// 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#"(?xm)<a\s+ # Look for '<a' followed by whitespace
([^>]+\s+)? # Look for anything else that isn't 'href='
# such as 'class=' or 'id='
href\s*=\s* # locate the 'href=' with any whitespace around the '=' character
(
'([^']*)' # Look for '...'
| # ...or...
"([^"]*) # Look for "..."
| # ...or...
([^\s>]+) # Look anything NOT '>' or spaces
)
[^>]*> # Match anything else up to the closing '>'
"#).unwrap();
let string = "<!DOCTYPE html>
<html>
<head>
<title>Hyperlinks</title>
<link href=\"theme.css\" rel=\"stylesheet\" />
</head>
<body>
<ul><li><a href=\"/\" id=\"home\">Home</a></li><li><a
class=\"selected\" href=/courses>Courses</a>
</li><li><a href =
'/forum' >Forum</a></li><li><a class=\"href\"
onclick=\"go()\" href= \"#\">Forum</a></li>
<li><a id=\"js\" href =
\"javascript:alert('hi yo')\" class=\"new\">click</a></li>
<li><a id='nakov' href =
http://www.nakov.com class='new'>nak</a></li></ul>
<a href=\"#empty\"></a>
<a id=\"href\">href='fake'<img src='http://abv.bg/i.gif'
alt='abv'/></a><a href=\"#\"><a href='hello'></a>
<!-- This code is commented:
<a href=\"#commented\">commentex hyperlink</a> -->
</body>
";
// 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/