misc-mirrors/article_scraper
1
0
Fork 0
mirror of https://gitlab.com/news-flash/article_scraper.git synced 2025-07-07 16:15:32 +02:00
Code Releases Activity

fix post processing

Browse source
This commit is contained in:
Jan Lukas Gernert 2023-03-04 23:40:01 +01:00
parent 2528aa3e18
commit f5b7ff198a
2 changed files with 32 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

37
src/full_text_parser/mod.rs
View file

@ -587,13 +587,14 @@ impl FullTextParser {
_ = Util::strip_node(context, "//*[contains(@style,'display: none')]");
_ = Self::remove_attribute(context, None, "style");
// strip all comments
// strip all input elements
_ = Util::strip_node(context, "//form");
_ = Util::strip_node(context, "//input");
_ = Util::strip_node(context, "//textarea");
_ = Util::strip_node(context, "//select");
_ = Util::strip_node(context, "//button");
// strip all input elements
// strip all comments
_ = Util::strip_node(context, "//comment()");
// strip all scripts
@ -859,11 +860,12 @@ impl FullTextParser {
Util::mark_data_tables(&context)?;
if let Some(mut root) = document.get_root_element() {
Util::clean_conditionally(&mut root, "form")?;
Util::clean_conditionally(&mut root, "fieldset")?;
Util::clean_conditionally(&mut root, "table")?;
Util::clean_conditionally(&mut root, "ul")?;
Util::clean_conditionally(&mut root, "div")?;
Self::remove_extra_p_and_div(&mut root);
Util::clean_conditionally(&mut root, "fieldset");
Util::clean_conditionally(&mut root, "table");
Util::clean_conditionally(&mut root, "ul");
Util::clean_conditionally(&mut root, "div");
Self::clean_classes(&mut root)?;
Self::simplify_nested_elements(&mut root)?;
@ -872,6 +874,27 @@ impl FullTextParser {
Ok(())
}
fn remove_extra_p_and_div(root: &mut Node) {
let mut node_iter = Some(root.clone());
while let Some(mut node) = node_iter {
let tag_name = node.get_name();
if tag_name == "P" || tag_name == "DIV" {
let img_count = Util::get_elements_by_tag_name(&node, "img").len();
let embed_count = Util::get_elements_by_tag_name(&node, "embed").len();
let object_count = Util::get_elements_by_tag_name(&node, "object").len();
let iframe_count = Util::get_elements_by_tag_name(&node, "iframe").len();
let total_count = img_count + embed_count + object_count + iframe_count;
if total_count == 0 && Util::get_inner_text(&node, false).trim().is_empty() {
node.unlink();
}
}
node_iter = Util::next_node(&node, false);
}
}
fn clean_classes(root: &mut Node) -> Result<(), FullTextParserError> {
let mut node_iter = Some(root.clone());

6
src/util.rs
View file

@ -504,7 +504,7 @@ impl Util {
// Clean an element of all tags of type "tag" if they look fishy.
// "Fishy" is an algorithm based on content length, classnames, link density, number of images & embeds, etc.
pub fn clean_conditionally(root: &mut Node, tag: &str) -> Result<(), FullTextParserError> {
pub fn clean_conditionally(root: &mut Node, tag: &str) {
// Gather counts for other typical elements embedded within.
// Traverse backwards so we can remove nodes at the same time
// without effecting the traversal.
@ -516,11 +516,9 @@ impl Util {
.filter(|node| Self::should_remove(node, tag))
.collect::<Vec<_>>();
for mut node in nodes_to_remove {
for mut node in nodes_to_remove.into_iter().rev() {
node.unlink();
}
Ok(())
}
fn should_remove(node: &Node, tag: &str) -> bool {