browser_oxide 0.1.3

Stealth headless browser engine in Rust: real HTML/CSS/DOM/JS, V8 via deno_core, own BoringSSL TLS/JA4 fingerprint, no Chromium, no CDP — for anti-bot web scraping, archival, and AI agents
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
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162

//! html5ever integration producing a browser_oxide DOM.
//!
//! MIT/Apache-2.0 licensed. Part of the browser_oxide project.

mod tree_sink;

use crate::dom::Dom;
use html5ever::parse_document;
use html5ever::tendril::TendrilSink;
pub use markup5ever;
use tree_sink::DomTreeSink;

/// Parse an HTML document string into a DOM tree.
pub fn parse_html(html: &str) -> Dom {
    let sink = DomTreeSink::new();
    parse_document(sink, Default::default())
        .from_utf8()
        .one(html.as_bytes())
}

#[cfg(test)]
mod tests {
    use super::*;
    use crate::css_selectors::Element as _;
    use crate::dom::node::NodeId;
    use crate::dom::DomElement;

    #[test]
    fn parse_basic_html() {
        let dom = parse_html("<html><body><h1>Hello</h1></body></html>");
        let children = dom.children(NodeId::DOCUMENT);
        assert!(!children.is_empty(), "Document should have children");
    }

    #[test]
    fn parse_has_html_element() {
        let dom = parse_html("<html><head></head><body><p>Test</p></body></html>");
        let doc_children = dom.child_elements(NodeId::DOCUMENT);
        assert!(!doc_children.is_empty());

        let html_el = DomElement::new(&dom, doc_children[0]).unwrap();
        assert_eq!(html_el.local_name(), "html");
    }

    #[test]
    fn parse_text_content() {
        let dom = parse_html("<html><body><p>Hello world</p></body></html>");
        // Navigate: doc → html → body → p
        let html = dom.child_elements(NodeId::DOCUMENT)[0];
        let body_candidates = dom.child_elements(html);
        // html has head and body
        let body = body_candidates
            .iter()
            .find(|&&id| {
                dom.get(id)
                    .and_then(|n| n.as_element())
                    .is_some_and(|e| e.name.local == "body")
            })
            .copied()
            .unwrap();
        let p = dom.child_elements(body)[0];
        assert_eq!(dom.text_content(p), "Hello world");
    }

    #[test]
    fn parse_attributes() {
        let dom = parse_html("<div id=\"main\" class=\"container\">test</div>");
        // Find the div
        let html = dom.child_elements(NodeId::DOCUMENT)[0];
        let body = dom
            .child_elements(html)
            .into_iter()
            .find(|&id| {
                dom.get(id)
                    .and_then(|n| n.as_element())
                    .is_some_and(|e| e.name.local == "body")
            })
            .unwrap();
        let div = dom.child_elements(body)[0];
        let el = DomElement::new(&dom, div).unwrap();

        assert_eq!(el.id(), Some("main"));
        assert!(el.has_class("container"));
    }

    #[test]
    fn parse_nested_structure() {
        let dom = parse_html("<html><body><div><span>a</span><span>b</span></div></body></html>");
        let html = dom.child_elements(NodeId::DOCUMENT)[0];
        let body = dom
            .child_elements(html)
            .into_iter()
            .find(|&id| {
                dom.get(id)
                    .and_then(|n| n.as_element())
                    .is_some_and(|e| e.name.local == "body")
            })
            .unwrap();

        let body_children = dom.child_elements(body);
        assert!(!body_children.is_empty());

        let div = body_children
            .iter()
            .find(|&&id| {
                dom.get(id)
                    .and_then(|n| n.as_element())
                    .is_some_and(|e| e.name.local == "div")
            })
            .copied()
            .unwrap();

        // List all children of div (including text nodes)
        let all_children = dom.children(div);
        let spans = dom.child_elements(div);
        // html5ever may have different parsing; just verify we got spans
        assert!(
            !spans.is_empty(),
            "expected at least 1 span, got {}. All children: {}",
            spans.len(),
            all_children.len()
        );
        // Verify text content of the div
        assert_eq!(dom.text_content(div), "ab");
    }

    #[test]
    fn parse_doctype_html() {
        let html = "<!DOCTYPE html>\n<html>\n  <head>\n  </head>\n  <body>\n      <h1>Herman Melville</h1>\n      <div>\n        <p>Some text here.</p>\n      </div>\n  </body>\n</html>";
        let dom = parse_html(html);
        let children = dom.children(NodeId::DOCUMENT);
        assert!(
            !children.is_empty(),
            "Document should have children after doctype parse"
        );
    }

    #[test]
    fn selector_matching_on_parsed_html() {
        let dom = parse_html(
            "<html><body><div id=\"main\" class=\"content\"><p>Hello</p></div></body></html>",
        );
        let html = dom.child_elements(NodeId::DOCUMENT)[0];
        let body = dom
            .child_elements(html)
            .into_iter()
            .find(|&id| {
                dom.get(id)
                    .and_then(|n| n.as_element())
                    .is_some_and(|e| e.name.local == "body")
            })
            .unwrap();
        let div = dom.child_elements(body)[0];
        let div_el = DomElement::new(&dom, div).unwrap();

        let sel = crate::css_selectors::parse_selector_list("div#main.content").unwrap();
        assert!(crate::css_selectors::matches_selector(&div_el, &sel[0]));

        let sel2 = crate::css_selectors::parse_selector_list("body > div").unwrap();
        assert!(crate::css_selectors::matches_selector(&div_el, &sel2[0]));
    }
}