youtube-dl/youtube_dl/extractor/acast.py

126 lines
4.6 KiB
Python
Raw Normal View History

2015-11-28 17:10:37 +00:00
# coding: utf-8
from __future__ import unicode_literals
import re
import functools
2015-11-28 17:10:37 +00:00
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
2018-04-07 17:08:45 +00:00
float_or_none,
2018-04-07 17:21:55 +00:00
int_or_none,
try_get,
2018-01-02 16:32:17 +00:00
unified_timestamp,
OnDemandPagedList,
)
2015-11-28 17:10:37 +00:00
class ACastIE(InfoExtractor):
2015-11-28 17:10:37 +00:00
IE_NAME = 'acast'
2018-12-16 21:32:59 +00:00
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
'''
2016-12-24 10:59:43 +00:00
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
2018-04-07 17:21:55 +00:00
'md5': 'a02393c74f3bdb1801c3ec2695577ce0',
2016-12-24 10:59:43 +00:00
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
2018-04-07 17:21:55 +00:00
'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
2016-12-24 10:59:43 +00:00
'timestamp': 1477346700,
'upload_date': '20161024',
2018-04-07 17:21:55 +00:00
'duration': 2766.602563,
'creator': 'Anton Berg & Martin Johnson',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
2016-12-24 10:59:43 +00:00
}
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
2018-12-16 21:32:59 +00:00
}, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
'only_matching': True,
2016-12-24 10:59:43 +00:00
}]
2015-11-28 17:10:37 +00:00
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
2018-04-07 17:08:45 +00:00
s = self._download_json(
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id),
display_id)['result']
media_url = s['url']
cast_data = self._download_json(
2018-04-07 17:21:55 +00:00
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
display_id)['result']
e = cast_data['episode']
title = e['name']
2015-11-28 17:10:37 +00:00
return {
2018-01-02 16:32:17 +00:00
'id': compat_str(e['id']),
2015-11-28 17:10:37 +00:00
'display_id': display_id,
2018-04-07 17:08:45 +00:00
'url': media_url,
2018-04-07 17:21:55 +00:00
'title': title,
'description': e.get('description') or e.get('summary'),
2018-01-02 16:32:17 +00:00
'thumbnail': e.get('image'),
'timestamp': unified_timestamp(e.get('publishingDate')),
2018-04-07 17:08:45 +00:00
'duration': float_or_none(s.get('duration') or e.get('duration')),
2018-04-07 17:21:55 +00:00
'filesize': int_or_none(e.get('contentLength')),
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),
'season_number': int_or_none(e.get('seasonNumber')),
'episode': title,
'episode_number': int_or_none(e.get('episodeNumber')),
2015-11-28 17:10:37 +00:00
}
class ACastChannelIE(InfoExtractor):
2015-11-28 17:10:37 +00:00
IE_NAME = 'acast:channel'
_VALID_URL = r'''(?x)
https?://
(?:
(?:www\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<id>[^/#?]+)
'''
_TESTS = [{
'url': 'https://www.acast.com/todayinfocus',
2015-11-28 17:10:37 +00:00
'info_dict': {
'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus',
'description': 'md5:9ba5564de5ce897faeb12963f4537a64',
2015-11-28 17:10:37 +00:00
},
'playlist_mincount': 35,
}, {
'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True,
}]
_API_BASE_URL = 'https://play.acast.com/api/'
_PAGE_SIZE = 10
2015-11-28 17:10:37 +00:00
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _fetch_page(self, channel_slug, page):
casts = self._download_json(
self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
channel_slug, note='Download page %d of channel data' % page)
for cast in casts:
yield self.url_result(
'https://play.acast.com/s/%s/%s' % (channel_slug, cast['url']),
'ACast', cast['id'])
2015-11-28 17:10:37 +00:00
def _real_extract(self, url):
channel_slug = self._match_id(url)
channel_data = self._download_json(
self._API_BASE_URL + 'channels/%s' % channel_slug, channel_slug)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, channel_slug), self._PAGE_SIZE)
return self.playlist_result(entries, compat_str(
channel_data['id']), channel_data['name'], channel_data.get('description'))