Detect URLs in text with JavaScript
Solution 1:
First you need a good regex that matches urls. This is hard to do. See here, here and here:
...almost anything is a valid URL. There are some punctuation rules for splitting it up. Absent any punctuation, you still have a valid URL.
Check the RFC carefully and see if you can construct an "invalid" URL. The rules are very flexible.
For example
:::::is a valid URL. The path is":::::". A pretty stupid filename, but a valid filename.Also,
/////is a valid URL. The netloc ("hostname") is"". The path is"///". Again, stupid. Also valid. This URL normalizes to"///"which is the equivalent.Something like
"bad://///worse/////"is perfectly valid. Dumb but valid.
Anyway, this answer is not meant to give you the best regex but rather a proof of how to do the string wrapping inside the text, with JavaScript.
OK so lets just use this one: /(https?:\/\/[^\s]+)/g
Again, this is a bad regex. It will have many false positives. However it's good enough for this example.
function urlify(text) {
var urlRegex = /(https?:\/\/[^\s]+)/g;
return text.replace(urlRegex, function(url) {
return '<a href="' + url + '">' + url + '</a>';
})
// or alternatively
// return text.replace(urlRegex, '<a href="$1">$1</a>')
}
var text = 'Find me at http://www.example.com and also at http://stackoverflow.com';
var html = urlify(text);
console.log(html)// html now looks like:
// "Find me at <a href="http://www.example.com">http://www.example.com</a> and also at <a href="http://stackoverflow.com">http://stackoverflow.com</a>"
So in sum try:
$$('#pad dl dd').each(function(element) {
element.innerHTML = urlify(element.innerHTML);
});
Solution 2:
Here is what I ended up using as my regex:
var urlRegex =/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;
This doesn't include trailing punctuation in the URL. Crescent's function works like a charm :) so:
function linkify(text) {
var urlRegex =/(\b(https?|ftp|file):\/\/[-A-Z0-9+&@#\/%?=~_|!:,.;]*[-A-Z0-9+&@#\/%=~_|])/ig;
return text.replace(urlRegex, function(url) {
return '<a href="' + url + '">' + url + '</a>';
});
}
Solution 3:
I googled this problem for quite a while, then it occurred to me that there is an Android method, android.text.util.Linkify, that utilizes some pretty robust regexes to accomplish this. Luckily, Android is open source.
They use a few different patterns for matching different types of urls. You can find them all here: http://grepcode.com/file/repository.grepcode.com/java/ext/com.google.android/android/2.0_r1/android/text/util/Regex.java#Regex.0WEB_URL_PATTERN
If you're just concerned about url's that match the WEB_URL_PATTERN, that is, urls that conform to the RFC 1738 spec, you can use this:
/((?:(http|https|Http|Https|rtsp|Rtsp):\/\/(?:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,64}(?:\:(?:[a-zA-Z0-9\$\-\_\.\+\!\*\'\(\)\,\;\?\&\=]|(?:\%[a-fA-F0-9]{2})){1,25})?\@)?)?((?:(?:[a-zA-Z0-9][a-zA-Z0-9\-]{0,64}\.)+(?:(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])|(?:biz|b[abdefghijmnorstvwyz])|(?:cat|com|coop|c[acdfghiklmnoruvxyz])|d[ejkmoz]|(?:edu|e[cegrstu])|f[ijkmor]|(?:gov|g[abdefghilmnpqrstuwy])|h[kmnrtu]|(?:info|int|i[delmnoqrst])|(?:jobs|j[emop])|k[eghimnrwyz]|l[abcikrstuvy]|(?:mil|mobi|museum|m[acdghklmnopqrstuvwxyz])|(?:name|net|n[acefgilopruz])|(?:org|om)|(?:pro|p[aefghklmnrstwy])|qa|r[eouw]|s[abcdeghijklmnortuvyz]|(?:tel|travel|t[cdfghjklmnoprtvwz])|u[agkmsyz]|v[aceginu]|w[fs]|y[etu]|z[amw]))|(?:(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}|[1-9][0-9]|[0-9])))(?:\:\d{1,5})?)(\/(?:(?:[a-zA-Z0-9\;\/\?\:\@\&\=\#\~\-\.\+\!\*\'\(\)\,\_])|(?:\%[a-fA-F0-9]{2}))*)?(?:\b|$)/gi;
Here is the full text of the source:
"((?:(http|https|Http|Https|rtsp|Rtsp):\\/\\/(?:(?:[a-zA-Z0-9\\$\\-\\_\\.\\+\\!\\*\\'\\(\\)"
+ "\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,64}(?:\\:(?:[a-zA-Z0-9\\$\\-\\_"
+ "\\.\\+\\!\\*\\'\\(\\)\\,\\;\\?\\&\\=]|(?:\\%[a-fA-F0-9]{2})){1,25})?\\@)?)?"
+ "((?:(?:[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}\\.)+" // named host
+ "(?:" // plus top level domain
+ "(?:aero|arpa|asia|a[cdefgilmnoqrstuwxz])"
+ "|(?:biz|b[abdefghijmnorstvwyz])"
+ "|(?:cat|com|coop|c[acdfghiklmnoruvxyz])"
+ "|d[ejkmoz]"
+ "|(?:edu|e[cegrstu])"
+ "|f[ijkmor]"
+ "|(?:gov|g[abdefghilmnpqrstuwy])"
+ "|h[kmnrtu]"
+ "|(?:info|int|i[delmnoqrst])"
+ "|(?:jobs|j[emop])"
+ "|k[eghimnrwyz]"
+ "|l[abcikrstuvy]"
+ "|(?:mil|mobi|museum|m[acdghklmnopqrstuvwxyz])"
+ "|(?:name|net|n[acefgilopruz])"
+ "|(?:org|om)"
+ "|(?:pro|p[aefghklmnrstwy])"
+ "|qa"
+ "|r[eouw]"
+ "|s[abcdeghijklmnortuvyz]"
+ "|(?:tel|travel|t[cdfghjklmnoprtvwz])"
+ "|u[agkmsyz]"
+ "|v[aceginu]"
+ "|w[fs]"
+ "|y[etu]"
+ "|z[amw]))"
+ "|(?:(?:25[0-5]|2[0-4]" // or ip address
+ "[0-9]|[0-1][0-9]{2}|[1-9][0-9]|[1-9])\\.(?:25[0-5]|2[0-4][0-9]"
+ "|[0-1][0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1]"
+ "[0-9]{2}|[1-9][0-9]|[1-9]|0)\\.(?:25[0-5]|2[0-4][0-9]|[0-1][0-9]{2}"
+ "|[1-9][0-9]|[0-9])))"
+ "(?:\\:\\d{1,5})?)" // plus option port number
+ "(\\/(?:(?:[a-zA-Z0-9\\;\\/\\?\\:\\@\\&\\=\\#\\~" // plus option query params
+ "\\-\\.\\+\\!\\*\\'\\(\\)\\,\\_])|(?:\\%[a-fA-F0-9]{2}))*)?"
+ "(?:\\b|$)";
If you want to be really fancy, you can test for email addresses as well. The regex for email addresses is:
/[a-zA-Z0-9\\+\\.\\_\\%\\-]{1,256}\\@[a-zA-Z0-9][a-zA-Z0-9\\-]{0,64}(\\.[a-zA-Z0-9][a-zA-Z0-9\\-]{0,25})+/gi
PS: The top level domains supported by above regex are current as of June 2007. For an up to date list you'll need to check https://data.iana.org/TLD/tlds-alpha-by-domain.txt.
Solution 4:
Based on Crescent Fresh answer
if you want to detect links with http:// OR without http:// and by www. you can use the following
function urlify(text) {
var urlRegex = /(((https?:\/\/)|(www\.))[^\s]+)/g;
//var urlRegex = /(https?:\/\/[^\s]+)/g;
return text.replace(urlRegex, function(url,b,c) {
var url2 = (c == 'www.') ? 'http://' +url : url;
return '<a href="' +url2+ '" target="_blank">' + url + '</a>';
})
}