yt-dlp/yt_dlp/extractor/acast.py

126 lines
4.4 KiB
Python
Raw Normal View History

2015-11-28 18:10:37 +01:00
# coding: utf-8
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
clean_html,
2021-01-08 17:14:50 +01:00
clean_podcast_url,
2018-04-07 19:21:55 +02:00
int_or_none,
2021-01-01 13:26:37 +01:00
parse_iso8601,
)
2015-11-28 18:10:37 +01:00
2021-01-01 13:26:37 +01:00
class ACastBaseIE(InfoExtractor):
def _extract_episode(self, episode, show_info):
title = episode['title']
info = {
'id': episode['id'],
'display_id': episode.get('episodeUrl'),
2021-01-08 17:14:50 +01:00
'url': clean_podcast_url(episode['url']),
2021-01-01 13:26:37 +01:00
'title': title,
'description': clean_html(episode.get('description') or episode.get('summary')),
'thumbnail': episode.get('image'),
'timestamp': parse_iso8601(episode.get('publishDate')),
'duration': int_or_none(episode.get('duration')),
'filesize': int_or_none(episode.get('contentLength')),
'season_number': int_or_none(episode.get('season')),
'episode': title,
'episode_number': int_or_none(episode.get('episode')),
}
info.update(show_info)
return info
def _extract_show_info(self, show):
return {
'creator': show.get('author'),
'series': show.get('title'),
}
def _call_api(self, path, video_id, query=None):
return self._download_json(
'https://feeder.acast.com/api/v1/shows/' + path, video_id, query=query)
class ACastIE(ACastBaseIE):
2015-11-28 18:10:37 +01:00
IE_NAME = 'acast'
2018-12-16 22:32:59 +01:00
_VALID_URL = r'''(?x)
https?://
(?:
(?:(?:embed|www)\.)?acast\.com/|
play\.acast\.com/s/
)
(?P<channel>[^/]+)/(?P<id>[^/#?]+)
'''
2016-12-24 11:59:43 +01:00
_TESTS = [{
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
2021-01-01 13:26:37 +01:00
'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
2016-12-24 11:59:43 +01:00
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
2021-01-01 13:26:37 +01:00
'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
2016-12-24 11:59:43 +01:00
'timestamp': 1477346700,
'upload_date': '20161024',
2021-01-01 13:26:37 +01:00
'duration': 2766,
2018-04-07 19:21:55 +02:00
'creator': 'Anton Berg & Martin Johnson',
'series': 'Spår',
'episode': '2. Raggarmordet - Röster ur det förflutna',
2016-12-24 11:59:43 +01:00
}
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
2018-12-16 22:32:59 +01:00
}, {
2021-01-01 13:26:37 +01:00
'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
2018-12-16 22:32:59 +01:00
'only_matching': True,
}, {
'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
'only_matching': True,
2016-12-24 11:59:43 +01:00
}]
2015-11-28 18:10:37 +01:00
def _real_extract(self, url):
channel, display_id = self._match_valid_url(url).groups()
2021-01-01 13:26:37 +01:00
episode = self._call_api(
'%s/episodes/%s' % (channel, display_id),
display_id, {'showInfo': 'true'})
return self._extract_episode(
episode, self._extract_show_info(episode.get('show') or {}))
2015-11-28 18:10:37 +01:00
2021-01-01 13:26:37 +01:00
class ACastChannelIE(ACastBaseIE):
2015-11-28 18:10:37 +01:00
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 18:10:37 +01:00
'info_dict': {
'id': '4efc5294-5385-4847-98bd-519799ce5786',
'title': 'Today in Focus',
2021-01-01 13:26:37 +01:00
'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
2015-11-28 18:10:37 +01:00
},
2021-01-01 13:26:37 +01:00
'playlist_mincount': 200,
}, {
'url': 'http://play.acast.com/s/ft-banking-weekly',
'only_matching': True,
}]
2015-11-28 18:10:37 +01:00
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _real_extract(self, url):
2021-01-01 13:26:37 +01:00
show_slug = self._match_id(url)
show = self._call_api(show_slug, show_slug)
show_info = self._extract_show_info(show)
entries = []
for episode in (show.get('episodes') or []):
entries.append(self._extract_episode(episode, show_info))
return self.playlist_result(
entries, show.get('id'), show.get('title'), show.get('description'))