crawlkit-engine 1.0.0

High-performance Rust web crawler and SEO analysis toolkit with 28 analyzers, WASM plugin system, and enterprise features
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

use serde::{Deserialize, Serialize};
use url::Url;

/// Open Graph protocol tags for social media previews.
///
/// Extracted from `<meta property="og:*">` tags. Used by the
/// [`SocialMediaAnalyzer`](crate::SocialMediaAnalyzer) to check
/// completeness of social sharing metadata.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct OpenGraphTags {
    /// `og:title` — title for social sharing.
    pub title: Option<String>,
    /// `og:description` — description for social sharing.
    pub description: Option<String>,
    /// `og:image` — image URL for social preview.
    pub image: Option<String>,
    /// `og:url` — canonical URL for social sharing.
    pub url: Option<String>,
    /// `og:type` — content type (website, article, etc.).
    pub r#type: Option<String>,
    /// `og:site_name` — site name.
    pub site_name: Option<String>,
    /// `og:locale` — content locale (e.g., "en_US").
    pub locale: Option<String>,
}

/// Twitter Card tags for Twitter/X previews.
///
/// Extracted from `<meta name="twitter:*">` tags. Used by the
/// [`SocialMediaAnalyzer`](crate::SocialMediaAnalyzer) to check
/// Twitter Card completeness.
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct TwitterTags {
    /// `twitter:card` — card type (summary, summary_large_image).
    pub card: Option<String>,
    /// `twitter:site` — site Twitter handle.
    pub site: Option<String>,
    /// `twitter:creator` — author Twitter handle.
    pub creator: Option<String>,
    /// `twitter:title` — title for Twitter sharing.
    pub title: Option<String>,
    /// `twitter:description` — description for Twitter sharing.
    pub description: Option<String>,
    /// `twitter:image` — image URL for Twitter card.
    pub image: Option<String>,
    /// `twitter:image:alt` — alt text for Twitter card image.
    pub image_alt: Option<String>,
}

/// A single hreflang alternate link.
///
/// Represents a `<link rel="alternate" hreflang="..." href="...">` tag
/// for international SEO. Validated by the [`HreflangValidator`](crate::HreflangValidator).
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct HreflangTag {
    /// Language code (e.g., "en", "fr-CA", "x-default").
    pub lang: String,
    /// URL of the alternate language version.
    pub url: Url,
}

/// Complete set of meta tags extracted from a page.
///
/// Aggregates all SEO-relevant meta information including title,
/// description, canonical URL, robots directives, Open Graph,
/// Twitter Cards, and hreflang tags. Provides helper methods
/// for common checks.
///
/// # Examples
///
/// ```rust
/// use crawlkit_engine::MetaTags;
///
/// let meta = MetaTags {
///     title: Some("My Page".to_string()),
///     robots: Some("noindex, nofollow".to_string()),
///     ..Default::default()
/// };
/// assert!(meta.is_noindex());
/// assert!(meta.is_nofollow());
/// assert_eq!(meta.title_length(), Some(7));
/// ```
#[derive(Debug, Clone, Default, Serialize, Deserialize)]
pub struct MetaTags {
    /// Page title (`<title>` tag).
    pub title: Option<String>,
    /// Meta description.
    pub description: Option<String>,
    /// Canonical URL (`<link rel="canonical">`).
    pub canonical: Option<Url>,
    /// Robots directive (`<meta name="robots">`).
    pub robots: Option<String>,
    /// Page language (`<html lang="...">`).
    pub language: Option<String>,
    /// Character encoding (`<meta charset="...">`).
    pub charset: Option<String>,
    /// Viewport meta tag.
    pub viewport: Option<String>,
    /// Open Graph tags.
    pub og: OpenGraphTags,
    /// Twitter Card tags.
    pub twitter: TwitterTags,
    /// Hreflang alternate links.
    pub hreflang: Vec<HreflangTag>,
}

impl MetaTags {
    /// Returns the length of the title, if present.
    pub fn title_length(&self) -> Option<usize> {
        self.title.as_ref().map(|t| t.len())
    }

    /// Returns the length of the description, if present.
    pub fn description_length(&self) -> Option<usize> {
        self.description.as_ref().map(|d| d.len())
    }

    /// Whether the page has a `<meta name="robots" content="noindex">` directive.
    pub fn is_noindex(&self) -> bool {
        self.robots
            .as_deref()
            .map(|r| r.split(',').any(|v| v.trim() == "noindex"))
            .unwrap_or(false)
    }

    /// Whether the page has a `<meta name="robots" content="nofollow">` directive.
    pub fn is_nofollow(&self) -> bool {
        self.robots
            .as_deref()
            .map(|r| r.split(',').any(|v| v.trim() == "nofollow"))
            .unwrap_or(false)
    }
}

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

    #[test]
    fn test_meta_tags_defaults() {
        let meta = MetaTags::default();
        assert!(meta.title.is_none());
        assert!(meta.description.is_none());
        assert!(meta.canonical.is_none());
        assert!(meta.og.title.is_none());
        assert!(meta.twitter.card.is_none());
        assert!(meta.hreflang.is_empty());
    }

    #[test]
    fn test_title_length() {
        let mut meta = MetaTags::default();
        assert_eq!(meta.title_length(), None);

        meta.title = Some("Hello World".into());
        assert_eq!(meta.title_length(), Some(11));
    }

    #[test]
    fn test_description_length() {
        let mut meta = MetaTags::default();
        assert_eq!(meta.description_length(), None);

        meta.description = Some("A short description".into());
        assert_eq!(meta.description_length(), Some(19));
    }

    #[test]
    fn test_is_noindex() {
        let mut meta = MetaTags::default();
        assert!(!meta.is_noindex());

        meta.robots = Some("noindex".into());
        assert!(meta.is_noindex());

        meta.robots = Some("index, nofollow".into());
        assert!(!meta.is_noindex());

        meta.robots = Some("noindex, nofollow".into());
        assert!(meta.is_noindex());
    }

    #[test]
    fn test_is_nofollow() {
        let mut meta = MetaTags::default();
        assert!(!meta.is_nofollow());

        meta.robots = Some("nofollow".into());
        assert!(meta.is_nofollow());

        meta.robots = Some("noindex, nofollow".into());
        assert!(meta.is_nofollow());
    }

    #[test]
    fn test_open_graph_serialization() {
        let og = OpenGraphTags {
            title: Some("My Page".into()),
            description: Some("Desc".into()),
            image: Some("https://example.com/img.png".into()),
            url: Some("https://example.com".into()),
            r#type: Some("website".into()),
            site_name: Some("Example".into()),
            locale: Some("en_US".into()),
        };
        let json = serde_json::to_string(&og).unwrap();
        let deser: OpenGraphTags = serde_json::from_str(&json).unwrap();
        assert_eq!(og.title, deser.title);
        assert_eq!(og.image, deser.image);
    }

    #[test]
    fn test_twitter_tags_serialization() {
        let tw = TwitterTags {
            card: Some("summary_large_image".into()),
            site: Some("@example".into()),
            creator: Some("@author".into()),
            title: Some("Title".into()),
            description: Some("Desc".into()),
            image: Some("https://example.com/tw.png".into()),
            image_alt: Some("Alt text".into()),
        };
        let json = serde_json::to_string(&tw).unwrap();
        let deser: TwitterTags = serde_json::from_str(&json).unwrap();
        assert_eq!(tw.card, deser.card);
        assert_eq!(tw.image_alt, deser.image_alt);
    }

    #[test]
    fn test_hreflang_tag() {
        let tag = HreflangTag {
            lang: "en".into(),
            url: Url::parse("https://example.com/en").unwrap(),
        };
        assert_eq!(tag.lang, "en");
        let json = serde_json::to_string(&tag).unwrap();
        let deser: HreflangTag = serde_json::from_str(&json).unwrap();
        assert_eq!(tag.url, deser.url);
    }
}