kumo 0.5.0

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

use std::time::Duration;

use tokio::sync::broadcast;

use crate::{
    error::KumoErrorKind,
    stats::{CrawlReport, StopReason},
};

/// Why a request was skipped before fetching.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum RequestSkipReason {
    RobotsTxt,
    Duplicate,
    DepthLimit,
    DomainDenied,
}

impl RequestSkipReason {
    /// Stable snake_case label for logs, reports, and event consumers.
    pub fn as_str(self) -> &'static str {
        match self {
            Self::RobotsTxt => "robots_txt",
            Self::Duplicate => "duplicate",
            Self::DepthLimit => "depth_limit",
            Self::DomainDenied => "domain_denied",
        }
    }
}

/// Why an item was dropped before storage.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum ItemDropReason {
    PipelineFiltered,
    PipelineError,
}

impl ItemDropReason {
    /// Stable snake_case label for logs, reports, and event consumers.
    pub fn as_str(self) -> &'static str {
        match self {
            Self::PipelineFiltered => "pipeline_filtered",
            Self::PipelineError => "pipeline_error",
        }
    }
}

/// Typed crawl lifecycle event emitted by [`crate::engine::CrawlEngine`].
///
/// Event delivery is best-effort. If there are no receivers or a receiver lags,
/// the crawl continues normally.
#[derive(Debug, Clone)]
pub enum CrawlEvent {
    CrawlStarted {
        spider: String,
        spider_index: Option<usize>,
        start_urls: usize,
    },
    RequestScheduled {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
    },
    RequestSkipped {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
        reason: RequestSkipReason,
    },
    RequestStarted {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
        attempt: u32,
    },
    RequestCompleted {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
        attempt: u32,
        status: u16,
        bytes: u64,
        items: u64,
        elapsed: Duration,
    },
    RequestRetried {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
        attempt: u32,
        max_attempts: u32,
        delay: Duration,
        error_kind: KumoErrorKind,
    },
    RequestFailed {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        domain: String,
        depth: usize,
        attempt: u32,
        error_kind: KumoErrorKind,
        retry_exhausted: bool,
    },
    TaskPanicked {
        spider: String,
        spider_index: Option<usize>,
        url: Option<String>,
        domain: Option<String>,
        depth: Option<usize>,
    },
    ItemScraped {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        depth: usize,
    },
    ItemDropped {
        spider: String,
        spider_index: Option<usize>,
        url: String,
        depth: usize,
        reason: ItemDropReason,
        error_kind: Option<KumoErrorKind>,
    },
    CrawlFinished {
        spider: String,
        spider_index: Option<usize>,
        report: CrawlReport,
        stop_reason: Option<StopReason>,
    },
}

impl CrawlEvent {
    /// Stable snake_case label for dashboards, metrics, and event logs.
    pub fn name(&self) -> &'static str {
        match self {
            Self::CrawlStarted { .. } => "crawl_started",
            Self::RequestScheduled { .. } => "request_scheduled",
            Self::RequestSkipped { .. } => "request_skipped",
            Self::RequestStarted { .. } => "request_started",
            Self::RequestCompleted { .. } => "request_completed",
            Self::RequestRetried { .. } => "request_retried",
            Self::RequestFailed { .. } => "request_failed",
            Self::TaskPanicked { .. } => "task_panicked",
            Self::ItemScraped { .. } => "item_scraped",
            Self::ItemDropped { .. } => "item_dropped",
            Self::CrawlFinished { .. } => "crawl_finished",
        }
    }
}

/// Best-effort event emitter used internally by the crawl engine.
#[derive(Debug, Clone)]
pub(crate) struct EventEmitter {
    tx: broadcast::Sender<CrawlEvent>,
}

impl EventEmitter {
    pub(crate) fn new(tx: broadcast::Sender<CrawlEvent>) -> Self {
        Self { tx }
    }

    pub(crate) fn emit(&self, event: CrawlEvent) {
        let _ = self.tx.send(event);
    }
}