mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-22 02:15:12 +00:00
[ndr] Fix extraction (closes #24326)
This commit is contained in:
parent
541fe3eaff
commit
4cbce88f8b
1 changed files with 9 additions and 4 deletions
|
@ -7,6 +7,7 @@
|
|||
from ..utils import (
|
||||
determine_ext,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
qualities,
|
||||
try_get,
|
||||
|
@ -87,21 +88,25 @@ class NDRIE(NDRBaseIE):
|
|||
|
||||
def _extract_embed(self, webpage, display_id):
|
||||
embed_url = self._html_search_meta(
|
||||
'embedURL', webpage, 'embed URL', fatal=True)
|
||||
'embedURL', webpage, 'embed URL',
|
||||
default=None) or self._search_regex(
|
||||
r'\bembedUrl["\']\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
|
||||
'embed URL', group='url')
|
||||
description = self._search_regex(
|
||||
r'<p[^>]+itemprop="description">([^<]+)</p>',
|
||||
webpage, 'description', default=None) or self._og_search_description(webpage)
|
||||
timestamp = parse_iso8601(
|
||||
self._search_regex(
|
||||
r'<span[^>]+itemprop="(?:datePublished|uploadDate)"[^>]+content="([^"]+)"',
|
||||
webpage, 'upload date', fatal=False))
|
||||
return {
|
||||
webpage, 'upload date', default=None))
|
||||
info = self._search_json_ld(webpage, display_id, default={})
|
||||
return merge_dicts({
|
||||
'_type': 'url_transparent',
|
||||
'url': embed_url,
|
||||
'display_id': display_id,
|
||||
'description': description,
|
||||
'timestamp': timestamp,
|
||||
}
|
||||
}, info)
|
||||
|
||||
|
||||
class NJoyIE(NDRBaseIE):
|
||||
|
|
Loading…
Reference in a new issue