mirror of
https://github.com/ytdl-org/youtube-dl.git
synced 2024-11-22 02:01:50 +00:00
New extraction tactic for Kaltura ID using image URL
This commit is contained in:
parent
09476ecdde
commit
5860937e17
1 changed files with 17 additions and 3 deletions
|
@ -12,7 +12,7 @@ class UNOIE(InfoExtractor):
|
|||
_VALID_URL = r'https?://media\.un\.org/(?:\w+/)+(?P<id>k\d[\w]+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://media.un.org/en/asset/k1r/k1r3vy9ikk',
|
||||
# 'md5': 'd91851bf9af73c0ad9b2cdf76c127fbb',
|
||||
'md5': '981c41cb283227f079d1e5059fd0d30c',
|
||||
'info_dict': {
|
||||
'id': '1_r3vy9ikk',
|
||||
'ext': 'mp4',
|
||||
|
@ -23,17 +23,31 @@ class UNOIE(InfoExtractor):
|
|||
'timestamp': 1625216872,
|
||||
'upload_date': '20210702',
|
||||
'uploader_id': 'UNWebTV_New_York',
|
||||
}
|
||||
}, {
|
||||
'url': 'https://media.un.org/en/asset/k12/k12gpkg3qx',
|
||||
'md5': '5978503ca886a922a0f00cf5a7e82395',
|
||||
'info_dict': {
|
||||
'id': '1_vohfjqkj',
|
||||
'ext': 'mp4',
|
||||
'title': '1851st Meeting, 81st session Committee on the Elimination of Discrimination Against Women (CEDAW)',
|
||||
'description': 'Informal meeting with NGOs and human rights institutions - 1851st Meeting, 81st session CEDAW',
|
||||
'thumbnail': 're:https?://.+/thumbnail/.+',
|
||||
'duration': 3502,
|
||||
'timestamp': 1644235332,
|
||||
'upload_date': '20220207',
|
||||
'uploader_id': 'nathalie.minard@un.org',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
video_id = video_id[1:2] + '_' + video_id[2:]
|
||||
webpage = self._download_webpage(url, video_id)
|
||||
partner_id = self._search_regex(r'partnerId\s*:\s*(\d+)\b', webpage, 'Partner ID')
|
||||
video_id = self._search_regex(r'/p/%s(?:/\w+)+?/entry_id/(\w+)/' % (partner_id, ), webpage, 'Kaltura ID')
|
||||
title = (
|
||||
self._html_search_meta(('title', 'og:title'), webpage)
|
||||
or self._html_search_regex(r'<title\b[^>]*>([^<]+)</title\b', webpage, 'title').rsplit('|', 1)[0]).strip()
|
||||
partner_id = self._search_regex(r'partnerId\s*:\s*(\d+)\b', webpage, 'Partner ID')
|
||||
result = self.url_result(
|
||||
'kaltura:%s:%s' % (partner_id, video_id), 'Kaltura',
|
||||
video_title=title,
|
||||
|
|
Loading…
Reference in a new issue