3 unstable releases

0.2.1	Dec 4, 2023
0.2.0	~~Dec 4, 2023~~
0.1.55	Nov 27, 2021

#193 in HTTP client

44 downloads per month

MIT/Apache

34KB
667 lines

Scraping Websites!

Examples:

Get InnerHTML:

let html = "<html><body><div>Hello World!</div></body></html>";
     
let dom = sitescraper::parse_html(html).unwrap();
     
let filtered_dom = dom.filter("body");
     
println!("{}", filtered_dom.get_inner_html());
//Output: <div>Hello World!</div>

Get Text:

let html = "<html><body><div>Hello World!</div></body></html>";

let dom = sitescraper::parse_html(html).unwrap();

let filtered_dom = dom.filter("body");

println!("{}", filtered_dom.get_text());
//Output: Hello World!

Get Text from single Tags:

use sitescraper;

let html = "<html><body><div>Hello World!</div></body></html>";

let dom = sitescraper::parse_html(html).unwrap();

let filtered_dom = dom.filter("div");

println!("{}", filtered_dom.tag[0].get_text());
//Output: Hello World!

Works also with

get_inner_html()

Filter by tag-name, attribute-name and attribute-value using a tuple:

use sitescraper;
 
let html = "<html><body><div id='hello'>Hello World!</div></body></html>";
 
let dom = sitescraper::parse_html(html).unwrap();
 
let filtered_dom = dom.filter(("div", "id", "hello"));
 
println!("{}", filtered_dom.tag[0].get_text());
//Output: Hello World!

Works also with a tuple consisting of two string literals

let filtered_dom = dom.filter(("div", "id"));

You can also leave arguments out by passing "*" or "":

use sitescraper;

let html = "<html><body><div id="hello">Hello World!</div></body></html>";

let dom = sitescraper::parse_html(html).unwrap();

let filtered_dom = dom.filter(("*", "id", "hello"));

println!("{}", filtered_dom.tag[0].get_text());
//Output: Hello World!

use sitescraper;

let html = "<html><body><div id="hello">Hello World!</div></body></html>";

let dom = sitescraper::parse_html(html).unwrap();

let filtered_dom = dom.filter(("", "", "hello"));

println!("{}", filtered_dom.tag[0].get_text());
//Output: Hello World!

Get Website-Content:

use sitescraper;

let html = sitescraper::http::get("http://example.com/).await.unwrap();

let dom = sitescraper::parse_html(html).unwrap();

let filtered_dom = sitescraper::filter!(dom, "div");

println!("{}", filtered_dom.get_inner_html());

Dependencies

~4–15MB
~204K SLoC