Check if a JavaScript string is a URL

Question

Is there a way in JavaScript to check if a string is a URL?

RegExes are excluded because the URL is most likely written like stackoverflow; that is to say that it might not have a .com, www or http.

Answer 1

Improvement on the accepted answer...

• Has double escaping for backslashes (\\)
• Ensures that domains have a dot and an extension (.com .io .xyz)
• Allows full colon (:) in the path e.g. http://thingiverse.com/download:1894343
• Allows ampersand (&) in path e.g http://en.wikipedia.org/wiki/Procter_&_Gamble

• Allows @ symbol in path e.g. https://medium.com/@techytimo

  isURL(str) {
    var pattern = new RegExp('^(https?:\\/\\/)?'+ // protocol
    '((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|'+ // domain name and extension
    '((\\d{1,3}\\.){3}\\d{1,3}))'+ // OR ip (v4) address
    '(\\:\\d+)?'+ // port
    '(\\/[-a-z\\d%@_.~+&:]*)*'+ // path
    '(\\?[;&a-z\\d%@_.,~+&:=-]*)?'+ // query string
    '(\\#[-a-z\\d_]*)?$','i'); // fragment locator
    return pattern.test(str);
  }
  

Answer 2

Here is yet another method.

var elm;
function isValidURL(u){
  if(!elm){
    elm = document.createElement('input');
    elm.setAttribute('type', 'url');
  }
  elm.value = u;
  return elm.validity.valid;
}

console.log(isValidURL('http://www.google.com/'));
console.log(isValidURL('//google.com'));
console.log(isValidURL('google.com'));
console.log(isValidURL('localhost:8000'));

Answer 3

(I don't have reps to comment on ValidURL example; hence post this as an answer.)

While use of protocol relative URLs is not encouraged (The Protocol-relative URL), they do get employed sometimes. To validate such an URL with a regular expression the protocol part could be optional, e.g.:

function isValidURL(str) {
    var pattern = new RegExp('^((https?:)?\\/\\/)?'+ // protocol
        '(?:\\S+(?::\\S*)?@)?' + // authentication
        '((([a-z\\d]([a-z\\d-]*[a-z\\d])*)\\.)+[a-z]{2,}|'+ // domain name
        '((\\d{1,3}\\.){3}\\d{1,3}))'+ // OR ip (v4) address
        '(\\:\\d+)?(\\/[-a-z\\d%_.~+]*)*'+ // port and path
        '(\\?[;&a-z\\d%_.~+=-]*)?'+ // query string
        '(\\#[-a-z\\d_]*)?$','i'); // fragment locater
    if (!pattern.test(str)) {
        return false;
    } else {
        return true;
    }
}

As others noted, regular expression does not seem to be the best suited approach for validating URLs, though.

Answer 4

I can't comment on the post that is the closest #5717133, but below is the way I figured out how to get @tom-gullen regex working.

/^(https?:\/\/)?((([a-z\d]([a-z\d-]*[a-z\d])*)\.)+[a-z]{2,}|((\d{1,3}\.){3}\d{1,3}))(\:\d+)?(\/[-a-z\d%_.~+]*)*(\?[;&a-z\d%_.~+=-]*)?(\#[-a-z\d_]*)?$/i

Answer 5

To Validate Url using javascript is shown below

function ValidURL(str) {
  var regex = /(http|https):\/\/(\w+:{0,1}\w*)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%!\-\/]))?/;
  if(!regex .test(str)) {
    alert("Please enter valid URL.");
    return false;
  } else {
    return true;
  }
}

Answer 6

This seems to be one of the hardest problems in CS ;)

Here's another incomplete solution that works well enough for me and better than the others I've seen here. I'm using a input[type=url] for this in order to support IE11, otherwise it would be much simpler using window.URL to perform the validation instead:

const ipv4Regex = /^(\d{1,3}\.){3}\d{1,3}$/;
function isValidIpv4(ip) {
  if (!ipv4Regex.test(ip)) return false;
  return !ip.split('.').find(n => n > 255);
}

const domainRegex = /(?:[a-z0-9-]{1,63}\.){1,125}[a-z]{2,63}$/i;
function isValidDomain(domain) {
  return isValidIpv4(domain) || domainRegex.test(domain);
}

let input;
function validateUrl(url) {
  if (! /^https?:\/\//.test(url)) url = `http://${url}`; // assuming Babel is used
  // to support IE11 we'll resort to input[type=url] instead of window.URL:
  // try { return isValidDomain(new URL(url).host) && url; } catch(e) { return false; }
  if (!input) { input = document.createElement('input'); input.type = 'url'; }
  input.value = url;
  if (! input.validity.valid) return false;
  const domain = url.split(/^https?:\/\//)[1].split('/')[0].split('@').pop();
  return isValidDomain(domain) && url;
}

console.log(validateUrl('google'), // false
  validateUrl('user:[e-mail]'),
  validateUrl('https://google.com'),
  validateUrl('100.100.100.100/abc'),
  validateUrl('100.100.100.256/abc')); // false

In order to accept incomplete inputs such as "www.mydomain.com" it will also make it valid assuming the protocol is "http" in those cases and returning the valid URL if the address is valid. It returns false when invalid.

It also supports IPv4 domains, but not IPv6.