How to replace plain URLs with links?

Question

I am using the function below to match URLs inside a given text and replace them for HTML links. The regular expression is working great, but currently I am only replacing t

Answer 1

Try Below Solution

function replaceLinkClickableLink(url = '') {
let pattern = new RegExp('^(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');

let isUrl = pattern.test(url);
if (isUrl) {
    return `<a href="${url}" target="_blank">${url}</a>`;
}
return url;
}

Answer 2

Here's my solution:

var content = "Visit https://wwww.google.com or watch this video: https://www.youtube.com/watch?v=0T4DQYgsazo and news at http://www.bbc.com";
content = replaceUrlsWithLinks(content, "http://");
content = replaceUrlsWithLinks(content, "https://");

function replaceUrlsWithLinks(content, protocol) {
    var startPos = 0;
    var s = 0;

    while (s < content.length) {
        startPos = content.indexOf(protocol, s);

        if (startPos < 0)
            return content;

        let endPos = content.indexOf(" ", startPos + 1);

        if (endPos < 0)
            endPos = content.length;

        let url = content.substr(startPos, endPos - startPos);

        if (url.endsWith(".") || url.endsWith("?") || url.endsWith(",")) {
            url = url.substr(0, url.length - 1);
            endPos--;
        }

        if (ROOTNS.utils.stringsHelper.validUrl(url)) {
            let link = "<a href='" + url + "'>" + url + "</a>";
            content = content.substr(0, startPos) + link + content.substr(endPos);
            s = startPos + link.length;
        } else {
            s = endPos + 1;
        }
    }

    return content;
}

function validUrl(url) {
    try {
        new URL(url);
        return true;
    } catch (e) {
        return false;
    }
}

Answer 3

I've made some small modifications to Travis's code (just to avoid any unnecessary redeclaration - but it's working great for my needs, so nice job!):

function linkify(inputText) {
    var replacedText, replacePattern1, replacePattern2, replacePattern3;

    //URLs starting with http://, https://, or ftp://
    replacePattern1 = /(\b(https?|ftp):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/gim;
    replacedText = inputText.replace(replacePattern1, '<a href="$1" target="_blank">$1</a>');

    //URLs starting with "www." (without // before it, or it'd re-link the ones done above).
    replacePattern2 = /(^|[^\/])(www\.[\S]+(\b|$))/gim;
    replacedText = replacedText.replace(replacePattern2, '$1<a href="http://$2" target="_blank">$2</a>');

    //Change email addresses to mailto:: links.
    replacePattern3 = /(([a-zA-Z0-9\-\_\.])+@[a-zA-Z\_]+?(\.[a-zA-Z]{2,6})+)/gim;
    replacedText = replacedText.replace(replacePattern3, '<a href="mailto:$1">$1</a>');

    return replacedText;
}

Answer 4

If you need to show shorter link (only domain), but with same long URL, you can try my modification of Sam Hasler's code version posted above

function replaceURLWithHTMLLinks(text) {
    var exp = /(\b(https?|ftp|file):\/\/([-A-Z0-9+&@#%?=~_|!:,.;]*)([-A-Z0-9+&@#%?\/=~_|!:,.;]*)[-A-Z0-9+&@#\/%=~_|])/ig;
    return text.replace(exp, "<a href='$1' target='_blank'>$3</a>");
}

Answer 5

Keep it simple! Say what you cannot have, rather than what you can have :)

As mentioned above, URLs can be quite complex, especially after the '?', and not all of them start with a 'www.' e.g. maps.bing.com/something?key=!"£$%^*()&lat=65&lon&lon=20

So, rather than have a complex regex that wont meet all edge cases, and will be hard to maintain, how about this much simpler one, which works well for me in practise.

Match

http(s):// (anything but a space)+

www. (anything but a space)+

Where 'anything' is [^'"<>\s] ... basically a greedy match, carrying on to you meet a space, quote, angle bracket, or end of line

Also:

Remember to check that it is not already in URL format, e.g. the text contains href="..." or src="..."

Add ref=nofollow (if appropriate)

This solution isn't as "good" as the libraries mentioned above, but is much simpler, and works well in practise.

if html.match( /(href)|(src)/i )) {
    return html; // text already has a hyper link in it
    }

html = html.replace( 
            /\b(https?:\/\/[^\s\(\)\'\"\<\>]+)/ig, 
            "<a ref='nofollow' href='$1'>$1</a>" 
            );

html = html.replace( 
            /\s(www\.[^\s\(\)\'\"\<\>]+)/ig, 
            "<a ref='nofollow' href='http://$1'>$1</a>" 
            );

html = html.replace( 
             /^(www\.[^\s\(\)\'\"\<\>]+)/ig, 
            "<a ref='nofollow' href='http://$1'>$1</a>" 
            );

return html;

Answer 6

After input from several sources I've now a solution that works well. It had to do with writing your own replacement code.

Answer.

Fiddle.

function replaceURLWithHTMLLinks(text) {
    var re = /(\(.*?)?\b((?:https?|ftp|file):\/\/[-a-z0-9+&@#\/%?=~_()|!:,.;]*[-a-z0-9+&@#\/%=~_()|])/ig;
    return text.replace(re, function(match, lParens, url) {
        var rParens = '';
        lParens = lParens || '';

        // Try to strip the same number of right parens from url
        // as there are left parens.  Here, lParenCounter must be
        // a RegExp object.  You cannot use a literal
        //     while (/\(/g.exec(lParens)) { ... }
        // because an object is needed to store the lastIndex state.
        var lParenCounter = /\(/g;
        while (lParenCounter.exec(lParens)) {
            var m;
            // We want m[1] to be greedy, unless a period precedes the
            // right parenthesis.  These tests cannot be simplified as
            //     /(.*)(\.?\).*)/.exec(url)
            // because if (.*) is greedy then \.? never gets a chance.
            if (m = /(.*)(\.\).*)/.exec(url) ||
                    /(.*)(\).*)/.exec(url)) {
                url = m[1];
                rParens = m[2] + rParens;
            }
        }
        return lParens + "<a href='" + url + "'>" + url + "</a>" + rParens;
    });
}