w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[acast] fix channel extraction(closes #9117)

Browse source
This commit is contained in:
remitamine 2016-04-08 15:15:34 +01:00
parent 9a32e80477
commit a1ff3cd5f9
1 changed files with 24 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

32
youtube_dl/extractor/acast.py
View file

@ -2,10 +2,14 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import functools
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_str from ..compat import compat_str
from ..utils import int_or_none from ..utils import (
int_or_none,
OnDemandPagedList,
)
class ACastIE(InfoExtractor): class ACastIE(InfoExtractor):
@ -26,7 +30,8 @@ class ACastIE(InfoExtractor):
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()
cast_data = self._download_json('https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id) cast_data = self._download_json(
'https://embed.acast.com/api/acasts/%s/%s' % (channel, display_id), display_id)
return { return {
'id': compat_str(cast_data['id']), 'id': compat_str(cast_data['id']),
'display_id': display_id, 'display_id': display_id,
@ -52,15 +57,26 @@ class ACastChannelIE(InfoExtractor):
'playlist_mincount': 20, 'playlist_mincount': 20,
} }
_API_BASE_URL = 'https://www.acast.com/api/' _API_BASE_URL = 'https://www.acast.com/api/'
_PAGE_SIZE = 10
@classmethod @classmethod
def suitable(cls, url): def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url) return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
def _real_extract(self, url): def _fetch_page(self, channel_slug, page):
display_id = self._match_id(url) casts = self._download_json(
channel_data = self._download_json(self._API_BASE_URL + 'channels/%s' % display_id, display_id) self._API_BASE_URL + 'channels/%s/acasts?page=%s' % (channel_slug, page),
casts = self._download_json(self._API_BASE_URL + 'channels/%s/acasts' % display_id, display_id) channel_slug, note='Download page %d of channel data' % page)
entries = [self.url_result('https://www.acast.com/%s/%s' % (display_id, cast['url']), 'ACast') for cast in casts] for cast in casts:
yield self.url_result(
'https://www.acast.com/%s/%s' % (channel_slug, cast['url']),
'ACast', cast['id'])
return self.playlist_result(entries, compat_str(channel_data['id']), channel_data['name'], channel_data.get('description')) 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'))