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
|
use html_parser::Dom;
use indoc::indoc;
#[test]
fn it_can_parse_simple() {
let html = indoc!(
r#"
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Document</title>
<style>
body {
background: black;
}
h1 {
color: white;
}
</style>
</head>
<body>
<h1>Hello world</h1>
<!-- There should be more text here -->
<script>
const title = document.querySelector("h1")
title.innerText = "Hello from script"
</script>
</body>
</html>
"#
);
assert!(Dom::parse(html).is_ok());
}
#[test]
fn it_can_parse_spotify() {
let resp = reqwest::blocking::get("https://www.spotify.com/se")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
#[ignore]
#[test]
fn it_can_parse_facebook() {
let resp = reqwest::blocking::get("https://www.facebook.com/")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
#[ignore]
#[test]
fn it_can_parse_amazon() {
let resp = reqwest::blocking::get("https://www.amazon.com/")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
#[ignore]
#[test]
fn it_can_parse_apple() {
let resp = reqwest::blocking::get("https://www.apple.com/")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
#[ignore]
#[test]
fn it_can_parse_nytimes() {
let resp = reqwest::blocking::get("https://www.nytimes.com/")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
#[ignore]
#[test]
fn it_can_parse_wikipedia() {
let resp = reqwest::blocking::get("https://en.wikipedia.org/wiki/Main_Page")
.unwrap()
.text()
.unwrap();
assert!(Dom::parse(&resp).is_ok());
}
|
