kumo 0.2.7

An async web crawling framework for Rust — Scrapy for Rust
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

use kumo::{
    CrawlRequest,
    engine::CrawlEngine,
    error::KumoError,
    extract::Response,
    fetch::MockFetcher,
    spider::{Output, Spider},
    stats::{CrawlReport, CrawlStats},
    store::StdoutStore,
};

#[test]
fn crawl_report_exposes_scheduler_counters() {
    let mut stats = CrawlStats::default();
    stats.record_scheduled("example.com");
    stats.record_deduped("example.com");
    stats.record_retry("example.com");
    stats.record_robots_blocked("example.com");

    let report = CrawlReport::from(stats);

    assert_eq!(report.scheduled, 1);
    assert_eq!(report.deduped, 1);
    assert_eq!(report.retries, 1);
    assert_eq!(report.robots_blocked, 1);
    assert_eq!(report.domains["example.com"].scheduled, 1);
    assert_eq!(report.domains["example.com"].deduped, 1);
    assert_eq!(report.domains["example.com"].retries, 1);
    assert_eq!(report.domains["example.com"].robots_blocked, 1);
}

struct DuplicateSpider {
    start: String,
    target: String,
}

struct PanicSpider {
    start: String,
    name: &'static str,
}

#[async_trait::async_trait]
impl Spider for DuplicateSpider {
    type Item = serde_json::Value;

    fn name(&self) -> &str {
        "duplicate-stats"
    }

    fn start_urls(&self) -> Vec<String> {
        vec![self.start.clone()]
    }

    async fn parse(&self, res: &Response) -> Result<Output<Self::Item>, KumoError> {
        if res.url() == self.start {
            return Ok(Output::new()
                .request(CrawlRequest::get(&self.target))
                .request(CrawlRequest::get(&self.target)));
        }
        Ok(Output::new())
    }
}

#[async_trait::async_trait]
impl Spider for PanicSpider {
    type Item = serde_json::Value;

    fn name(&self) -> &str {
        self.name
    }

    fn start_urls(&self) -> Vec<String> {
        vec![self.start.clone()]
    }

    async fn parse(&self, _res: &Response) -> Result<Output<Self::Item>, KumoError> {
        panic!("intentional panic for stats coverage");
    }
}

#[tokio::test]
async fn engine_stats_count_scheduled_completed_and_deduped_requests() {
    let start = "https://example.com/start";
    let target = "https://example.com/target";
    let mock = MockFetcher::new()
        .with_response(start, 200, "<a>start</a>")
        .with_response(target, 200, "<h1>target</h1>");

    let stats = CrawlEngine::builder()
        .concurrency(1)
        .respect_robots_txt(false)
        .fetcher(mock)
        .store(StdoutStore)
        .run(DuplicateSpider {
            start: start.to_string(),
            target: target.to_string(),
        })
        .await
        .unwrap();

    assert_eq!(stats.pages_crawled, 2);
    assert_eq!(stats.scheduled, 2);
    assert_eq!(stats.deduped, 1);
    assert_eq!(stats.domains["example.com"].scheduled, 2);
    assert_eq!(stats.domains["example.com"].deduped, 1);
    assert_eq!(stats.domains["example.com"].completed, 2);
}

#[tokio::test]
async fn engine_stats_count_task_panic_as_domain_failure() {
    let start = "https://panic.example.com/start";
    let mock = MockFetcher::new().with_response(start, 200, "<h1>panic</h1>");

    let stats = CrawlEngine::builder()
        .concurrency(1)
        .respect_robots_txt(false)
        .fetcher(mock)
        .store(StdoutStore)
        .run(PanicSpider {
            start: start.to_string(),
            name: "panic-single",
        })
        .await
        .unwrap();

    assert_eq!(stats.errors, 1);
    assert_eq!(stats.pages_crawled, 0);
    assert_eq!(stats.domains["panic.example.com"].failed, 1);
}

#[tokio::test]
async fn run_all_stats_count_task_panic_for_the_right_spider() {
    let panic_url = "https://panic.example.com/start";
    let ok_url = "https://ok.example.com/start";
    let mock = MockFetcher::new()
        .with_response(panic_url, 200, "<h1>panic</h1>")
        .with_response(ok_url, 200, "<h1>ok</h1>");

    struct OkSpider(String);

    #[async_trait::async_trait]
    impl Spider for OkSpider {
        type Item = serde_json::Value;

        fn name(&self) -> &str {
            "ok"
        }

        fn start_urls(&self) -> Vec<String> {
            vec![self.0.clone()]
        }

        async fn parse(&self, _res: &Response) -> Result<Output<Self::Item>, KumoError> {
            Ok(Output::new())
        }
    }

    let stats = CrawlEngine::builder()
        .concurrency(2)
        .respect_robots_txt(false)
        .fetcher(mock)
        .store(StdoutStore)
        .add_spider(PanicSpider {
            start: panic_url.to_string(),
            name: "panic-multi",
        })
        .add_spider(OkSpider(ok_url.to_string()))
        .run_all()
        .await
        .unwrap();

    assert_eq!(stats[0].errors, 1);
    assert_eq!(stats[0].pages_crawled, 0);
    assert_eq!(stats[0].domains["panic.example.com"].failed, 1);

    assert_eq!(stats[1].errors, 0);
    assert_eq!(stats[1].pages_crawled, 1);
    assert_eq!(stats[1].domains["ok.example.com"].completed, 1);
}