skyscraper 0.7.0

XPath for HTML web scraping
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
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197

use skyscraper::{
    html,
    xpath::{self, grammar::data_model::XpathItem},
};

// ── parent:: of attribute ────────────────────────────────────────────

/// `@class/..` should return the parent element of the attribute.
#[test]
fn parent_of_attribute_returns_element() {
    let text = r#"<html><body><div class="main">hello</div></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//div/@class/..").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 1);
    let node = items[0].extract_as_node();
    assert_eq!(node.extract_as_element_node().name, "div");
}

// ── ancestor:: axis ──────────────────────────────────────────────────

/// `ancestor::*` returns all ancestors of the context node.
#[test]
fn ancestor_returns_all_ancestors() {
    let text = r#"<html><body><div><p>hello</p></div></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//p/ancestor::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    let names: Vec<&str> = items
        .iter()
        .filter_map(|i| match i {
            XpathItem::Node(n) => n.as_element_node().ok().map(|e| e.name.as_str()),
            _ => None,
        })
        .collect();
    assert!(names.contains(&"div"));
    assert!(names.contains(&"body"));
    assert!(names.contains(&"html"));
}

/// `ancestor::div` filters ancestors by name.
#[test]
fn ancestor_with_name_test() {
    let text = r#"<html><body><div><p>hello</p></div></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//p/ancestor::div").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 1);
    let node = items[0].extract_as_node();
    assert_eq!(node.extract_as_element_node().name, "div");
}

/// Root element has no ancestors (except the document node).
#[test]
fn ancestor_of_root_element() {
    let text = r#"<html><body></body></html>"#;

    let document = html::parse(text).unwrap();
    // html's ancestors that are elements: none (document node is not an element)
    let xpath = xpath::parse("/html/ancestor::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 0);
}

// ── ancestor-or-self:: axis ──────────────────────────────────────────

/// `ancestor-or-self::*` includes the context node itself.
#[test]
fn ancestor_or_self_includes_self() {
    let text = r#"<html><body><div><p>hello</p></div></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//p/ancestor-or-self::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    let names: Vec<&str> = items
        .iter()
        .filter_map(|i| match i {
            XpathItem::Node(n) => n.as_element_node().ok().map(|e| e.name.as_str()),
            _ => None,
        })
        .collect();
    assert!(names.contains(&"p"));
    assert!(names.contains(&"div"));
    assert!(names.contains(&"body"));
    assert!(names.contains(&"html"));
}

/// `ancestor-or-self::p` matches the context node itself.
#[test]
fn ancestor_or_self_matches_self_name() {
    let text = r#"<html><body><p>hello</p></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//p/ancestor-or-self::p").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 1);
    let node = items[0].extract_as_node();
    assert_eq!(node.extract_as_element_node().name, "p");
}

// ── preceding-sibling:: axis ─────────────────────────────────────────

/// `preceding-sibling::*` returns all preceding siblings.
#[test]
fn preceding_sibling_returns_all_preceding() {
    let text = r#"<html><body><a>1</a><b>2</b><c>3</c><d>4</d></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//c/preceding-sibling::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    let names: Vec<&str> = items
        .iter()
        .map(|i| i.extract_as_node().extract_as_element_node().name.as_str())
        .collect();
    assert!(names.contains(&"a"));
    assert!(names.contains(&"b"));
    assert_eq!(items.len(), 2);
}

/// `preceding-sibling::` with name test filters.
#[test]
fn preceding_sibling_with_name_test() {
    let text = r#"<html><body><a>1</a><b>2</b><a>3</a></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//a[2]/preceding-sibling::b").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 1);
    let node = items[0].extract_as_node();
    assert_eq!(node.extract_as_element_node().name, "b");
}

/// First element has no preceding siblings.
#[test]
fn preceding_sibling_of_first_is_empty() {
    let text = r#"<html><body><a>1</a><b>2</b></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//a/preceding-sibling::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 0);
}

// ── preceding:: axis ─────────────────────────────────────────────────

/// `preceding::*` returns all nodes before the context node (excluding ancestors).
#[test]
fn preceding_axis_returns_all_preceding_nodes() {
    let text = r#"<html><body><div><a>1</a></div><p>2</p><span>3</span></body></html>"#;

    let document = html::parse(text).unwrap();
    // preceding:: of <span> should include <p>, <a>, <div> and their text nodes.
    let xpath = xpath::parse("//span/preceding::*").unwrap();

    let items = xpath.apply(&document).unwrap();
    let names: Vec<&str> = items
        .iter()
        .filter_map(|i| match i {
            XpathItem::Node(n) => n.as_element_node().ok().map(|e| e.name.as_str()),
            _ => None,
        })
        .collect();
    assert!(names.contains(&"div"));
    assert!(names.contains(&"a"));
    assert!(names.contains(&"p"));
    // <span> and ancestors (body, html) should not be in preceding.
    assert!(!names.contains(&"span"));
    assert!(!names.contains(&"body"));
    assert!(!names.contains(&"html"));
}

/// `preceding::` includes descendants of preceding siblings.
#[test]
fn preceding_axis_includes_descendants() {
    let text =
        r#"<html><body><div><p>inner</p></div><a>last</a></body></html>"#;

    let document = html::parse(text).unwrap();
    let xpath = xpath::parse("//a/preceding::p").unwrap();

    let items = xpath.apply(&document).unwrap();
    assert_eq!(items.len(), 1);
    let node = items[0].extract_as_node();
    assert_eq!(node.extract_as_element_node().name, "p");
}