aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/acast.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/acast.py')
-rw-r--r--youtube_dl/extractor/acast.py150
1 files changed, 89 insertions, 61 deletions
diff --git a/youtube_dl/extractor/acast.py b/youtube_dl/extractor/acast.py
index 6dace3051..b9355a2c8 100644
--- a/youtube_dl/extractor/acast.py
+++ b/youtube_dl/extractor/acast.py
@@ -2,97 +2,125 @@
from __future__ import unicode_literals
import re
-import functools
from .common import InfoExtractor
-from ..compat import compat_str
from ..utils import (
+ clean_html,
+ clean_podcast_url,
int_or_none,
parse_iso8601,
- OnDemandPagedList,
)
-class ACastIE(InfoExtractor):
+class ACastBaseIE(InfoExtractor):
+ def _extract_episode(self, episode, show_info):
+ title = episode['title']
+ info = {
+ 'id': episode['id'],
+ 'display_id': episode.get('episodeUrl'),
+ 'url': clean_podcast_url(episode['url']),
+ '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):
IE_NAME = 'acast'
- _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<channel>[^/]+)/(?P<id>[^/#?]+)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:(?:embed|www)\.)?acast\.com/|
+ play\.acast\.com/s/
+ )
+ (?P<channel>[^/]+)/(?P<id>[^/#?]+)
+ '''
_TESTS = [{
- # test with one bling
- 'url': 'https://www.acast.com/condenasttraveler/-where-are-you-taipei-101-taiwan',
- 'md5': 'ada3de5a1e3a2a381327d749854788bb',
- 'info_dict': {
- 'id': '57de3baa-4bb0-487e-9418-2692c1277a34',
- 'ext': 'mp3',
- 'title': '"Where Are You?": Taipei 101, Taiwan',
- 'timestamp': 1196172000,
- 'upload_date': '20071127',
- 'description': 'md5:a0b4ef3634e63866b542e5b1199a1a0e',
- 'duration': 211,
- }
- }, {
- # test with multiple blings
'url': 'https://www.acast.com/sparpodcast/2.raggarmordet-rosterurdetforflutna',
- 'md5': '55c0097badd7095f494c99a172f86501',
+ 'md5': 'f5598f3ad1e4776fed12ec1407153e4b',
'info_dict': {
'id': '2a92b283-1a75-4ad8-8396-499c641de0d9',
'ext': 'mp3',
'title': '2. Raggarmordet - Röster ur det förflutna',
+ 'description': 'md5:a992ae67f4d98f1c0141598f7bebbf67',
'timestamp': 1477346700,
'upload_date': '20161024',
- 'description': 'md5:4f81f6d8cf2e12ee21a321d8bca32db4',
- 'duration': 2797,
+ 'duration': 2766,
+ 'creator': 'Anton Berg & Martin Johnson',
+ 'series': 'Spår',
+ 'episode': '2. Raggarmordet - Röster ur det förflutna',
}
+ }, {
+ 'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://play.acast.com/s/rattegangspodden/s04e09styckmordetihelenelund-del2-2',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://play.acast.com/s/sparpodcast/2a92b283-1a75-4ad8-8396-499c641de0d9',
+ 'only_matching': True,
}]
def _real_extract(self, url):
channel, display_id = re.match(self._VALID_URL, url).groups()
- cast_data = self._download_json(
- 'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
- return {
- 'id': compat_str(cast_data['id']),
- 'display_id': display_id,
- 'url': [b['audio'] for b in cast_data['blings'] if b['type'] == 'BlingAudio'][0],
- 'title': cast_data['name'],
- 'description': cast_data.get('description'),
- 'thumbnail': cast_data.get('image'),
- 'timestamp': parse_iso8601(cast_data.get('publishingDate')),
- 'duration': int_or_none(cast_data.get('duration')),
- }
+ 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 {}))
-class ACastChannelIE(InfoExtractor):
+class ACastChannelIE(ACastBaseIE):
IE_NAME = 'acast:channel'
- _VALID_URL = r'https?://(?:www\.)?acast\.com/(?P<id>[^/#?]+)'
- _TEST = {
- 'url': 'https://www.acast.com/condenasttraveler',
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ (?:www\.)?acast\.com/|
+ play\.acast\.com/s/
+ )
+ (?P<id>[^/#?]+)
+ '''
+ _TESTS = [{
+ 'url': 'https://www.acast.com/todayinfocus',
'info_dict': {
- 'id': '50544219-29bb-499e-a083-6087f4cb7797',
- 'title': 'Condé Nast Traveler Podcast',
- 'description': 'md5:98646dee22a5b386626ae31866638fbd',
+ 'id': '4efc5294-5385-4847-98bd-519799ce5786',
+ 'title': 'Today in Focus',
+ 'description': 'md5:c09ce28c91002ce4ffce71d6504abaae',
},
- 'playlist_mincount': 20,
- }
- _API_BASE_URL = 'https://www.acast.com/api/'
- _PAGE_SIZE = 10
+ 'playlist_mincount': 200,
+ }, {
+ 'url': 'http://play.acast.com/s/ft-banking-weekly',
+ 'only_matching': True,
+ }]
@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://www.acast.com/%s/%s' % (channel_slug, cast['url']),
- 'ACast', cast['id'])
-
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'))
+ 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'))
generated by cgit v1.2.3 (git 2.26.2) at 2025-11-02 07:47:29 +0000