Simple Javascript regex to find root domain
I have a function that uses regex to return the root domain of a given URL.
function cleanUp(url) {
url = url.replace(new RegExp(/^\s+/),""); // START
url = url.replace(new RegExp(/\s+$/),""); // END
// IF FOUND, CONVERT BACK SLASHES TO FORWARD SLASHES
url = url.replace(new RegExp(/\\/g),"/");
// IF THERE, REMOVES 'http://', 'https://' or 'ftp://' FROM THE START
url = url.replace(new RegExp(/^http\:\/\/|^https\:\/\/|^ftp\:\/\//i),"");
// IF THERE, REMOVES 'www.' FROM THE START OF THE STRING
url = url.replace(new RegExp(/^www\./i),"");
//remove slash from end
url = url.replace(new RegExp(/\/$/i),"");
return url;
}
But it uses a multi-mode expression and we are concerned about performance. Is there a better way to do the same in a single line regex?
Note:
document.location.host doesn't seem to work in my case.
+3
source to share
2 answers
Try:
function cleanUp(url) {
var url = $.trim(url);
if(url.search(/^https?\:\/\//) != -1)
url = url.match(/^https?\:\/\/([^\/?#]+)(?:[\/?#]|$)/i, "");
else
url = url.match(/^([^\/?#]+)(?:[\/?#]|$)/i, "");
return url[1];
}
alert(cleanUp(' http://www.google.com/about.html'));
alert(cleanUp(' www.google.com/about.html'));
+5
source to share
Try the following:
http://jsfiddle.net/picklespy/gb34u/1/
It works on all modern browsers and even IE 5.5+.
var url = document.createElement('a');
url.href = 'http://maps.test.google.com';
var host = url.hostname;
host = host.split('.');
var domain = host.pop();
domain = host.pop() + '.' + domain;
alert('Root is: ' + domain)
+1
source to share