I hate the DOM! The API sucks! Don’t you agree?

Regardless, we should definitely take advantage of what we’ve been given. So, if something is built into the DOM it would be silly not to use it, right?

Well, that’s what I believe and that’s why I think it’s okay to parse URLs via this API instead of trying to accomplish it in a language-agnostic manner (using a tonne of expensive string operations).

This short function returns an object containing all possible information you would want to retrieve from a URL:

parseURL

// This function creates a new anchor element and uses location
// properties (inherent) to get the desired URL data. Some String
// operations are used (to normalize results across browsers).
 
function parseURL(url) {
    var a =  document.createElement('a');
    a.href = url;
    return {
        source: url,
        protocol: a.protocol.replace(':',''),
        host: a.hostname,
        port: a.port,
        query: a.search,
        params: (function(){
            var ret = {},
                seg = a.search.replace(/^?/,'').split('&'),
                len = seg.length, i = 0, s;
            for (;i<len;i++) {
                if (!seg[i]) { continue; }
                s = seg[i].split('=');
                ret[s[0]] = s[1];
            }
            return ret;
        })(),
        file: (a.pathname.match(//([^/?#]+)$/i) || [,''])[1],
        hash: a.hash.replace('#',''),
        path: a.pathname.replace(/^([^/])/,'/$1'),
        relative: (a.href.match(/tps?://[^/]+(.+)/) || [,''])[1],
        segments: a.pathname.replace(/^//,'').split('/')
    };
}

Usage

var myURL = parseURL('http://abc.com:8080/dir/index.html?id=255&m=hello#top');
 
myURL.file;     // = 'index.html'
myURL.hash;     // = 'top'
myURL.host;     // = 'abc.com'
myURL.query;    // = '?id=255&m=hello'
myURL.params;   // = Object = { id: 255, m: hello }
myURL.path;     // = '/dir/index.html'
myURL.segments; // = Array = ['dir', 'index.html']
myURL.port;     // = '8080'
myURL.protocol; // = 'http'
myURL.source;   // = 'http://abc.com:8080/dir/index.html?id=255&m=hello#top'

I’ve tested this solution in all modern browsers (including IE6) and it seems to work perfectly. If you spot any inconsistencies please let me know.

If you don’t feel comfortable using something which relies on the DOM then have a look at this although please note it’s about 12 times slower than the above solution…

Thanks for reading! Please share your thoughts with me on Twitter. Have a great day!