Extract hostname name from string – Dev

The best answers to the question “Extract hostname name from string” in the category Dev.

QUESTION:

I would like to match just the root of a URL and not the whole URL from a text string. Given:

http://www.youtube.com/watch?v=ClkQA2Lb_iE

http://www.example.com/12xy45
http://example.com/random

I want to get the 2 last instances resolving to the www.example.com or example.com domain.

I heard regex is slow and this would be my second regex expression on the page so If there is anyway to do it without regex let me know.

I’m seeking a JS/jQuery version of this solution.

ANSWER:

I recommend using the npm package psl (Public Suffix List). The “Public Suffix List” is a list of all valid domain suffixes and rules, not just Country Code Top-Level domains, but unicode characters as well that would be considered the root domain (i.e. www.食狮.公司.cn, b.c.kobe.jp, etc.). Read more about it here.

Try:

npm install --save psl

Then with my “extractHostname” implementation run:

let psl = require('psl');
let url="http://www.youtube.com/watch?v=ClkQA2Lb_iE";
psl.get(extractHostname(url)); // returns youtube.com

I can’t use an npm package, so below only tests extractHostname.

function extractHostname(url) {
    var hostname;
    //find & remove protocol (http, ftp, etc.) and get hostname

    if (url.indexOf("//") > -1) {
        hostname = url.split("https://stackoverflow.com/")[2];
    }
    else {
        hostname = url.split("https://stackoverflow.com/")[0];
    }

    //find & remove port number
    hostname = hostname.split(':')[0];
    //find & remove "?"
    hostname = hostname.split('?')[0];

    return hostname;
}

//test the code
console.log("== Testing extractHostname: ==");
console.log(extractHostname("http://www.blog.classroom.me.uk/index.php"));
console.log(extractHostname("http://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractHostname("https://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractHostname("www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractHostname("ftps://ftp.websitename.com/dir/file.txt"));
console.log(extractHostname("websitename.com:1234/dir/file.txt"));
console.log(extractHostname("ftps://websitename.com:1234/dir/file.txt"));
console.log(extractHostname("example.com?param=value"));
console.log(extractHostname("https://facebook.github.io/jest/"));
console.log(extractHostname("//youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractHostname("http://localhost:4200/watch?v=ClkQA2Lb_iE"));

// Warning: you can use this function to extract the "root" domain, but it will not be as accurate as using the psl package.

function extractRootDomain(url) {
    var domain = extractHostname(url),
        splitArr = domain.split('.'),
        arrLen = splitArr.length;

    //extracting the root domain here
    //if there is a subdomain 
    if (arrLen > 2) {
        domain = splitArr[arrLen - 2] + '.' + splitArr[arrLen - 1];
        //check to see if it's using a Country Code Top Level Domain (ccTLD) (i.e. ".me.uk")
        if (splitArr[arrLen - 2].length == 2 && splitArr[arrLen - 1].length == 2) {
            //this is using a ccTLD
            domain = splitArr[arrLen - 3] + '.' + domain;
        }
    }
    return domain;
}

//test extractRootDomain
console.log("== Testing extractRootDomain: ==");
console.log(extractRootDomain("http://www.blog.classroom.me.uk/index.php"));
console.log(extractRootDomain("http://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomain("https://www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomain("www.youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomain("ftps://ftp.websitename.com/dir/file.txt"));
console.log(extractRootDomain("websitename.co.uk:1234/dir/file.txt"));
console.log(extractRootDomain("ftps://websitename.com:1234/dir/file.txt"));
console.log(extractRootDomain("example.com?param=value"));
console.log(extractRootDomain("https://facebook.github.io/jest/"));
console.log(extractRootDomain("//youtube.com/watch?v=ClkQA2Lb_iE"));
console.log(extractRootDomain("http://localhost:4200/watch?v=ClkQA2Lb_iE"));

Regardless having the protocol or even port number, you can extract the domain. This is a very simplified, non-regex solution, so I think this will do.

*Thank you @Timmerz, @renoirb, @rineez, @BigDong, @ra00l, @ILikeBeansTacos, @CharlesRobertson for your suggestions! @ross-allen, thank you for reporting the bug!

ANSWER:

A neat trick without using regular expressions:

var tmp        = document.createElement ('a');
;   tmp.href   = "http://www.example.com/12xy45";

// tmp.hostname will now contain 'www.example.com'
// tmp.host will now contain hostname and port 'www.example.com:80'

Wrap the above in a function such as the below and you have yourself a superb way of snatching the domain part out of an URI.

function url_domain(data) {
  var    a      = document.createElement('a');
         a.href = data;
  return a.hostname;
}

ANSWER:

Try this:

var matches = url.match(/^https?\:\/\/([^\/?#]+)(?:[\/?#]|$)/i);
var domain = matches && matches[1];  // domain will be null if no match is found

If you want to exclude the port from your result, use this expression instead:

/^https?\:\/\/([^\/:?#]+)(?:[\/:?#]|$)/i

Edit: To prevent specific domains from matching, use a negative lookahead. (?!youtube.com)

/^https?\:\/\/(?!(?:www\.)?(?:youtube\.com|youtu\.be))([^\/:?#]+)(?:[\/:?#]|$)/i

ANSWER:

There is no need to parse the string, just pass your URL as an argument to URL constructor:

const url="http://www.youtube.com/watch?v=ClkQA2Lb_iE";
const { hostname } = new URL(url);

console.assert(hostname === 'www.youtube.com');