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     float_or_none,
  11     int_or_none,
  12     try_get,
  13     unified_timestamp,
  14     OnDemandPagedList,
  15 )
  16
  17
  18 class ACastIE(InfoExtractor):
  19     IE_NAME = 'acast'
  20     _VALID_URL = r'''(?x)
  21                     https?://
  22                         (?:
  23                             (?:(?:embed|www)\.)?acast\.com/|
  24                             play\.acast\.com/s/
  25                         )
  26                         (?P<channel>[^/]+)/(?P<id>[^/#?]+)
  27                     '''
  28     _TESTS = [{
  29         'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
  30         'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
  31         'info_dict': {
  32             'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
  33             'ext': 'mp3',
  34             'title': '2. Raggarmordet - Röster ur det förflutna',
  35             'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
  36             'timestamp': 1477346700,
  37             'upload_date': '20161024',
  38             'duration': 2766.602563,
  39             'creator': 'Anton Berg & Martin Johnson',
  40             'series': 'Spår',
  41             'episode': '2. Raggarmordet - Röster ur det förflutna',
  42         }
  43     }, {
  44         'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
  45         'only_matching': True,
  46     }, {
  47         'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
  48         'only_matching': True,
  49     }]
  50
  51     def _real_extract(self, url):
  52         channel, display_id = re.match(self._VALID_URL, url).groups()
  53         s = self._download_json(
  54             'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
  55             display_id)['result']
  56         media_url = s['url']
  57         cast_data = self._download_json(
  58             'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
  59             display_id)['result']
  60         e = cast_data['episode']
  61         title = e['name']
  62         return {
  63             'id': compat_str(e['id']),
  64             'display_id': display_id,
  65             'url': media_url,
  66             'title': title,
  67             'description': e.get('description') or e.get('summary'),
  68             'thumbnail': e.get('image'),
  69             'timestamp': unified_timestamp(e.get('publishingDate')),
  70             'duration': float_or_none(s.get('duration') or e.get('duration')),
  71             'filesize': int_or_none(e.get('contentLength')),
  72             'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
  73             'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
  74             'season_number': int_or_none(e.get('seasonNumber')),
  75             'episode': title,
  76             'episode_number': int_or_none(e.get('episodeNumber')),
  77         }
  78
  79
  80 class ACastChannelIE(InfoExtractor):
  81     IE_NAME = 'acast:channel'
  82     _VALID_URL = r'''(?x)
  83                     https?://
  84                         (?:
  85                             (?:www\.)?acast\.com/|
  86                             play\.acast\.com/s/
  87                         )
  88                         (?P<id>[^/#?]+)
  89                     '''
  90     _TESTS = [{
  91         'url': 'https://www.acast.com/todayinfocus',
  92         'info_dict': {
  93             'id': '4efc5294-5385-4847-98bd-519799ce5786',
  94             'title': 'Today in Focus',
  95             'description': 'md5:9ba5564de5ce897faeb12963f4537a64',
  96         },
  97         'playlist_mincount': 35,
  98     }, {
  99         'url': 'http://play.acast.com/s/ft-banking-weekly',
 100         'only_matching': True,
 101     }]
 102     _API_BASE_URL = 'https://play.acast.com/api/'
 103     _PAGE_SIZE = 10
 104
 105     @classmethod
 106     def suitable(cls, url):
 107         return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
 108
 109     def _fetch_page(self, channel_slug, page):
 110         casts = self._download_json(
 111             self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
 112             channel_slug, note='Download page %d of channel data' % page)
 113         for cast in casts:
 114             yield self.url_result(
 115                 'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']),
 116                 'ACast', cast['id'])
 117
 118     def _real_extract(self, url):
 119         channel_slug = self._match_id(url)
 120         channel_data = self._download_json(
 121             self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
 122         entries = OnDemandPagedList(functools.partial(
 123             self._fetch_page, channel_slug), self._PAGE_SIZE)
 124         return self.playlist_result(entries, compat_str(
 125             channel_data['id']), channel_data['name'], channel_data.get('description'))