// 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#"(?msix)<div\b # Start of outer DIV start tag.
[^>]*? # Lazily match up to id attrib.
\bclass\s*+=\s*+ # id attribute name and =
([\'"]?+) # $1: Optional quote delimiter.
\basd\b # specific ID to be matched.
(?(1)\1) # If open quote, match same closing quote
[^>]*+> # remaining outer DIV start tag.
( # $2: DIV contents. (may be called recursively!)
(?: # Non-capture group for DIV contents alternatives.
# DIV contents option 1: All non-DIV, non-comment stuff...
[^<]++ # One or more non-tag, non-comment characters.
# DIV contents option 2: Start of a non-DIV tag...
| < # Match a "<", but only if it
(?! # is not the beginning of either
/?div\b # a DIV start or end tag,
| !-- # or an HTML comment.
) # Ok, that < was not a DIV or comment.
# DIV contents Option 3: an HTML comment.
| <!--.*?--> # A non-SGML compliant HTML comment.
# DIV contents Option 4: a nested DIV element!
| <div\b[^>]*+> # Inner DIV element start tag.
(?2) # Recurse group 2 as a nested subroutine.
</div\s*> # Inner DIV element end tag.
)*+ # Zero or more of these contents alternatives.
) # End 2$: DIV contents.
</div\s*>"#).unwrap();
let string = "<div>
<div class=\"asd\">
<div>
<div>
Hello
</div>
</div>
</div>
</div>";
// result will be a tuple containing the start and end indices for the first match in the string
let result = regex.captures(string);
let (start, end) = match result {
Some((s, e)) => (s, e),
None => {
// ...
}
};
println!("{}", &string[start, end]);
}
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/