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 embedded videos test

Browse source
This commit is contained in:
Jan Lukas Gernert 2023-03-19 15:39:08 +01:00
parent 8309e227eb
commit 32dd074b6d
3 changed files with 69 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

21
resources/tests/readability/embedded-videos/expected.html Normal file
View file

@ -0,0 +1,21 @@
<article><DIV id="readability-page-1"><article><h2>Lorem</h2>
<p>Lorem ipsum dolor sit amet, consectetur adipisicing elit, sed do eiusmod
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. 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>
<h2>Videos</h2>
<p>At root</p>
<iframe width="100%" height="100%" src="https://www.youtube.com/embed/LtOGa5M8AuU" frameborder="0" allowfullscreen=""></iframe><iframe width="560" height="315" src="https://www.youtube-nocookie.com/embed/LtOGa5M8AuU" frameborder="0" allowfullscreen=""></iframe><iframe src="https://player.vimeo.com/video/32246206?color=ffffff+title=0+byline=0+portrait=0" width="500" height="281" frameborder="0" webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe><p>In a paragraph</p>
<p><iframe width="560" height="315" src="https://www.youtube-nocookie.com/embed/LtOGa5M8AuU" frameborder="0" allowfullscreen=""></iframe></p>
<p>In a div</p>
<div><iframe width="100%" height="100%" src="https://www.youtube.com/embed/LtOGa5M8AuU" frameborder="0" allowfullscreen=""></iframe></div>
<h2>Foo</h2>
<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. 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></article></DIV></article>

43
resources/tests/readability/embedded-videos/source.html Normal file
View file

@ -0,0 +1,43 @@
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8"/>
<title>Embedded videos test</title>
</head>
<body>
<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. Ut enim ad minim veniam,
quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo
consequat. 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>Videos</h2>
<p>At root</p>
<iframe width="560" height="315" src="https://www.youtube.com/embed/LtOGa5M8AuU"
frameborder="0" allowfullscreen=""></iframe>
<iframe width="560" height="315" src="https://www.youtube-nocookie.com/embed/LtOGa5M8AuU"
frameborder="0" allowfullscreen=""></iframe>
<iframe src="https://player.vimeo.com/video/32246206?color=ffffff+title=0+byline=0+portrait=0"
width="500" height="281" frameborder="0"
webkitallowfullscreen="" mozallowfullscreen="" allowfullscreen=""></iframe>
<p>In a paragraph</p>
<p><iframe width="560" height="315" src="https://www.youtube-nocookie.com/embed/LtOGa5M8AuU"
frameborder="0" allowfullscreen=""></iframe></p>
<p>In a div</p>
<div><iframe width="560" height="315" src="https://www.youtube.com/embed/LtOGa5M8AuU"
frameborder="0" allowfullscreen=""></iframe></div>
<h2>Foo</h2>
<div>
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. 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.
</div>
</article>
</body>
</html>

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

@ -186,6 +186,11 @@ async fn ehow_2() {
run_test("ehow-2").await
}
#[tokio::test]
async fn embedded_videos() {
run_test("embedded-videos").await
}
#[tokio::test]
async fn webmd_1() {
run_test("webmd-1").await