rust_scraper 1.0.0

Production-ready web scraper with Clean Architecture, TUI selector, and sitemap support
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301

//! Link extraction from HTML
//!
//! Extracts and normalizes links from HTML content.
//!
//! # Rules Applied
//!
//! - **own-borrow-over-clone**: Accept `&str` not `&String`
//! - **opt-inline**: Inline hot path functions
//! - **mem-with-capacity**: Pre-allocate Vec when size is estimable

use scraper::{Html, Selector};
use tracing::debug;
use url::Url;

/// Extract all links from HTML content
///
/// Following **own-borrow-over-clone**: Accepts `&str` not `&String`.
/// Following **mem-with-capacity**: Pre-allocates Vec with estimated capacity.
///
/// # Arguments
///
/// * `html` - HTML content to parse
/// * `base_url` - Base URL for resolving relative links
///
/// # Returns
///
/// * `Ok(Vec<String>)` - List of extracted URLs
/// * `Err(CrawlError)` - Parse error
///
/// # Examples
///
/// ```
/// use rust_scraper::infrastructure::crawler::extract_links;
///
/// let html = r#"<html><body><a href="/page1">Link 1</a><a href="https://other.com/page2">Link 2</a></body></html>"#;
/// let links = extract_links(html, "https://example.com").unwrap();
/// assert!(links.contains(&"https://example.com/page1".to_string()));
/// assert!(links.contains(&"https://other.com/page2".to_string()));
/// ```
pub fn extract_links(html: &str, base_url: &str) -> Result<Vec<String>, crate::domain::CrawlError> {
    debug!("Extracting links from HTML (base_url={})", base_url);

    let document = Html::parse_document(html);
    let selector = Selector::parse("a[href]").map_err(|e| {
        crate::domain::CrawlError::Parse(format!("Failed to parse selector: {}", e))
    })?;

    // Parse base URL once
    let base =
        Url::parse(base_url).map_err(|e| crate::domain::CrawlError::InvalidUrl(e.to_string()))?;

    // Pre-allocate with estimated capacity (optimization for typical pages)
    let mut links = Vec::with_capacity(32);

    for element in document.select(&selector) {
        if let Some(href) = element.value().attr("href") {
            // Resolve relative URLs
            match base.join(href) {
                Ok(absolute_url) => {
                    let normalized = normalize_url(absolute_url.as_str());
                    if !links.contains(&normalized) {
                        links.push(normalized);
                    }
                }
                Err(e) => {
                    debug!("Failed to resolve URL '{}': {}", href, e);
                }
            }
        }
    }

    debug!("Extracted {} links from {}", links.len(), base_url);
    Ok(links)
}

/// Check if a URL is internal (same domain)
///
/// Following **own-borrow-over-clone**: Accepts `&str` for both parameters.
/// Following **opt-inline**: Inlined for hot path performance.
///
/// # Arguments
///
/// * `url` - URL to check
/// * `domain` - Domain to check against
///
/// # Returns
///
/// `true` if the URL belongs to the domain
///
/// # Examples
///
/// ```
/// use rust_scraper::infrastructure::crawler::is_internal_link;
///
/// assert!(is_internal_link("https://example.com/page", "example.com"));
/// assert!(is_internal_link("https://www.example.com/page", "example.com"));
/// assert!(!is_internal_link("https://other.com/page", "example.com"));
/// ```
#[inline]
#[must_use]
pub fn is_internal_link(url: &str, domain: &str) -> bool {
    extract_domain(url)
        .map(|url_domain| url_domain == domain || url_domain.ends_with(&format!(".{}", domain)))
        .unwrap_or(false)
}

/// Normalize a URL (remove fragments, trailing slashes, etc.)
///
/// Following **own-borrow-over-clone**: Accepts `&str`.
///
/// # Arguments
///
/// * `url` - URL to normalize
///
/// # Returns
///
/// Normalized URL string
///
/// # Examples
///
/// ```
/// use rust_scraper::infrastructure::crawler::normalize_url;
///
/// assert_eq!(
///     normalize_url("https://example.com/page#section"),
///     "https://example.com/page"
/// );
/// assert_eq!(
///     normalize_url("https://example.com/page/"),
///     "https://example.com/page/"
/// );
/// ```
#[inline]
#[must_use]
pub fn normalize_url(url: &str) -> String {
    // Remove fragment
    let without_fragment = url.split('#').next().unwrap_or(url);

    // Parse and rebuild URL for consistent normalization
    if let Ok(parsed) = Url::parse(without_fragment) {
        // Keep trailing slash if present, remove query params for deduplication
        let mut normalized = parsed[..url::Position::AfterPath].to_string();

        // Preserve trailing slash
        if without_fragment.ends_with('/') && !normalized.ends_with('/') {
            normalized.push('/');
        }

        normalized
    } else {
        without_fragment.to_string()
    }
}

/// Extract domain from URL
///
/// Following **own-borrow-over-clone**: Accepts `&str`.
/// Following **opt-inline**: Inlined for hot path.
///
/// # Arguments
///
/// * `url` - URL to extract domain from
///
/// # Returns
///
/// Domain string or None if invalid
#[inline]
#[must_use]
fn extract_domain(url: &str) -> Option<&str> {
    url.split("://")
        .nth(1)
        .and_then(|rest| rest.split('/').next())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn test_extract_links_basic() {
        let html = r#"
            <html>
                <body>
                    <a href="/page1">Link 1</a>
                    <a href="/page2">Link 2</a>
                    <a href="https://other.com/external">External</a>
                </body>
            </html>
        "#;

        let links = extract_links(html, "https://example.com").unwrap();

        assert!(links.contains(&"https://example.com/page1".to_string()));
        assert!(links.contains(&"https://example.com/page2".to_string()));
        assert!(links.contains(&"https://other.com/external".to_string()));
        assert_eq!(links.len(), 3);
    }

    #[test]
    fn test_extract_links_relative_paths() {
        let html = r#"
            <html>
                <body>
                    <a href="../parent">Parent</a>
                    <a href="./current">Current</a>
                    <a href="sub/child">Child</a>
                </body>
            </html>
        "#;

        let links = extract_links(html, "https://example.com/dir/page").unwrap();

        assert!(links.contains(&"https://example.com/parent".to_string()));
        assert!(links.contains(&"https://example.com/dir/current".to_string()));
        assert!(links.contains(&"https://example.com/dir/sub/child".to_string()));
    }

    #[test]
    fn test_extract_links_no_duplicates() {
        let html = r#"
            <html>
                <body>
                    <a href="/page">Link 1</a>
                    <a href="/page">Link 2</a>
                    <a href="/page">Link 3</a>
                </body>
            </html>
        "#;

        let links = extract_links(html, "https://example.com").unwrap();
        assert_eq!(links.len(), 1);
        assert_eq!(links[0], "https://example.com/page");
    }

    #[test]
    fn test_extract_links_empty() {
        let html = r#"<html><body>No links here</body></html>"#;
        let links = extract_links(html, "https://example.com").unwrap();
        assert!(links.is_empty());
    }

    #[test]
    fn test_extract_links_invalid_html() {
        let html = "This is not HTML at all";
        let links = extract_links(html, "https://example.com").unwrap();
        assert!(links.is_empty());
    }

    #[test]
    fn test_is_internal_link() {
        assert!(is_internal_link("https://example.com/page", "example.com"));
        assert!(is_internal_link(
            "https://www.example.com/page",
            "example.com"
        ));
        assert!(is_internal_link(
            "https://blog.example.com/post",
            "example.com"
        ));
        assert!(!is_internal_link("https://other.com/page", "example.com"));
        assert!(!is_internal_link("invalid-url", "example.com"));
    }

    #[test]
    fn test_normalize_url_remove_fragment() {
        assert_eq!(
            normalize_url("https://example.com/page#section"),
            "https://example.com/page"
        );
        assert_eq!(
            normalize_url("https://example.com/page#top"),
            "https://example.com/page"
        );
    }

    #[test]
    fn test_normalize_url_preserve_trailing_slash() {
        assert_eq!(
            normalize_url("https://example.com/page/"),
            "https://example.com/page/"
        );
        assert_eq!(
            normalize_url("https://example.com/page/#section"),
            "https://example.com/page/"
        );
    }

    #[test]
    fn test_normalize_url_no_change() {
        assert_eq!(
            normalize_url("https://example.com/page"),
            "https://example.com/page"
        );
    }

    #[test]
    fn test_normalize_url_invalid() {
        let result = normalize_url("not-a-valid-url");
        assert_eq!(result, "not-a-valid-url");
    }
}