pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-12 21:37:59 +09:00
Code Issues Projects Releases Wiki Activity

[acast] add support for URLs with episode id(closes #21444)

Browse Source
This commit is contained in:
Remita Amine 2019-07-01 12:05:18 +01:00
parent 5e3da0d42b
commit 976e1ff7f9
1 changed files with 17 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/acast.py
View File

@ -7,6 +7,7 @@ import functools
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import ( from ..utils import (
clean_html,
float_or_none, float_or_none,
int_or_none, int_or_none,
try_get, try_get,
@ -27,7 +28,7 @@ class ACastIE(InfoExtractor):
''' '''
_TESTS = [{ _TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna', 'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
'md5': 'a02393c74f3bdb1801c3ec2695577ce0', 'md5': '16d936099ec5ca2d5869e3a813ee8dc4',
'info_dict': { 'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9', 'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3', 'ext': 'mp3',
@ -46,28 +47,37 @@ class ACastIE(InfoExtractor):
}, { }, {
'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22', 'url': 'https://play.acast.com/s/rattegangspodden/s04e09-styckmordet-i-helenelund-del-22',
'only_matching': True, 'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups() channel, display_id = re.match(self._VALID_URL, url).groups()
s = self._download_json( s = self._download_json(
'https://play-api.acast.com/stitch/%s/%s' % (channel, display_id), 'https://feeder.acast.com/api/v1/shows/%s/episodes/%s' % (channel, display_id),
display_id)['result'] display_id)
media_url = s['url'] media_url = s['url']
if re.search(r'[0-9a-f]{8}-(?:[0-9a-f]{4}-){3}[0-9a-f]{12}', display_id):
episode_url = s.get('episodeUrl')
if episode_url:
display_id = episode_url
else:
channel, display_id = re.match(self._VALID_URL, s['link']).groups()
cast_data = self._download_json( cast_data = self._download_json(
'https://play-api.acast.com/splash/%s/%s' % (channel, display_id), 'https://play-api.acast.com/splash/%s/%s' % (channel, display_id),
display_id)['result'] display_id)['result']
e = cast_data['episode'] e = cast_data['episode']
title = e['name'] title = e.get('name') or s['title']
return { return {
'id': compat_str(e['id']), 'id': compat_str(e['id']),
'display_id': display_id, 'display_id': display_id,
'url': media_url, 'url': media_url,
'title': title, 'title': title,
'description': e.get('description') or e.get('summary'), 'description': e.get('summary') or clean_html(e.get('description') or s.get('description')),
'thumbnail': e.get('image'), 'thumbnail': e.get('image'),
'timestamp': unified_timestamp(e.get('publishingDate')), 'timestamp': unified_timestamp(e.get('publishingDate') or s.get('publishDate')),
'duration': float_or_none(s.get('duration') or e.get('duration')), 'duration': float_or_none(e.get('duration') or s.get('duration')),
'filesize': int_or_none(e.get('contentLength')), 'filesize': int_or_none(e.get('contentLength')),
'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str), 'creator': try_get(cast_data, lambda x: x['show']['author'], compat_str),
'series': try_get(cast_data, lambda x: x['show']['name'], compat_str), 'series': try_get(cast_data, lambda x: x['show']['name'], compat_str),