mirror of
https://gitlab.com/news-flash/article_scraper.git
synced 2025-07-08 16:40:00 +02:00
move conditional cleaning right after parsing & port attribute cleaning form readability
This commit is contained in:
parent
47eed3a94f
commit
11e08ae505
10 changed files with 943 additions and 104 deletions
|
@ -497,6 +497,11 @@ impl Readability {
|
|||
}
|
||||
}
|
||||
|
||||
crate::FullTextParser::post_process_content(
|
||||
&mut article_content,
|
||||
state.clean_conditionally,
|
||||
)?;
|
||||
|
||||
if needed_to_create_top_candidate {
|
||||
// We already created a fake div thing, and there wouldn't have been any siblings left
|
||||
// for the previous loop, so there's no point trying to create a new div, and then
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue