iocutil 0.1.3

IoC utilities for malware researchers
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

//! utilities for scraping web pages

use crate::GenericResult;
use failure::Fail;
use lazy_static::lazy_static;
use scraper::{Html, Selector};

lazy_static! {
    static ref ARTICLE_SELECTOR: Selector = Selector::parse("article").unwrap();
    static ref BODY_SELECTOR: Selector = Selector::parse("body").unwrap();
}

/// get html from specified url
pub fn get_html(url: impl AsRef<str>) -> GenericResult<String> {
    Ok(reqwest::get(url.as_ref())?.text()?)
}

/// scrape articles from html text
pub fn scrape_articles(html: impl AsRef<str>) -> Vec<String> {
    let document = Html::parse_document(html.as_ref());
    document
        .select(&ARTICLE_SELECTOR)
        .map(|x| x.text().collect::<Vec<_>>().join(" "))
        .collect()
}

/// scrape body from html text
pub fn scrape_body(html: impl AsRef<str>) -> Vec<String> {
    let document = Html::parse_document(html.as_ref());
    document
        .select(&BODY_SELECTOR)
        .map(|x| x.text().collect::<Vec<_>>().join(" "))
        .collect()
}

/// Errors in scraping
#[derive(Fail, Debug)]
pub enum ScrapingError {
    #[fail(display = "could not find target elements")]
    TargetNotFound,
}

/// get article (or body) text from specified url
pub fn get_article(url: impl AsRef<str>) -> GenericResult<String> {
    let html = get_html(url)?;
    let articles = scrape_articles(&html);
    if !articles.is_empty() {
        return Ok(articles.join("\n"));
    }
    let body = scrape_body(&html);
    if body.is_empty() {
        return Err(ScrapingError::TargetNotFound.into());
    }
    Ok(body.join("\n"))
}