phrona 0.1.0

High-performance metasearch engine library for Rust and Python
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

use async_trait::async_trait;

use crate::engine::{Engine, EngineContext};
use crate::engines::util;
use crate::error::{Error, Result};
use crate::models::{Category, RawResult};
use crate::parse;

/// Anna's Archive book search. The project's domains rotate after TLD
/// seizures, so the engine tries a list of known mirrors in order and uses
/// the first one that responds with a parseable SERP.
pub struct AnnasArchive;

const ANNAS_DOMAINS: &[&str] = &["annas-archive.gd", "annas-archive.se", "annas-archive.org"];

#[async_trait]
impl Engine for AnnasArchive {
    fn name(&self) -> &'static str {
        "annas_archive"
    }

    fn category(&self) -> Category {
        Category::Books
    }

    async fn search(&self, ctx: &EngineContext<'_>) -> Result<Vec<RawResult>> {
        let opts = ctx.opts;
        let mut last_err: Option<Error> = None;
        for domain in ANNAS_DOMAINS {
            let url = parse::with_query(
                &format!("https://{domain}/search"),
                [
                    ("q", opts.query.as_str()),
                    ("page", opts.page.to_string().as_str()),
                ],
            );
            match ctx.client.get(&url).await {
                Ok(resp) => match util::check_response(self.name(), &resp, util::MediaType::Html) {
                    Ok(()) => match util::read_body(resp, self.name()).await {
                        Ok(body) => {
                            let text = String::from_utf8_lossy(&body);
                            let results = parse_annas(&text, self.name(), domain);
                            if !results.is_empty() {
                                return Ok(results);
                            }
                        }
                        Err(e) => last_err = Some(e),
                    },
                    Err(e) => last_err = Some(e),
                },
                Err(e) => last_err = Some(e),
            }
        }
        Err(last_err.unwrap_or_else(|| Error::internal("annas_archive", "all mirrors failed")))
    }
}

pub fn parse_annas(html: &str, engine: &str, domain: &str) -> Vec<RawResult> {
    let cleaned = html.replace("<!--", "").replace("-->", "");
    let doc = parse::parse_html(&cleaned);
    let mut out = Vec::new();
    let sel = scraper::Selector::parse("div.js-aarecord-list-outer > div").unwrap();
    let mut pos = 0u32;
    for node in doc.select(&sel) {
        let title = parse::select_first_nonempty(&node, "a[class*='text-lg']");
        let href = parse::attr(&node, "a[class*='text-lg']", "href").unwrap_or_default();
        if let (Some(title), _) = (title, href.clone()) {
            if href.is_empty() {
                continue;
            }
            let author = parse::select_text(&node, "a[class*='text-sm']").unwrap_or_default();
            let author = if author.is_empty() {
                parse::attr(&node, "a[class*='text-sm']", "href")
                    .unwrap_or_default()
                    .strip_prefix("/search?q=")
                    .map(crate::parse::percent_decode)
                    .unwrap_or_default()
            } else {
                author
            };
            let publisher = parse::select_text(&node, "a[class*='company']").unwrap_or_default();
            let info = parse::select_text(&node, "div[class*='text-gray-800']").unwrap_or_default();
            let thumb = parse::attr(&node, "img", "src").unwrap_or_default();
            pos += 1;
            out.push(RawResult {
                title,
                url: if href.starts_with("http") {
                    href
                } else {
                    format!("https://{domain}{href}")
                },
                author,
                publisher,
                description: info,
                thumbnail_url: thumb,
                engine: engine.to_string(),
                position: pos,
                ..Default::default()
            });
        }
    }
    out
}

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

    #[test]
    fn parse_fixture() {
        let html = include_str!("../../tests/fixtures/annas_archive.html");
        if !crate::engines::util::fixture_parses("annas_archive.html") {
            return;
        }
        let results = parse_annas(html, "annas_archive", "annas-archive.gd");
        assert!(!results.is_empty());
    }
}