// 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"<p>(\s*)(<a(.*)>)?(\s*)(https?:\/\/)?(w{3}\.)?(youtube\.com|youtu\.be)\/(watch\?v=|embed\/)?([A-Za-z0-9-_]{11})(\S*)(\s*)(<\/a>)?(\s*)<\/p>").unwrap();
let string = "No protocol:
<p>youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>www.youtube.com/watch?v=dQw4w9WgXcQ</p>
HTTP or HTTPS:
<p>http://youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>http://www.youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>https://youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ</p>
With or without “www”
<p>https://youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ</p>
Youtu.be short links
<p>youtu.be/LQaehcfXvK0</p>
<p>https://youtu.be/LQaehcfXvK0</p>
Embed Urls:
<p>http://www.youtube.com/embed/dQw4w9WgXcQ</p>
URLs with extra parameters:
<p>https://www.youtube.com/watch?v=LQaehcfXvK0&feature=youtu.be</p>
<p>https://www.youtube.com/watch?v=dQw4w9WgXcQ&list=RDdQw4w9WgXcQ&start_radio=1&t=1</p>
This URL won’t actually work on YouTube, but it works here, which is somewhat odd? And yet doesn't seem harmful.
<p>youtu.be/embed/dQw4w9WgXcQ</p>
Paragraph tags on separate lines with arbitrary whitespace:
<p>
www.youtube.com/embed/u8pCsfT1gDU
</p>
<p>
https://youtube.com/watch?v=dQw4w9WgXcQ
</p>
<p>
http://www.youtube.com/embed/dQw4w9WgXcQ
</p>
<p>
youtube.com/watch?v=dQw4w9WgXcQ
</p>
Paragraph tags with any other text in them, besides the URL:
<p>This shouldn’t work: https://youtube.com/watch?v=dQw4w9WgXcQ</p>
<p>https://youtube.com/watch?v=dQw4w9WgXcQ nor this</p>
<p>
https://youtube.com/watch?v=dQw4w9WgXcQ also not this
</p>
Paragraph tags with links added by markdown-it:
<p><a href=\"https://www.youtube.com/watch?v=dQw4w9WgXcQ\">https://www.youtube.com/watch?v=dQw4w9WgXcQ</a></p>
<p>
<a href=\"https://www.youtube.com/watch?v=dQw4w9WgXcQ?something\" class=\"something\" id=\"whatever\">
youtube.com/watch?v=dQw4w9WgXcQ?foo=bar&whatever
</a>
</p>
";
// 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/