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

add new test

Browse source
This commit is contained in:
Jan Lukas Gernert 2023-03-12 11:53:42 +01:00
parent c654f63319
commit fa63d297f8
3 changed files with 60 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

21
resources/tests/readability/comment-inside-script-parsing/expected.html Normal file
View file

@ -0,0 +1,21 @@
<article><DIV id="readability-page-1">
<div>
<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua.</p>
<p>Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.</p>
<p>Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
</div>
<div>
<p>Tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.</p>
<p>Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur.
Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
</div>
</DIV></article>

34
resources/tests/readability/comment-inside-script-parsing/source.html Normal file
View file

@ -0,0 +1,34 @@
<html>
<head><title>Test script parsing</title></head>
<body>
<script>
<!--
Silly test
<script src="foo.js"></script>
-->
</script>
<article>
<h1>Lorem</h1>
<div>
<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
tempor incididunt ut labore et dolore magna aliqua.</p>
<p>Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.</p>
<p>Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
</div>
<h2>Foo</h2>
<div>
<p>Tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat.</p>
<p>Duis aute irure dolor in reprehenderit in voluptate velit esse
cillum dolore eu fugiat nulla pariatur.
Excepteur sint occaecat cupidatat non
proident, sunt in culpa qui officia deserunt mollit anim id est laborum.</p>
</div>
</article>
</body>
</html>

5
src/full_text_parser/readability/tests.rs
View file

@ -146,6 +146,11 @@ async fn cnn() {
run_test("cnn").await run_test("cnn").await
} }
#[tokio::test]
async fn comment_inside_script_parsing() {
run_test("comment-inside-script-parsing").await
}
#[tokio::test] #[tokio::test]
async fn webmd_1() { async fn webmd_1() {
run_test("webmd-1").await run_test("webmd-1").await