Crate soup

Expand description

Inspired by the Python library “BeautifulSoup,” soup is a layer on top of html5ever that aims to provide a slightly different API for querying & manipulating HTML

Examples (inspired by bs4’s docs)


const THREE_SISTERS: &'static str = r#"
<html><head><title>The Dormouse's story</title></head>
<body>
<p class="title"><b>The Dormouse's story</b></p>

<p class="story">Once upon a time there were three little sisters; and their names were
<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>,
<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and
<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>;
and they lived at the bottom of a well.</p>

<p class="story">...</p>
"#;

let soup = Soup::new(THREE_SISTERS);


let title = soup.tag("title").find().unwrap();
assert_eq!(title.display(), "<title>The Dormouse's story</title>");
assert_eq!(title.name(), "title");
assert_eq!(title.text(), Some("The Dormouse's story".to_string()));

let p = soup.tag("p").find().unwrap();
assert_eq!(p.display(), r#"<p class="title"><b>The Dormouse's story</b></p>"#);
assert_eq!(p.get("class"), Some("title".to_string()));
let a = soup.tag("a").find().unwrap();
assert_eq!(a.display(), r#"<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>"#);
let a_s = soup.tag("a").find_all().collect::<Vec<_>>();
assert_eq!(
    a_s.iter().map(|a| a.display()).collect::<Vec<_>>().join("\n"),
    r#"<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>
<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>
<a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>"#
);


let expected = [
    "http://example.com/elsie",
    "http://example.com/lacie",
    "http://example.com/tillie",
];

for (i, link) in soup.tag("a").find_all().enumerate() {
    let href = link.get("href").unwrap();
    assert_eq!(href, expected[i].to_string());
}


let text = soup.text().unwrap();
assert_eq!(text,
r#"The Dormouse's story

The Dormouse's story

Once upon a time there were three little sisters; and their names were
Elsie,
Lacie and
Tillie;
and they lived at the bottom of a well.

...
"#);

Modules

prelude

This module exports all the important types & traits to use soup effectively

Structs

QueryBuilder

Construct a query to apply to an HTML tree

Soup

Parses HTML & provides methods to query & manipulate the document

Traits

NodeExt

Adds some convenience methods to the html5ever::rcdom::Node type