CODEWITHSUNDEEP
javascriptregex
Sergio del Amo
Sergio del Amo

Reputation: 78096

How to replace plain URLs with links?

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 the first match.

How I can replace all the URL? I guess I should be using the exec command, but I did not really figure how to do it.

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

Upvotes: 493

Views: 302141

Answers (26)

Elice Palasara
Elice Palasara

Reputation: 11

export function replaceLinkText(input) {
    const regex = /{"([^"]+)"\|\| ([^}]+)}/g;
    const result = [];
    let lastIndex = 0;
    let match;

    while ((match = regex.exec(input)) !== null) {
      // Push the text before the match
      if (match.index > lastIndex) {
        result.push(input.substring(lastIndex, match.index));
      }

    // Push the matched link
      const displayText = match[1];
      const url = match[2];
      result.push(
        <a href={url} target="_blank" rel="noopener noreferrer" key={url}>
          {displayText}
        </a>
      );

    // Update the last index to the end of the current match
      lastIndex = match.index + match[0].length;
    }

    // Push the remaining text after the last match
    if (lastIndex < input.length) {
      result.push(input.substring(lastIndex));
    }

    return result;
  }

Upvotes: 0

Danial Nazari
Danial Nazari

Reputation: 499

worked for me :

var urlRegex =/(\b((https?|ftp|file):\/\/)?((([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_]*)?)/ig;

return text.replace(urlRegex, function(url) {
    var newUrl = url.indexOf("http") === -1 ? "http://" + url : url;
    return '<a href="' + newUrl + '">' + url + '</a>';
});

Upvotes: 0

Zuhair Taha
Zuhair Taha

Reputation: 3032

/**
 * Convert URLs in a string to anchor buttons
 * @param {!string} string
 * @returns {!string}
 */

function URLify(string){
  var urls = string.match(/(((ftp|https?):\/\/)[\-\w@:%_\+.~#?,&\/\/=]+)/g);
  if (urls) {
    urls.forEach(function (url) {
      string = string.replace(url, '<a target="_blank" href="' + url + '">' + url + "</a>");
    });
  }
  return string.replace("(", "<br/>(");
}

simple example

Upvotes: 9

Rahul Hirve
Rahul Hirve

Reputation: 1139

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;
}

Upvotes: 1

Moonis Abidi
Moonis Abidi

Reputation: 699

Try the below function :

function anchorify(text){
  var exp = /(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;
  var text1=text.replace(exp, "<a href='$1'>$1</a>");
  var exp2 =/(^|[^\/])(www\.[\S]+(\b|$))/gim;
  return text1.replace(exp2, '$1<a target="_blank" href="http://$2">$2</a>');
}

alert(anchorify("Hola amigo! https://www.sharda.ac.in/academics/"));

Upvotes: 4

Johann
Johann

Reputation: 29867

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;
    }
}

Upvotes: 1

Alex C.
Alex C.

Reputation: 4081

I've wrote yet another JavaScript library, it might be better for you since it's very sensitive with the least possible false positives, fast and small in size. I'm currently actively maintaining it so please do test it in the demo page and see how it would work for you.

link: https://github.com/alexcorvi/anchorme.js

Upvotes: 2

Dan Dascalescu
Dan Dascalescu

Reputation: 151926

First off, rolling your own regexp to parse URLs is a terrible idea. You must imagine this is a common enough problem that someone has written, debugged and tested a library for it, according to the RFCs. URIs are complex - check out the code for URL parsing in Node.js and the Wikipedia page on URI schemes.

There are a ton of edge cases when it comes to parsing URLs: international domain names, actual (.museum) vs. nonexistent (.etc) TLDs, weird punctuation including parentheses, punctuation at the end of the URL, IPV6 hostnames etc.

I've looked at a ton of libraries, and there are a few worth using despite some downsides:

Libraries that I've disqualified quickly for this task:

If you insist on a regular expression, the most comprehensive is the URL regexp from Component, though it will falsely detect some non-existent two-letter TLDs by looking at it.

Upvotes: 402

Moritz
Moritz

Reputation: 471

The warnings about URI complexity should be noted, but the simple answer to your question is:
To replace every match you need to add the /g flag to the end of the RegEx:
/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/gi

Upvotes: 4

degenerate
degenerate

Reputation: 1417

I searched on google for anything newer and ran across this one:

$('p').each(function(){
   $(this).html( $(this).html().replace(/((http|https|ftp):\/\/[\w?=&.\/-;#~%-]+(?![\w\s?&.\/;#~%"=-]*>))/g, '<a href="$1">$1</a> ') );
});

demo: http://jsfiddle.net/kachibito/hEgvc/1/

Works really well for normal links.

Upvotes: 15

Jim Liu
Jim Liu

Reputation: 372

Replace URLs in text with HTML links, ignore the URLs within a href/pre tag. https://github.com/JimLiu/auto-link

Upvotes: 0

Vitaly
Vitaly

Reputation: 3460

Correct URL detection with international domains & astral characters support is not trivial thing. linkify-it library builds regex from many conditions, and final size is about 6 kilobytes :) . It's more accurate than all libs, currently referenced in accepted answer.

See linkify-it demo to check live all edge cases and test your ones.

If you need to linkify HTML source, you should parse it first, and iterate each text token separately.

Upvotes: 3

Roshambo
Roshambo

Reputation: 2708

Made some optimizations to Travis' Linkify() code above. I also fixed a bug where email addresses with subdomain type formats would not be matched (i.e. [email protected]).

In addition, I changed the implementation to prototype the String class so that items can be matched like so:

var text = '[email protected]';
text.linkify();

'http://stackoverflow.com/'.linkify();

Anyway, here's the script:

if(!String.linkify) {
    String.prototype.linkify = function() {

        // http://, https://, ftp://
        var urlPattern = /\b(?:https?|ftp):\/\/[a-z0-9-+&@#\/%?=~_|!:,.;]*[a-z0-9-+&@#\/%=~_|]/gim;

        // www. sans http:// or https://
        var pseudoUrlPattern = /(^|[^\/])(www\.[\S]+(\b|$))/gim;

        // Email addresses
        var emailAddressPattern = /[\w.]+@[a-zA-Z_-]+?(?:\.[a-zA-Z]{2,6})+/gim;

        return this
            .replace(urlPattern, '<a href="$&">$&</a>')
            .replace(pseudoUrlPattern, '$1<a href="http://$2">$2</a>')
            .replace(emailAddressPattern, '<a href="mailto:$&">$&</a>');
    };
}

Upvotes: 78

Andrew Murphy
Andrew Murphy

Reputation: 1435

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;

Upvotes: 3

Sam Hasler
Sam Hasler

Reputation: 12616

Replacing URLs with links (Answer to the General Problem)

The regular expression in the question misses a lot of edge cases. When detecting URLs, it's always better to use a specialized library that handles international domain names, new TLDs like .museum, parentheses and other punctuation within and at the end of the URL, and many other edge cases. See the Jeff Atwood's blog post The Problem With URLs for an explanation of some of the other issues.

The best summary of URL matching libraries is in Dan Dascalescu's Answer +100
(as of Feb 2014)

"Make a regular expression replace more than one match" (Answer to the specific problem)

Add a "g" to the end of the regular expression to enable global matching:

/ig;

But that only fixes the problem in the question where the regular expression was only replacing the first match. Do not use that code.

Upvotes: 287

Travis
Travis

Reputation: 497

Thanks, this was very helpful. I also wanted something that would link things that looked like a URL -- as a basic requirement, it'd link something like www.yahoo.com, even if the http:// protocol prefix was not present. So basically, if "www." is present, it'll link it and assume it's http://. I also wanted emails to turn into mailto: links. EXAMPLE: www.yahoo.com would be converted to www.yahoo.com

Here's the code I ended up with (combination of code from this page and other stuff I found online, and other stuff I did on my own):

function Linkify(inputText) {
    //URLs starting with http://, https://, or ftp://
    var replacePattern1 = /(\b(https?|ftp):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/gim;
    var 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)
    var replacePattern2 = /(^|[^\/])(www\.[\S]+(\b|$))/gim;
    var replacedText = replacedText.replace(replacePattern2, '$1<a href="http://$2" target="_blank">$2</a>');

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

    return replacedText
}

In the 2nd replace, the (^|[^/]) part is only replacing www.whatever.com if it's not already prefixed by // -- to avoid double-linking if a URL was already linked in the first replace. Also, it's possible that www.whatever.com might be at the beginning of the string, which is the first "or" condition in that part of the regex.

This could be integrated as a jQuery plugin as Jesse P illustrated above -- but I specifically wanted a regular function that wasn't acting on an existing DOM element, because I'm taking text I have and then adding it to the DOM, and I want the text to be "linkified" before I add it, so I pass the text through this function. Works great.

Upvotes: 27

cloud8421
cloud8421

Reputation: 1797

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;
}

Upvotes: 178

Nishant Kumar
Nishant Kumar

Reputation: 6083

Reg Ex: /(\b((https?|ftp|file):\/\/|(www))[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|]*)/ig

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

Below are some tested string:

  1. Find me on to www.google.com
  2. www
  3. Find me on to www.http://www.com
  4. Follow me on : http://www.nishantwork.wordpress.com
  5. http://www.nishantwork.wordpress.com
  6. Follow me on : http://www.nishantwork.wordpress.com
  7. https://stackoverflow.com/users/430803/nishant

Note: If you don't want to pass www as valid one just use below reg ex: /(\b((https?|ftp|file):\/\/|(www))[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig

Upvotes: 4

Mike Mestnik
Mike Mestnik

Reputation: 323

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;
    });
}

Upvotes: 1

rlemon
rlemon

Reputation: 17666

This solution works like many of the others, and in fact uses the same regex as one of them, however in stead of returning a HTML String this will return a document fragment containing the A element and any applicable text nodes. 

 function make_link(string) {
    var words = string.split(' '),
        ret = document.createDocumentFragment();
    for (var i = 0, l = words.length; i < l; i++) {
        if (words[i].match(/[-a-zA-Z0-9@:%_\+.~#?&//=]{2,256}\.[a-z]{2,4}\b(\/[-a-zA-Z0-9@:%_\+.~#?&//=]*)?/gi)) {
            var elm = document.createElement('a');
            elm.href = words[i];
            elm.textContent = words[i];
            if (ret.childNodes.length > 0) {
                ret.lastChild.textContent += ' ';
            }
            ret.appendChild(elm);
        } else {
            if (ret.lastChild && ret.lastChild.nodeType === 3) {
                ret.lastChild.textContent += ' ' + words[i];
            } else {
                ret.appendChild(document.createTextNode(' ' + words[i]));
            }
        }
    }
    return ret;
}

There are some caveats, namely with older IE and textContent support.

here is a demo.

Upvotes: 6

Vebjorn Ljosa
Vebjorn Ljosa

Reputation: 18008

Identifying URLs is tricky because they are often surrounded by punctuation marks and because users frequently do not use the full form of the URL. Many JavaScript functions exist for replacing URLs with hyperlinks, but I was unable to find one that works as well as the urlize filter in the Python-based web framework Django. I therefore ported Django's urlize function to JavaScript:

https://github.com/ljosa/urlize.js

An example:

urlize('Go to SO (stackoverflow.com) and ask. <grin>', 
       {nofollow: true, autoescape: true})
=> "Go to SO (<a href="http://stackoverflow.com" rel="nofollow">stackoverflow.com</a>) and ask. &lt;grin&gt;"

The second argument, if true, causes rel="nofollow" to be inserted. The third argument, if true, escapes characters that have special meaning in HTML. See the README file.

Upvotes: 18

Artjom Kurapov
Artjom Kurapov

Reputation: 6155

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>");
}

Upvotes: 5

Christian Koch
Christian Koch

Reputation: 701

I made a change to Roshambo String.linkify() to the emailAddressPattern to recognize [email protected] addresses

if(!String.linkify) {
    String.prototype.linkify = function() {

        // http://, https://, ftp://
        var urlPattern = /\b(?:https?|ftp):\/\/[a-z0-9-+&@#\/%?=~_|!:,.;]*[a-z0-9-+&@#\/%=~_|]/gim;

        // www. sans http:// or https://
        var pseudoUrlPattern = /(^|[^\/])(www\.[\S]+(\b|$))/gim;

        // Email addresses *** here I've changed the expression ***
        var emailAddressPattern = /(([a-zA-Z0-9_\-\.]+)@[a-zA-Z_]+?(?:\.[a-zA-Z]{2,6}))+/gim;

        return this
            .replace(urlPattern, '<a target="_blank" href="$&">$&</a>')
            .replace(pseudoUrlPattern, '$1<a target="_blank" href="http://$2">$2</a>')
            .replace(emailAddressPattern, '<a target="_blank" href="mailto:$1">$1</a>');
    };
}

Upvotes: 11

Uwe Keim
Uwe Keim

Reputation: 40736

The e-mail detection in Travitron's answer above did not work for me, so I extended/replaced it with the following (C# code).

// Change e-mail addresses to mailto: links.
const RegexOptions o = RegexOptions.Multiline | RegexOptions.IgnoreCase;
const string pat3 = @"([a-zA-Z0-9_\-\.]+)@([a-zA-Z0-9_\-\.]+)\.([a-zA-Z]{2,6})";
const string rep3 = @"<a href=""mailto:$1@$2.$3"">$1@$2.$3</a>";
text = Regex.Replace(text, pat3, rep3, o);

This allows for e-mail addresses like "[email protected]".

Upvotes: 1

Tiago Fischer
Tiago Fischer

Reputation: 145

The best script to do this: http://benalman.com/projects/javascript-linkify-process-lin/

Upvotes: 7

Reece
Reece

Reputation:

I had to do the opposite, and make html links into just the URL, but I modified your regex and it works like a charm, thanks :) 

var exp = /<a\s.*href=['"](\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])['"].*>.*<\/a>/ig;

source = source.replace(exp,"$1");

Upvotes: 1

Related Questions