data['id']), channel_data['name'], channel_data.get('description'))