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

use skyscraper::{
    html::{self, trim_internal_whitespace},
    xpath,
};

#[test]
fn class_equals_predicate_should_select_nodes_with_that_match() {
    // arrange
    let text = r###"
        <html>
            <div>
                bad
            </div>
            <div class="here">
                good
            </div>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("/html/div[@class='here']").unwrap();

    // act
    let nodes = xpath.apply(&document).unwrap();

    // assert
    assert_eq!(nodes.len(), 1);
    let mut nodes = nodes.into_iter();

    // assert node
    {
        let tree_node = nodes.next().unwrap().extract_into_node();

        let element = tree_node.extract_as_element_node();
        assert_eq!(element.name, "div");

        assert_eq!(
            trim_internal_whitespace(&tree_node.text(&document).unwrap()),
            "good"
        );
    }
}

#[test]
fn predicate_on_double_leading_slash_should_select_nodes_with_that_match() {
    // arrange
    let text = r###"
        <html>
            <div>
                bad
            </div>
            <div class="here">
                good
            </div>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//div[@class='here']").unwrap();

    // act
    let nodes = xpath.apply(&document).unwrap();

    // assert
    assert_eq!(nodes.len(), 1);
    let mut nodes = nodes.into_iter();

    // assert node
    {
        let tree_node = nodes.next().unwrap().extract_into_node();

        let element = tree_node.extract_as_element_node();
        assert_eq!(element.name, "div");

        assert_eq!(
            trim_internal_whitespace(&tree_node.text(&document).unwrap()),
            "good"
        );
    }
}

#[test]
fn index_should_select_indexed_child_for_all_selected_parents() {
    // arrange
    let text = r###"
        <html>
            <div>
                <p>1</p>
                <p>2</p>
                <p>3</p>
            </div>
            <div>
                <p>4</p>
                <p>5</p>
                <p>6</p>
            </div>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//div/p[2]").unwrap();

    // act
    let nodes = xpath.apply(&document).unwrap();

    // assert
    assert_eq!(nodes.len(), 2);
    let mut nodes = nodes.into_iter();

    // assert node
    {
        let tree_node = nodes.next().unwrap().extract_into_node();

        let element = tree_node.extract_as_element_node();
        assert_eq!(element.name, "p");

        assert_eq!(
            trim_internal_whitespace(&tree_node.text(&document).unwrap()),
            "2"
        );
    }

    // assert node
    {
        let tree_node = nodes.next().unwrap().extract_into_node();

        let element = tree_node.extract_as_element_node();
        assert_eq!(element.name, "p");

        assert_eq!(
            trim_internal_whitespace(&tree_node.text(&document).unwrap()),
            "5"
        );
    }
}

/// The index being out of bounds for one parent should not affect the selection of the indexed node for some other parent.
#[test]
fn index_out_of_bounds_should_select_nothing_for_parent() {
    // arrange
    let text = r###"
        <html>
            <div>
                <p>1</p>
                <p>2</p>
                <p>3</p>
            </div>
            <div>
                <p>4</p>
                <p>5</p>
            </div>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//div/p[2]").unwrap();

    // act
    let nodes = xpath.apply(&document).unwrap();

    // assert
    assert_eq!(nodes.len(), 2);
    let mut nodes = nodes.into_iter();

    // assert node
    {
        let tree_node = nodes.next().unwrap().extract_into_node();

        let element = tree_node.extract_as_element_node();
        assert_eq!(element.name, "p");

        assert_eq!(
            trim_internal_whitespace(&tree_node.text(&document).unwrap()),
            "2"
        );
    }
}