mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-11-05 02:32:44 +01:00
[vrtnu] Relax title extraction and extract JSON-LD (closes #17018)
This commit is contained in:
parent
25586c601c
commit
fd62b36680
@ -11,6 +11,7 @@
|
||||
strip_or_none,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
)
|
||||
|
||||
@ -248,9 +249,13 @@ def _real_extract(self, url):
|
||||
|
||||
webpage, urlh = self._download_webpage_handle(url, display_id)
|
||||
|
||||
title = self._html_search_regex(
|
||||
info = self._search_json_ld(webpage, display_id, default={})
|
||||
|
||||
# title is optional here since it may be extracted by extractor
|
||||
# that is delegated from here
|
||||
title = strip_or_none(self._html_search_regex(
|
||||
r'(?ms)<h1 class="content__heading">(.+?)</h1>',
|
||||
webpage, 'title').strip()
|
||||
webpage, 'title', default=None))
|
||||
|
||||
description = self._html_search_regex(
|
||||
r'(?ms)<div class="content__description">(.+?)</div>',
|
||||
@ -295,7 +300,7 @@ def _real_extract(self, url):
|
||||
# the first one
|
||||
video_id = list(video.values())[0].get('videoid')
|
||||
|
||||
return {
|
||||
return merge_dicts(info, {
|
||||
'_type': 'url_transparent',
|
||||
'url': 'https://mediazone.vrt.be/api/v1/vrtvideo/assets/%s' % video_id,
|
||||
'ie_key': CanvasIE.ie_key(),
|
||||
@ -307,4 +312,4 @@ def _real_extract(self, url):
|
||||
'season_number': season_number,
|
||||
'episode_number': episode_number,
|
||||
'release_date': release_date,
|
||||
}
|
||||
})
|
||||
|
Loading…
Reference in New Issue
Block a user