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 cleaning of empty p/div-tags

Browse source
This commit is contained in:
Jan Lukas Gernert 2023-03-12 12:20:50 +01:00
parent d9c92ea42c
commit 779afd6245
2 changed files with 5 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

1
resources/tests/readability/cnn/expected.html
View file

@ -1,7 +1,6 @@
<article><div id="readability-page-1"> <article><div id="readability-page-1">
<h2>The U.S. has long been heralded as a land of opportunity -- a place where anyone can succeed regardless of the economic class they were born into.</h2> <h2>The U.S. has long been heralded as a land of opportunity -- a place where anyone can succeed regardless of the economic class they were born into.</h2>
<p> But a new report released on Monday by <a href="http://web.stanford.edu/group/scspi-dev/cgi-bin/" target="_blank">Stanford University's Center on Poverty and Inequality</a> calls that into question. </p> <p> But a new report released on Monday by <a href="http://web.stanford.edu/group/scspi-dev/cgi-bin/" target="_blank">Stanford University's Center on Poverty and Inequality</a> calls that into question. </p>
<P id="ie_column"></P>
<p> The report assessed poverty levels, income and wealth inequality, economic mobility and unemployment levels among 10 wealthy countries with social welfare programs. </p> <p> The report assessed poverty levels, income and wealth inequality, economic mobility and unemployment levels among 10 wealthy countries with social welfare programs. </p>
<div id="smartassetcontainer"><div><div><div id="smartasset-article"><div><p> <div id="smartassetcontainer"><div><div><div id="smartasset-article"><div><p>
Powered by SmartAsset.com Powered by SmartAsset.com

8
src/full_text_parser/mod.rs
View file

@ -848,8 +848,6 @@ impl FullTextParser {
Util::mark_data_tables(&context)?; Util::mark_data_tables(&context)?;
if let Some(mut root) = document.get_root_element() { if let Some(mut root) = document.get_root_element() {
Self::remove_extra_p_and_div(&mut root);
Util::clean_conditionally(&mut root, "fieldset"); Util::clean_conditionally(&mut root, "fieldset");
Util::clean_conditionally(&mut root, "table"); Util::clean_conditionally(&mut root, "table");
Util::clean_conditionally(&mut root, "ul"); Util::clean_conditionally(&mut root, "ul");
@ -857,6 +855,8 @@ impl FullTextParser {
Self::clean_attributes(&mut root)?; Self::clean_attributes(&mut root)?;
Self::simplify_nested_elements(&mut root)?; Self::simplify_nested_elements(&mut root)?;
Self::remove_extra_p_and_div(&mut root);
} }
Ok(()) Ok(())
@ -866,7 +866,7 @@ impl FullTextParser {
let mut node_iter = Some(root.clone()); let mut node_iter = Some(root.clone());
while let Some(mut node) = node_iter { while let Some(mut node) = node_iter {
let tag_name = node.get_name(); let tag_name = node.get_name().to_uppercase();
if tag_name == "P" || tag_name == "DIV" { if tag_name == "P" || tag_name == "DIV" {
let img_count = Util::get_elements_by_tag_name(&node, "img").len(); 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 embed_count = Util::get_elements_by_tag_name(&node, "embed").len();
@ -875,7 +875,9 @@ impl FullTextParser {
let total_count = img_count + embed_count + object_count + iframe_count; let total_count = img_count + embed_count + object_count + iframe_count;
if total_count == 0 && Util::get_inner_text(&node, false).trim().is_empty() { if total_count == 0 && Util::get_inner_text(&node, false).trim().is_empty() {
node_iter = Util::next_node(&node, false);
node.unlink(); node.unlink();
continue;
} }
} }