lithtml 0.8.0

A lightweight and fast HTML parser for Rust, designed to handle both full HTML documents and fragments efficiently.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62

use indoc::indoc;
use insta::assert_json_snapshot;
use lithtml::{Dom, Result};

#[test]
fn it_can_parse_document_with_just_text() -> Result<()> {
    let html = "hello world";
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_document_with_text_and_line_breaks() -> Result<()> {
    let html = indoc!(
        r"
        hello world
        here's another line for you!
        The end
    "
    );
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_document_with_multiple_text_elements() -> Result<()> {
    let html = indoc!(
        r"
        hello world
        here's another line for you!
        <div/>
        The end
    "
    );
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_text_with_chevron() -> Result<()> {
    let html = indoc!(r"hello <> world");
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}

#[test]
fn it_can_parse_text_in_paragraph_with_weird_formatting() -> Result<()> {
    let html = indoc!(
        r"
        <p>
            This is a <b>para</b>gra<b>ph</b> with some<i> weird </i> formatting.
        </p>
    "
    );
    let dom = Dom::parse(html)?;
    assert_json_snapshot!(dom);
    Ok(())
}