poc/crieur
1
0
Fork 0
Code Issues 26 Pull Requests Projects 1 Releases 1 Wiki Activity

feat: allow to inject styles

Browse Source
This commit is contained in:
koalp 2021-05-19 04:09:44 +02:00
parent 6e091a32fc
commit 40ebc1ddea
Signed by: koalp
GPG Key ID: 35B21047DEB09A81
2 changed files with 63 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
crieur-retrieve/src/newspapers/courrier_international.rs
View File

@ -81,16 +81,9 @@ impl Newspaper for CourrierInternational {
None => bail!("404 not found"),
};
// TODO: Move to const
let elements_to_remove = [
// navigation elements
"#entete.connecte",
];
let single_page_html = tools::self_contained_html::Config {
downloader: Some(&downloader),
base_url: Some(&url),
elements_to_remove: &elements_to_remove,
..Default::default()
}
.run(&html)

63
crieur-retrieve/src/tools/self_contained_html.rs
View File

@ -169,6 +169,15 @@ where
for element in self.elements_to_remove {
document.select(element.as_ref()).remove();
}
// ---- Add additional styles ----
//
for style in self.styles_to_add {
document
.select("head")
.append_html(format!("\n<style>{}</style>\n", style.as_ref()));
}
String::from(document.html())
};
@ -444,4 +453,58 @@ mod tests {
);
Ok(())
}
#[tokio::test]
async fn add_style() -> Result<()> {
let html = indoc! {"
<html>
<head>
<meta charset=\"UTF-8\">
</head>
<body>
The body
</body>
</html>
"};
let wanted_html = indoc! {"
<html><head>
<meta charset=\"UTF-8\">
<style>
body {
margin: 3em;
}
</style>
</head>
<body>
The body
</body></html>
"};
let style_to_add = indoc! {"
body {
margin: 3em;
}
"};
let base_url = Url::parse("http://example.com")?;
let downloader = DummyDownloader {};
let mut minifier = HTMLMinifier::new();
minifier.digest(wanted_html)?;
let minified = String::from_utf8(minifier.get_html().into())?;
assert_eq!(
Config {
downloader: Some(&downloader),
base_url: Some(&base_url),
styles_to_add: &[style_to_add],
..Default::default()
}
.run(html)
.await,
minified
);
Ok(())
}
}