artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-06-12 05:44:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/onsen] Fix extraction (#16830)

Browse Source 
Closes #16674
Authored by: doe1080
This commit is contained in:
doe1080 2026-06-09 15:31:34 +09:00 committed by GitHub
parent 70050a6262
commit bc90c36b13
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 17 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
yt_dlp/extractor/onsen.py
View File

@ -21,6 +21,7 @@ class OnsenIE(InfoExtractor):
IE_NAME = 'onsen'
IE_DESC = 'インターネットラジオステーション＜音泉＞'
_API_HEADERS = {'X-Client': 'onsen-web'}
_BASE_URL = 'https://www.onsen.ag'
_HEADERS = {'Referer': f'{_BASE_URL}/'}
_NETRC_MACHINE = 'onsen'
@ -71,6 +72,15 @@ class OnsenIE(InfoExtractor):
'playlist_mincount': 35,
}]
@classmethod
def get_temp_id(cls, url):
import base64
import urllib.parse
if c := urllib.parse.parse_qs(urllib.parse.urlparse(url).query).get('c'):
return base64.urlsafe_b64decode(f'{c[-1]}===').decode()
return super().get_temp_id(url)
@staticmethod
def _get_encoded_id(program):
return base64.urlsafe_b64encode(str(program['id']).encode()).decode()
@ -80,6 +90,7 @@ class OnsenIE(InfoExtractor):
f'{self._BASE_URL}/web_api/signin', None, 'Logging in', headers={
'Accept': 'application/json',
'Content-Type': 'application/json',
**self._API_HEADERS,
}, data=json.dumps({
'session': {
'email': username,
@ -94,7 +105,8 @@ class OnsenIE(InfoExtractor):
program_id = self._match_id(url)
try:
programs = self._download_json(
f'{self._BASE_URL}/web_api/programs/{program_id}', program_id)
f'{self._BASE_URL}/web_api/programs/{program_id}',
program_id, headers=self._API_HEADERS)
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 404:
raise ExtractorError('Invalid URL', expected=True)
@ -103,8 +115,10 @@ class OnsenIE(InfoExtractor):
query = {k: v[-1] for k, v in parse_qs(url).items() if v}
if 'c' not in query:
entries = [
self.url_result(update_url_query(url, {'c': self._get_encoded_id(program)}), OnsenIE)
for program in traverse_obj(programs, ('contents', lambda _, v: v['id']))
self.url_result(
update_url_query(url, {'c': self._get_encoded_id(program)}),
OnsenIE, str_or_none(program['id']),
) for program in traverse_obj(programs, ('contents', lambda _, v: v['id']))
]
return self.playlist_result(