administration/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-14 21:23:05 +00:00
Code Issues Projects Releases Wiki Activity

[ie/Spreaker] fix SpreakerPageIE URL detection

Browse Source
This commit is contained in:
Julio Napurí 2024-11-10 16:50:22 -05:00
parent ae672525e7
commit b10c245a82
2 changed files with 16 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
yt_dlp/extractor/_extractors.py
View File

@ -1938,7 +1938,6 @@ from .spotify import (
SpotifyShowIE, SpotifyShowIE,
) )
from .spreaker import ( from .spreaker import (
SpreakerEpisodeIE,
SpreakerIE, SpreakerIE,
SpreakerPageIE, SpreakerPageIE,
SpreakerShowIE, SpreakerShowIE,

46
yt_dlp/extractor/spreaker.py
View File

@ -66,6 +66,7 @@ class SpreakerIE(InfoExtractor):
v2/episodes v2/episodes
)/ )/
(?P<id>\d+) (?P<id>\d+)
(?:\?key=(?P<key>[^&]+))?
''' '''
_TESTS = [{ _TESTS = [{
'url': 'https://api.spreaker.com/episode/12534508', 'url': 'https://api.spreaker.com/episode/12534508',
@ -94,28 +95,33 @@ class SpreakerIE(InfoExtractor):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
episode_id = self._match_id(url) episode_id, key = self._match_valid_url(url).group(
'id', 'key')
query = {}
if key is not None:
query = {'key': key}
data = self._download_json( data = self._download_json(
f'https://api.spreaker.com/v2/episodes/{episode_id}', f'https://api.spreaker.com/v2/episodes/{episode_id}',
episode_id)['response']['episode'] episode_id,
query=query)['response']['episode']
return _extract_episode(data, episode_id) return _extract_episode(data, episode_id)
class SpreakerPageIE(InfoExtractor): class SpreakerPageIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/user/[^/]+/(?P<id>[^/?#&]+)' _VALID_URL = r'https?://(?:www\.)?spreaker\.com/episode/(?P<title>[^/?#]+)-(?P<id>\d+)(?:\?key=(?P<key>[^&]+))?'
_TESTS = [{ _TESTS = [{
'url': 'https://www.spreaker.com/user/9780658/swm-ep15-how-to-market-your-music-part-2', 'url': 'https://www.spreaker.com/episode/ep-15-music-marketing-likes-part-2--12534508',
'only_matching': True, 'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) episode_id, key = self._match_valid_url(url).group(
webpage = self._download_webpage(url, display_id) 'id', 'key')
episode_id = self._search_regex( url = f'https://api.spreaker.com/episode/{episode_id}'
(r'data-episode_id=["\'](?P<id>\d+)', if key is not None:
r'episode_id\s*:\s*(?P<id>\d+)'), webpage, 'episode id') url = f'https://api.spreaker.com/episode/{episode_id}?key={key}'
return self.url_result( return self.url_result(
f'https://api.spreaker.com/episode/{episode_id}', url,
ie=SpreakerIE.ie_key(), video_id=episode_id) ie=SpreakerIE.ie_key(), video_id=episode_id)
@ -170,23 +176,3 @@ class SpreakerShowPageIE(InfoExtractor):
return self.url_result( return self.url_result(
f'https://api.spreaker.com/show/{show_id}', f'https://api.spreaker.com/show/{show_id}',
ie=SpreakerShowIE.ie_key(), video_id=show_id) ie=SpreakerShowIE.ie_key(), video_id=show_id)
class SpreakerEpisodeIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?spreaker\.com/episode/(?P<title>[^/?#]+)-(?P<id>\d+)(?:\?key=(?P<key>[^&]+))?'
_TESTS = [{
'url': 'https://www.spreaker.com/episode/ep-15-music-marketing-likes-part-2--12534508',
'only_matching': True,
}]
def _real_extract(self, url):
episode_id, key = self._match_valid_url(url).group(
'id', 'key')
result = f'https://api.spreaker.com/episode/{episode_id}'
if key is not None:
access_key = f'?key={key}'
result = f'https://api.spreaker.com/episode/{episode_id}{access_key}'
data = self._download_json(
result,
episode_id)['response']['episode']
return _extract_episode(data, episode_id)