// include the latest version of the regex crate in your Cargo.toml
extern crate regex;
use regex::Regex;
fn main() {
let regex = Regex::new(r"(?m)https?:\/\/(?:w{1,3}\.)?[^\s.]*(?:\.[a-z]+)+(?::\d+)?(?![^<]*(?:<\/\w+>|\/?>))").unwrap();
let string = "This is my text to be parsed which contains url
http://someurl.com <a href=\"http://thisshouldnotbetampered.com\">
some text and a url http://someotherurl.com test 1q2w </a> <img src=\"http://someasseturl.com/abc.jpeg\"/>
Hello http://someurl.com</a> <!-- fail -->
<img src=\"http://someurl.com/image.jpg>
http://someurl.localhost.com
<div>Regex is awesome</div>
<a href='https://help.mojohelpdesk.com/mytickets/show/26737327'>https://help.mojohelpdesk.com/mytickets/show/26737327</a>
<a href=\"https://help.mojohelpdesk.com/mytickets/show/26737327\">https://help.mojohelpdesk.com/mytickets/show/26737327</a>
https://google.com
https://www.mojo.com
http://localhost:3000
http://site.quelqu
http://localhost.com:3000
www.google.com";
// result will be an iterator over tuples containing the start and end indices for each match in the string
let result = regex.captures_iter(string);
for mat in result {
println!("{:?}", mat);
}
}
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for Rust, please visit: https://docs.rs/regex/latest/regex/