artem/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2026-07-02 16:28:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

[ie/svt] Fix extractor (#16288)

Browse Source 
Closes #16255
Authored by: billauer, dirkf

Co-authored-by: dirkf <1222880+dirkf@users.noreply.github.com>
This commit is contained in:
billauer 2026-06-30 05:20:11 +02:00 committed by GitHub
parent e7b5d68f37
commit c84b2c6736
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 12 additions and 20 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
yt_dlp/extractor/svt.py
View File

@ -6,6 +6,8 @@ from ..utils import (
determine_ext, determine_ext,
dict_get, dict_get,
int_or_none, int_or_none,
js_to_json,
str_or_none,
try_get, try_get,
unified_timestamp, unified_timestamp,
) )
@ -17,6 +19,7 @@ from ..utils.traversal import (
class SVTBaseIE(InfoExtractor): class SVTBaseIE(InfoExtractor):
_GEO_COUNTRIES = ['SE'] _GEO_COUNTRIES = ['SE']
_GEO_BYPASS = False
def _extract_video(self, video_info, video_id): def _extract_video(self, video_info, video_id):
is_live = dict_get(video_info, ('live', 'simulcast'), default=False) is_live = dict_get(video_info, ('live', 'simulcast'), default=False)
@ -252,32 +255,21 @@ class SVTPlayIE(SVTBaseIE):
mobj = self._match_valid_url(url) mobj = self._match_valid_url(url)
video_id = mobj.group('id') video_id = mobj.group('id')
svt_id = mobj.group('svt_id') or mobj.group('modal_id') svt_id = mobj.group('svt_id') or mobj.group('modal_id')
if svt_id: webpage = self._download_webpage(url, video_id, fatal=not svt_id) or ''
return self._extract_by_video_id(svt_id)
webpage = self._download_webpage(url, video_id)
data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
'props', 'urqlState', ..., 'data', {json.loads},
'detailsPageByPath', {dict}, any, {require('video data')}))
details = traverse_obj(data, (
'modules', lambda _, v: v['details']['smartStart']['item']['videos'], 'details', any))
svt_id = traverse_obj(details, (
'smartStart', 'item', 'videos',
# There can be 'AudioDescribed' and 'SignInterpreted' variants; try 'Default' or else get first
(lambda _, v: v['accessibility'] == 'Default', 0),
'svtId', {str}, any))
if not svt_id: if not svt_id:
svt_id = traverse_obj(data, ('video', 'svtId', {str}, {require('SVT ID')})) data = self._search_json(
r'(?<=[\s.])URQL_DATA\s*=', webpage, 'json data', video_id,
transform_source=js_to_json)
svt_id = traverse_obj(data, (
{dict.values}, ..., 'data', {json.loads}, 'detailsPageByPath',
'smartStart', 'videoSvtId', {str_or_none}, any, {require('SVT ID')}))
info_dict = self._extract_by_video_id(svt_id) info_dict = self._extract_by_video_id(svt_id)
if not info_dict.get('title'): if not info_dict.get('title'):
info_dict['title'] = re.sub(r'\s*\|\s*.+?$', '', self._og_search_title(webpage)) info_dict['title'] = re.sub(r'\s*\|\s*.+?$', '', self._og_search_title(webpage))
if not info_dict.get('thumbnail'):
info_dict['thumbnail'] = self._og_search_thumbnail(webpage)
if not info_dict.get('description'): if not info_dict.get('description'):
info_dict['description'] = traverse_obj(details, ('description', {str})) info_dict['description'] = self._og_search_description(webpage, default=None)
info_dict['thumbnail'] = self._og_search_thumbnail(webpage)
return info_dict return info_dict