[simpcity] improve post content extraction (#8214)
use a better end marker to not stop prematurely when a quoted post is present
This commit is contained in:
@@ -92,7 +92,8 @@ class SimpcityExtractor(Extractor):
|
||||
"id": extr('data-content="post-', '"'),
|
||||
"author_url": extr('itemprop="url" content="', '"'),
|
||||
"date": text.parse_datetime(extr('datetime="', '"')),
|
||||
"content": extr('<div itemprop="text">', "\t\t</div>").strip(),
|
||||
"content": extr('<div itemprop="text">',
|
||||
'<div class="js-selectToQuote').strip(),
|
||||
}
|
||||
|
||||
url_a = post["author_url"]
|
||||
|
||||
Reference in New Issue
Block a user