html-to-markdown-rs 3.6.21

High-performance HTML to Markdown converter using the astral-tl parser. Part of the Kreuzberg ecosystem.
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
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132

#![allow(missing_docs)]

use html_to_markdown_rs::ConversionOptions;

fn convert(html: &str, opts: Option<ConversionOptions>) -> html_to_markdown_rs::error::Result<String> {
    html_to_markdown_rs::convert(html, opts).map(|r| r.content.unwrap_or_default())
}

#[test]
fn test_exclude_selectors_drops_matching_elements() {
    let html = r#"<body>
        <div class="cookie-banner">Accept cookies</div>
        <article><p>Main content here.</p></article>
        <div id="ad-container">Buy stuff</div>
    </body>"#;

    let options = ConversionOptions {
        exclude_selectors: vec![".cookie-banner".to_string(), "#ad-container".to_string()],
        ..Default::default()
    };

    let result = convert(html, Some(options)).unwrap();

    assert!(result.contains("Main content"), "Should keep main content");
    assert!(!result.contains("cookie"), "Should drop .cookie-banner element");
    assert!(!result.contains("Buy stuff"), "Should drop #ad-container element");
}

#[test]
fn test_exclude_selectors_drops_nested_content() {
    let html = r#"<body>
        <aside class="sidebar">
            <h2>Related articles</h2>
            <p>Some sidebar content</p>
        </aside>
        <main><p>Primary content.</p></main>
    </body>"#;

    let options = ConversionOptions {
        exclude_selectors: vec![".sidebar".to_string()],
        ..Default::default()
    };

    let result = convert(html, Some(options)).unwrap();

    assert!(result.contains("Primary content"), "Should keep main content");
    assert!(
        !result.contains("Related articles"),
        "Should drop heading inside excluded element"
    );
    assert!(
        !result.contains("sidebar content"),
        "Should drop paragraph inside excluded element"
    );
}

#[test]
fn test_exclude_selectors_empty_list_is_noop() {
    let html = r"<body><p>Hello world</p></body>";

    let options = ConversionOptions {
        exclude_selectors: vec![],
        ..Default::default()
    };

    let result = convert(html, Some(options)).unwrap();
    assert!(
        result.contains("Hello world"),
        "Empty exclude_selectors should not affect output"
    );
}

#[test]
fn test_exclude_selectors_invalid_selector_is_skipped() {
    let html = r"<body><p>Visible text</p></body>";

    // An empty string or garbled selector should not panic or error — just be ignored.
    let options = ConversionOptions {
        exclude_selectors: vec![String::new(), "p".to_string()],
        ..Default::default()
    };

    // Should not return an error; whether the paragraph is excluded depends on the
    // selector, but it must not panic.
    let _ = convert(html, Some(options));
}

#[test]
fn test_exclude_selectors_attribute_selector() {
    let html = r#"<body>
        <div role="complementary">Sidebar</div>
        <p>Main text</p>
    </body>"#;

    let options = ConversionOptions {
        exclude_selectors: vec!["[role='complementary']".to_string()],
        ..Default::default()
    };

    let result = convert(html, Some(options)).unwrap();

    assert!(result.contains("Main text"), "Should keep non-excluded content");
    assert!(
        !result.contains("Sidebar"),
        "Should drop element matching attribute selector"
    );
}

#[test]
fn test_exclude_selectors_plain_text_output() {
    let html = r#"<body>
        <div class="nav">Navigation links</div>
        <p>Article body text.</p>
    </body>"#;

    let options = ConversionOptions {
        exclude_selectors: vec![".nav".to_string()],
        output_format: html_to_markdown_rs::OutputFormat::Plain,
        ..Default::default()
    };

    let result = convert(html, Some(options)).unwrap();

    assert!(
        result.contains("Article body text"),
        "Should keep body text in plain output"
    );
    assert!(
        !result.contains("Navigation links"),
        "Should drop excluded element in plain output"
    );
}