maman 0.13.1

Rust Web Crawler
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

extern crate mockito;
extern crate sidekiq;
extern crate url;
#[macro_use]
extern crate maman;

use maman::{Page, Spider};
use sidekiq::create_redis_pool;

use std::collections::BTreeMap;
use std::env;
use std::str::FromStr;

use url::Url;

fn visit_page(input: &str) -> Spider {
    env::set_var("MAMAN_ENV", "test");
    let url = Url::parse("https://example.net/").unwrap();
    let redis_pool = create_redis_pool().unwrap();
    let mut spider = Spider::new(redis_pool, url.clone(), 0, Vec::new());
    let page = Page::new(
        url,
        input.to_string(),
        BTreeMap::new(),
        "200 OK".to_string(),
    );
    let tok = Spider::read_page(page, input);
    spider.visit_page(tok.sink);
    spider
}

#[test]
fn test_ignore_initial_url_link() {
    let input = "<html><body><a href='/' /><a href='/new' /></html>";
    let spider = visit_page(input);
    assert_eq!(spider.visited_urls.len(), 1);
    assert_eq!(spider.unvisited_urls.len(), 1);
}

#[test]
fn test_ignore_fragment_link() {
    let input = "<html><body><a href='#' /><a href='/new' /></html>";
    let spider = visit_page(input);
    assert_eq!(spider.visited_urls.len(), 1);
    assert_eq!(spider.unvisited_urls.len(), 1);
}

#[test]
fn test_ignore_mailto_link() {
    let input = "<html><body><a href='mailto:example@example.net' /><a href='/new' /></html>";
    let spider = visit_page(input);
    assert_eq!(spider.visited_urls.len(), 1);
    assert_eq!(spider.unvisited_urls.len(), 1);
}

#[test]
fn test_new_with_fragment_link() {
    let input = "<html><body><a href='/todo#new' /><a href='/new' /></html>";
    let spider = visit_page(input);
    assert_eq!(spider.visited_urls.len(), 1);
    assert_eq!(spider.unvisited_urls.len(), 2);
}

#[test]
fn test_other_domain_link() {
    let input = "<html><body><a href='https://github.com/' /></html>";
    let spider = visit_page(input);
    assert_eq!(spider.visited_urls.len(), 1);
    assert_eq!(spider.unvisited_urls.len(), 0);
}

#[test]
fn test_json_job_format() {
    env::set_var("MAMAN_ENV", "test");
    let input = "<html><body><a href='/todo#new' /><a href='/new' /></html>";
    let url = Url::parse("http://example.net/").unwrap();
    let mut headers = BTreeMap::new();
    headers.insert("content-type".to_string(), "text/html".to_string());
    let page = Page::new(
        url,
        input.to_string(),
        headers.clone(),
        "200 OK".to_string(),
    );
    let page_object = page.as_object();
    let job = page.to_job();
    assert_eq!(job.class, maman_name!());
    assert_eq!(job.retry, 25);
    assert_eq!(job.queue, maman_name!().to_string().to_lowercase());
    assert_eq!(job.args, vec![page_object]);
}

#[test]
fn test_integration() {
    use mockito::mock;
    let _r = mock("GET", "/robots.txt")
        .with_status(200)
        .with_header("content-type", "text/plain")
        .with_body("User-agent: *\nAllow: /")
        .create();
    let _m1 = mock("GET", "/")
        .with_status(200)
        .with_header("content-type", "text/html")
        .with_body("<html><a href='/hello'>hello</a>")
        .create();
    let _m2 = mock("GET", "/hello")
        .with_status(200)
        .with_header("content-type", "text/html")
        .with_body("<html><a href='/world'>world</a></html>")
        .create();
    let _m3 = mock("GET", "/world")
        .with_status(200)
        .with_header("content-type", "text/html")
        .with_body("<html>!</html>")
        .create();
    let redis_pool = create_redis_pool().unwrap();
    let url = Url::parse(mockito::SERVER_URL).unwrap();
    let mut spider = Spider::new(redis_pool, url, 0, Vec::new());
    spider.crawl();
    assert_eq!(spider.visited_urls.len(), 3);
}

#[test]
fn test_integration_filter() {
    use mockito::mock;
    let _r = mock("GET", "/robots.txt")
        .with_status(200)
        .with_header("content-type", "text/plain")
        .with_body("User-agent: *\nAllow: /")
        .create();
    let _m1 = mock("GET", "/")
        .with_status(200)
        .with_header("content-type", "text/html; charset=utf-8")
        .with_body("<html><a href='/hello'>hello</a>")
        .create();
    let _m2 = mock("GET", "/hello")
        .with_status(200)
        .with_header("content-type", "text/html; charset=utf-8")
        .with_body("<html><a href='/world'>world</a></html>")
        .create();
    let _m3 = mock("GET", "/world")
        .with_status(200)
        .with_header("content-type", "text/html; charset=utf-8")
        .with_body("<html>!</html>")
        .create();
    let redis_pool = create_redis_pool().unwrap();
    let url = Url::parse(mockito::SERVER_URL).unwrap();
    let mut spider = Spider::new(
        redis_pool,
        url,
        0,
        vec![mime::Mime::from_str("text/html").unwrap()],
    );
    spider.crawl();
    assert_eq!(spider.visited_urls.len(), 3);
}