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

use skyscraper::{html, xpath};

#[test]
fn parent_axis_should_select_parent_node() {
    // arrange
    let text = r###"
        <html>
            <body>
            </body>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//body/parent::html").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, "html");
    }
}

#[test]
fn parent_axis_should_select_parents_of_all_selected_nodes() {
    // arrange

    // `not-p` is not selected by the initial `//p` query, so its parent `div` should not be selected by the parent axis.
    let text = r###"
        <html>
            <body>
                <div id="1">
                    <p>1</p>
                </div>
                <div id="2">
                    <p>2</p>
                </div>
                <div>
                    <not-p>3</not-p>
                </div>
            </body>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//p/parent::div").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, "div");
        assert_eq!(element.get_attribute(&document, "id"), Some("1"));
    }

    // 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!(element.get_attribute(&document, "id"), Some("2"));
    }
}

/// The node test (ex. `div`) is applied to the parent of the context node.
#[test]
fn parent_axis_should_respect_node_test() {
    // arrange

    // `not-div` does not match the node test of `div`, so it should not be selected.
    let text = r###"
        <html>
            <body>
                <div id="1">
                    <p>1</p>
                </div>
                <div id="2">
                    <p>2</p>
                </div>
                <not-div>
                    <p>3</p>
                </not-div>
            </body>
        </html>"###;

    let document = html::parse(&text).unwrap();
    let xpath = xpath::parse("//p/parent::div").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, "div");
        assert_eq!(element.get_attribute(&document, "id"), Some("1"));
    }

    // 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!(element.get_attribute(&document, "id"), Some("2"));
    }
}