github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 20:38:11 -05:00
Code Issues Projects Releases Packages Wiki Activity

[ie/spreaker] Support podcast and feed pages (#10968)

Browse source 
Closes #10925
Authored by: subrat-lima
This commit is contained in:
Subrat Lima 2024-11-12 00:38:18 +05:30 committed by GitHub
parent e398217aae
commit c673731061
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 26 additions and 25 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View file

@ -1940,7 +1940,6 @@
from .spreaker import (
SpreakerIE,
SpreakerShowIE,
SpreakerShowPageIE,
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE

50
yt_dlp/extractor/spreaker.py
View file

@ -2,6 +2,7 @@
from .common import InfoExtractor
from ..utils import (
filter_dict,
float_or_none,
int_or_none,
parse_qs,
@ -119,29 +120,46 @@ class SpreakerIE(InfoExtractor):
def _real_extract(self, url):
episode_id = self._match_id(url)
data = self._download_json(
f'https://api.spreaker.com/v2/episodes/{episode_id}',
episode_id, query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode']
f'https://api.spreaker.com/v2/episodes/{episode_id}', episode_id,
query=traverse_obj(parse_qs(url), {'key': ('key', 0)}))['response']['episode']
return _extract_episode(data, episode_id)
class SpreakerShowIE(InfoExtractor):
_VALID_URL = r'https?://api\.spreaker\.com/show/(?P<id>\d+)'
_VALID_URL = [
r'https?://api\.spreaker\.com/show/(?P<id>\d+)',
r'https?://(?:www\.)?spreaker\.com/podcast/[\w-]+--(?P<id>[\d]+)',
r'https?://(?:www\.)?spreaker\.com/show/(?P<id>\d+)/episodes/feed',
]
_TESTS = [{
'url': 'https://api.spreaker.com/show/4652058',
'info_dict': {
'id': '4652058',
},
'playlist_mincount': 118,
}, {
'url': 'https://www.spreaker.com/podcast/health-wealth--5918323',
'info_dict': {
'id': '5918323',
},
'playlist_mincount': 60,
}, {
'url': 'https://www.spreaker.com/show/5887186/episodes/feed',
'info_dict': {
'id': '5887186',
},
'playlist_mincount': 290,
}]
def _entries(self, show_id):
def _entries(self, show_id, key=None):
for page_num in itertools.count(1):
episodes = self._download_json(
f'https://api.spreaker.com/show/{show_id}/episodes',
show_id, note=f'Downloading JSON page {page_num}', query={
show_id, note=f'Downloading JSON page {page_num}', query=filter_dict({
'page': page_num,
'max_per_page': 100,
})
'key': key,
}))
pager = try_get(episodes, lambda x: x['response']['pager'], dict)
if not pager:
break
@ -157,21 +175,5 @@ def _entries(self, show_id):
def _real_extract(self, url):
show_id = self._match_id(url)
return self.playlist_result(self._entries(show_id), playlist_id=show_id)
class SpreakerShowPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/show/(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://www.spreaker.com/show/success-with-music',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
show_id = self._search_regex(
r'show_id\s*:\s*(?P<id>\d+)', webpage, 'show id')
return self.url_result(
f'https://api.spreaker.com/show/{show_id}',
ie=SpreakerShowIE.ie_key(), video_id=show_id)
key = traverse_obj(parse_qs(url), ('key', 0))
return self.playlist_result(self._entries(show_id, key), playlist_id=show_id)