[ie/nitter] Fix title extraction fallback (#8102)

Closes #7575
Authored by: ApoorvShah111
This commit is contained in:
ApoorvShah111 2023-09-17 02:31:26 +05:30 committed by GitHub
parent 9d376c4dae
commit a83da3717d
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -265,6 +265,26 @@ class NitterIE(InfoExtractor):
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
} }
}, { # no OpenGraph title
'url': f'https://{current_instance}/LocalBateman/status/1678455464038735895#m',
'info_dict': {
'id': '1678455464038735895',
'ext': 'mp4',
'title': 'Your Typical Local Man - Local man, what did Romanians ever do to you?',
'description': 'Local man, what did Romanians ever do to you?',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'Your Typical Local Man',
'uploader_id': 'LocalBateman',
'uploader_url': f'https://{current_instance}/LocalBateman',
'upload_date': '20230710',
'timestamp': 1689009900,
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
},
'expected_warnings': ['Ignoring subtitle tracks found in the HLS manifest'],
'params': {'skip_download': 'm3u8'},
} }
] ]
@ -292,7 +312,7 @@ def _real_extract(self, url):
'ext': ext 'ext': ext
}] }]
title = description = self._og_search_description(full_webpage) or self._html_search_regex( title = description = self._og_search_description(full_webpage, default=None) or self._html_search_regex(
r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title', fatal=False) r'<div class="tweet-content[^>]+>([^<]+)</div>', webpage, 'title', fatal=False)
uploader_id = self._html_search_regex( uploader_id = self._html_search_regex(