How to extract base URL from a string in JavaScrip

Question

I'm trying to find a relatively easy and reliable method to extract the base URL from a string variable using JavaScript (or jQuery).

For example, given something like:

http://www.sitename.com/article/2009/09/14/this-is-an-article/

I'd like to get:

http://www.sitename.com/

Is a regular expression the best bet? If so, what statement could I use to assign the base URL extracted from a given string to a new variable?

I've done some searching on this, but everything I find in the JavaScript world seems to revolve around gathering this information from the actual document URL using location.host or similar.

Answer 1

I use a simple regex that extracts the host form the url:

function get_host(url){
    return url.replace(/^((\w+:)?\/\/[^\/]+\/?).*$/,'$1');
}

and use it like this

var url = 'http://www.sitename.com/article/2009/09/14/this-is-an-article/'
var host = get_host(url);

Note, if the url does not end with a / the host will not end in a /.

Here are some tests:

describe('get_host', function(){
    it('should return the host', function(){
        var url = 'http://www.sitename.com/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'http://www.sitename.com/');
    });
    it('should not have a / if the url has no /', function(){
        var url = 'http://www.sitename.com';
        assert.equal(get_host(url),'http://www.sitename.com');
    });
    it('should deal with https', function(){
        var url = 'https://www.sitename.com/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'https://www.sitename.com/');
    });
    it('should deal with no protocol urls', function(){
        var url = '//www.sitename.com/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'//www.sitename.com/');
    });
    it('should deal with ports', function(){
        var url = 'http://www.sitename.com:8080/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'http://www.sitename.com:8080/');
    });
    it('should deal with localhost', function(){
        var url = 'http://localhost/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'http://localhost/');
    });
    it('should deal with numeric ip', function(){
        var url = 'http://192.168.18.1/article/2009/09/14/this-is-an-article/';
        assert.equal(get_host(url),'http://192.168.18.1/');
    });
});

Answer 2

Well, URL API object avoids splitting and constructing the url's manually.

 let url = new URL('https://stackoverflow.com/questions/1420881');
 alert(url.origin);