How to get search query from the hash in the URL - javascript

I am adding a Search feature, and if the user is on the search results and they refresh the page I want it to stay at that search. I already put the search query into the URL, but I don't know how to retrieve it. It will most likely require a regexp so anyone that is experienced with regexp, please help.
Here is how I put it into the URL:
function trimspace(str) {
str = str.replace(/ +(?= )/g, '');
return str;
}
function searchMail() {
var query = trimspace($('#search_input').val());
if (query == '' || !query || query == null) {
$('#search_input').focus();
}
else {
window.location.hash = '#!/search/' + query;
$('#loader').show();
$.get('tools.php?type=search', { q: query }, function(data, textStatus) {
$('#loader').hide();
if (textStatus == 'success') {
hideAllTabs();
$('#search_results').html(data).show();
document.title = "Search results - WeeBuild Mail";
}
else {
alertBox('Search failed. Please try again in a few minutes.', 2500);
}
});
}
}
And besides just retreiving the query I need to be able to detect if the hash is #!/search/query.
Thanks in advance!


Detect if query is #!/search/query:
location.hash==='#!/search/query'
Finding out about the query parts assuming the query is #!/search/query:
var parts = location.hash.split('/');
parts[0] is #!. parts[1] is search and parts[2] is test. Doing with the parts want you want should now be trivial enough.
In response to the comments:
function getPartAndRemainder(){
var parts = location.hash.split('/');
if(parts[0]!=='#!' || parts.length<2){
// Value after # does not follow the expected pattern #!/part/any_parameters
throw new Error('Cannot parse application part.');
}
return {
// Contains the part of your application (word after first slash after #)
part: parts[1],
// Contains everything after second slash after # or the empty string
remainder: location.hash.substring(
// Length of #! (or whatever somebody might use instead)
parts[0].length
// Length of first slash
+1
// Length of your application part's name
+parts[1].length
// Length of the second slash
+1)
};
}
The function gives back an object that contains the part of your application at the key part and the remainder key will contain the rest. So, if your URI would be something#!/search/test the function would return {part:'search', remainder:'test'}.
In case the URI can't be parsed, you'll get an error and you should then use a sensible default instead.
You would use the method as follows whenever the hash changes or at some other event (point in time) where you are interested in the hash value:
try {
var hashValue = getPartAndRemainder();
if(hashValue.part==='search'){
var query = hashValue.remainder;
alert('You searched: '+query)
}
if(hashValue.part==='inbox'){
alert('You are in inbox, now');
}
} catch(e){
// It was not possible to parse the value after the # from URI according to our expected pattern.
alert('No idea what to do with: '+location.hash);
}


This regex will match anything after the search param, is this what you are looking for?
/#1/search/(.*)/


var match = /\/.*\/.*\/(.*)\//i.exec(location.hash)
//match contain the query

Related

Complete url validation angular [duplicate]

I want to validate a URL and display message. Below is my code:
$("#pageUrl").keydown(function(){
$(".status").show();
var url = $("#pageUrl").val();
if(isValidURL(url)){
$.ajax({
type: "POST",
url: "demo.php",
data: "pageUrl="+ url,
success: function(msg){
if(msg == 1 ){
$(".status").html('<img src="images/success.gif"/><span><strong>SiteID:</strong>12345678901234456</span>');
}else{
$(".status").html('<img src="images/failure.gif"/>');
}
}
});
}else{
$(".status").html('<img src="images/failure.gif"/>');
}
});
function isValidURL(url){
var RegExp = /(ftp|http|https):\/\/(\w+:{0,1}\w*#)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%#!\-\/]))?/;
if(RegExp.test(url)){
return true;
}else{
return false;
}
}
My problem is now it will show an error message even when entering a proper URL until it matches regular expression, and it return true even if the URL is something like "http://wwww".
I appreciate your suggestions.

Someone mentioned the Jquery Validation plugin, seems overkill if you just want to validate the url, here is the line of regex from the plugin:
return this.optional(element) || /^(https?|ftp):\/\/(((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:)*#)?(((\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5]))|((([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.)+(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.?)(:\d*)?)(\/((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)+(\/(([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)*)*)?)?(\?((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)|[\uE000-\uF8FF]|\/|\?)*)?(\#((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)|\/|\?)*)?$/i.test(value);
Here is where they got it from: http://projects.scottsplayground.com/iri/
Pointed out by #nhahtdh This has been updated to:
// Copyright (c) 2010-2013 Diego Perini, MIT licensed
// https://gist.github.com/dperini/729294
// see also https://mathiasbynens.be/demo/url-regex
// modified to allow protocol-relative URLs
return this.optional( element ) || /^(?:(?:(?:https?|ftp):)?\/\/)(?:\S+(?::\S*)?#)?(?:(?!(?:10|127)(?:\.\d{1,3}){3})(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)(?:\.(?:[a-z\u00a1-\uffff0-9]-*)*[a-z\u00a1-\uffff0-9]+)*(?:\.(?:[a-z\u00a1-\uffff]{2,})).?)(?::\d{2,5})?(?:[/?#]\S*)?$/i.test( value );
source: https://github.com/jzaefferer/jquery-validation/blob/c1db10a34c0847c28a5bd30e3ee1117e137ca834/src/core.js#L1349

It's not practical to parse URLs using regex. A full implementation of the RFC1738 rules would result in an enormously long regex (assuming it's even possible). Certainly your current expression fails many valid URLs, and passes invalid ones.
Instead:
a. use a proper URL parser that actually follows the real rules. (I don't know of one for JavaScript; it would probably be overkill. You could do it on the server side though). Or,
b. just trim away any leading or trailing spaces, then check it has one of your preferred schemes on the front (typically ‘http://’ or ‘https://’), and leave it at that. Or,
c. attempt to use the URL and see what lies at the end, for example by sending it am HTTP HEAD request from the server-side. If you get a 404 or connection error, it's probably wrong.
it return true even if url is something like "http://wwww".
Well, that is indeed a perfectly valid URL.
If you want to check whether a hostname such as ‘wwww’ actually exists, you have no choice but to look it up in the DNS. Again, this would be server-side code.

function validateURL(textval) {
var urlregex = /^(https?|ftp):\/\/([a-zA-Z0-9.-]+(:[a-zA-Z0-9.&%$-]+)*#)*((25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9][0-9]?)(\.(25[0-5]|2[0-4][0-9]|1[0-9]{2}|[1-9]?[0-9])){3}|([a-zA-Z0-9-]+\.)*[a-zA-Z0-9-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(:[0-9]+)*(\/($|[a-zA-Z0-9.,?'\\+&%$#=~_-]+))*$/;
return urlregex.test(textval);
}
This can return true for URLs like:
http://stackoverflow.com/questions/1303872/url-validation-using-javascript
or:
http://regexlib.com/DisplayPatterns.aspx?cattabindex=1&categoryId=2

I written also a URL validation function base on rfc1738 and rfc3986 to check http and https urls. I try to hold this modular, so it can be better maintained and adapted to own requirements.
The RegExp in one line is show at end of this post.
The RegExp accept HTTP and HTTPS URLs with some international domain or IPv4 number. IPv6 is not supported yet.
window.isValidURL = (function() {// wrapped in self calling function to prevent global pollution
//URL pattern based on rfc1738 and rfc3986
var rg_pctEncoded = "%[0-9a-fA-F]{2}";
var rg_protocol = "(http|https):\\/\\/";
var rg_userinfo = "([a-zA-Z0-9$\\-_.+!*'(),;:&=]|" + rg_pctEncoded + ")+" + "#";
var rg_decOctet = "(25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])"; // 0-255
var rg_ipv4address = "(" + rg_decOctet + "(\\." + rg_decOctet + "){3}" + ")";
var rg_hostname = "([a-zA-Z0-9\\-\\u00C0-\\u017F]+\\.)+([a-zA-Z]{2,})";
var rg_port = "[0-9]+";
var rg_hostport = "(" + rg_ipv4address + "|localhost|" + rg_hostname + ")(:" + rg_port + ")?";
// chars sets
// safe = "$" | "-" | "_" | "." | "+"
// extra = "!" | "*" | "'" | "(" | ")" | ","
// hsegment = *[ alpha | digit | safe | extra | ";" | ":" | "#" | "&" | "=" | escape ]
var rg_pchar = "a-zA-Z0-9$\\-_.+!*'(),;:#&=";
var rg_segment = "([" + rg_pchar + "]|" + rg_pctEncoded + ")*";
var rg_path = rg_segment + "(\\/" + rg_segment + ")*";
var rg_query = "\\?" + "([" + rg_pchar + "/?]|" + rg_pctEncoded + ")*";
var rg_fragment = "\\#" + "([" + rg_pchar + "/?]|" + rg_pctEncoded + ")*";
var rgHttpUrl = new RegExp(
"^"
+ rg_protocol
+ "(" + rg_userinfo + ")?"
+ rg_hostport
+ "(\\/"
+ "(" + rg_path + ")?"
+ "(" + rg_query + ")?"
+ "(" + rg_fragment + ")?"
+ ")?"
+ "$"
);
// export public function
return function (url) {
if (rgHttpUrl.test(url)) {
return true;
} else {
return false;
}
};
})();
RegExp in one line:
var rg = /^(http|https):\/\/(([a-zA-Z0-9$\-_.+!*'(),;:&=]|%[0-9a-fA-F]{2})+#)?(((25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])(\.(25[0-5]|2[0-4][0-9]|[0-1][0-9][0-9]|[1-9][0-9]|[0-9])){3})|localhost|([a-zA-Z0-9\-\u00C0-\u017F]+\.)+([a-zA-Z]{2,}))(:[0-9]+)?(\/(([a-zA-Z0-9$\-_.+!*'(),;:#&=]|%[0-9a-fA-F]{2})*(\/([a-zA-Z0-9$\-_.+!*'(),;:#&=]|%[0-9a-fA-F]{2})*)*)?(\?([a-zA-Z0-9$\-_.+!*'(),;:#&=\/?]|%[0-9a-fA-F]{2})*)?(\#([a-zA-Z0-9$\-_.+!*'(),;:#&=\/?]|%[0-9a-fA-F]{2})*)?)?$/;

In a similar situation I got away with this:
someUtils.validateURL = function(url) {
var parser = document.createElement('a');
try {
parser.href = url;
return !!parser.hostname;
} catch (e) {
return false;
}
};
i.e. why invent the wheel if browsers can do it for you? But, of course, this will only work in the browser.
there are various parts of parsed URL exactly how browser would interpret it:
parser.protocol; // => "http:"
parser.hostname; // => "example.com"
parser.port; // => "8080"
parser.pathname; // => "/path/"
parser.search; // => "?search=test"
parser.hash; // => "#hash"
parser.host; // => "example.com:3000"
Using these you can improve your validating function depending on the requirements. The only drawback is that it will accept relative URLs and use current page server's host and port. But you can use it for your advantage, by re-assembling the URL from parts and always passing it in full to your AJAX service.
What validateURL won't accept is invalid URL, e.g. http:\:8883 will return false, but :1234 is valid and is interpreted as http://pagehost.example.com/:1234 i.e. as a relative path.
UPDATE
This approach is no longer working with Chrome and other WebKit browsers. Even when URL is invalid, hostname is filled with some value, e.g. taken from base. It still helps to parse parts of URL, but will not allow to validate one.
Possible better no-own-parser approach is to use var parsedURL = new URL(url) and catch exceptions. See e.g. URL API. Supported by all major browsers and NodeJS, although still marked experimental.

best regex I found from http://angularjs.org/
var urlregex = /^(ftp|http|https):\/\/(\w+:{0,1}\w*#)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%#!\-\/]))?$/;

This is what worked for me:
function validateURL(value) {
return /^(https?|ftp):\/\/(((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:)*#)?(((\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5])\.(\d|[1-9]\d|1\d\d|2[0-4]\d|25[0-5]))|((([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|\d|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.)+(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])*([a-z]|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])))\.?)(:\d*)?)(\/((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)+(\/(([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)*)*)?)?(\?((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)|[\uE000-\uF8FF]|\/|\?)*)?(\#((([a-z]|\d|-|\.|_|~|[\u00A0-\uD7FF\uF900-\uFDCF\uFDF0-\uFFEF])|(%[\da-f]{2})|[!\$&'\(\)\*\+,;=]|:|#)|\/|\?)*)?$/i.test(value);
}
from there is is just a matter of calling the function to get a true or false back:
validateURL(urltovalidate);

I know it's quite an old question but since it does not have any accepted answer, I suggest you to use the URI.js framework: https://github.com/medialize/URI.js
You can use it to check for malformed URI using a try/catch block:
function isValidURL(url)
{
try {
(new URI(url));
return true;
}
catch (e) {
// Malformed URI
return false;
}
}
Of course it will consider something like "%#" as a well formed relative URI... So I suggest you read the URI.js API to perform more checks, for example if you want to make sure that the user entered a well formed absolute URL you may do like this:
function isValidURL(url)
{
try {
var uri = new URI(url);
// URI has a scheme and a host
return (!!uri.scheme() && !!uri.host());
}
catch (e) {
// Malformed URI
return false;
}
}

Import in an npm package like
https://www.npmjs.com/package/valid-url
and use it to validate your url.

You can use the URL API that is recently standard. Browser support is sketchy at best, see the link. new URL(str) is guaranteed to throw TypeError for invalid URLs.
As stated above, http://wwww is a valid URL.

The URL API can be used to validate the structure of a URL string.
An error is thrown when trying to serialise an invalid URL string into a URL object. This could be abstracted into a helper function (Typescript snippet below):
function isValidURL(URL: string) : boolean {
try {
new URL(string);
return true;
} catch (err) { return false; }
}
isValidURL('https://www.google.com'); // returns true
isValidURL('localhost:3000'); // returns true
isValidURL('not-a-valid-url'); // returns false
isValidURL('google.com'); // returns false (see footnote)
If you strictly want HTTP / web links to be valid, we can simply add a condition to the return statement:
...
const url = new URL(string);
return url.protocol === 'https:' || url.protocol === 'http:';
...
Granted, this approach comes with a few caveats:
No support for the URL API in Internet Explorer (could be fixed with a polyfill)
Without additional checks, URLs without either a protocol or port are seen as invalid (e.g. google.com is invalid but google.com:3000 is OK). This may be an unintended behaviour for some usecases.

If you're looking for a more reliable regex, check out RegexLib. Here's the page you'd probably be interested in:
http://regexlib.com/Search.aspx?k=url
As for the error messages showing while the person is still typing, change the event from keydown to blur and then it will only check once the person moves to the next element.

var RegExp = (/^HTTP|HTTP|http(s)?:\/\/(www\.)?[A-Za-z0-9]+([\-\.]{1}[A-Za-z0-9]+)*\.[A-Za-z]{2,40}(:[0-9]{1,40})?(\/.*)?$/);

My solution:
function isValidUrl(t)
{
return t.match(/^(http|https|ftp):\/\/(([A-Z0-9][A-Z0-9_-]*)(\.[A-Z0-9][A-Z0-9_-]*)+)(:(\d+))?\/?/i)
}

Demo : http://jsbin.com/uzimeb/1/edit
function checkURL(value) {
var urlregex = new RegExp("^(http|https|ftp)\://([a-zA-Z0-9\.\-]+(\:[a-zA-Z0-9\.&%\$\-]+)*#)*((25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9])\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[1-9]|0)\.(25[0-5]|2[0-4][0-9]|[0-1]{1}[0-9]{2}|[1-9]{1}[0-9]{1}|[0-9])|([a-zA-Z0-9\-]+\.)*[a-zA-Z0-9\-]+\.(com|edu|gov|int|mil|net|org|biz|arpa|info|name|pro|aero|coop|museum|[a-zA-Z]{2}))(\:[0-9]+)*(/($|[a-zA-Z0-9\.\,\?\'\\\+&%\$#\=~_\-]+))*$");
if (urlregex.test(value)) {
return (true);
}
return (false);
}

I have found a great resource for comparing different solutions:
https://mathiasbynens.be/demo/url-regex
According to that page, only solution from diegoperini passes all tests. Here is that regex:
_^(?:(?:https?|ftp)://)(?:\S+(?::\S*)?#)?(?:(?!10(?:\.\d{1,3}){3})(?!127(?:\.\d{1,3}){3})(?!169\.254(?:\.\d{1,3}){2})(?!192\.168(?:\.\d{1,3}){2})(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))|(?:(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)(?:\.(?:[a-z\x{00a1}-\x{ffff}0-9]+-?)*[a-z\x{00a1}-\x{ffff}0-9]+)*(?:\.(?:[a-z\x{00a1}-\x{ffff}]{2,})))(?::\d{2,5})?(?:/[^\s]*)?$_iuS

I checked a lot of url validators in google and no one works for me. For example I'd like to see valid on links like 'aa.com'. I like silly check for dot sign in string.
function isValidUri(str) {
var dotIndex = str.indexOf('.');
return (dotIndex > 0 && dotIndex < str.length - 2);
}
It should not stay on beginning and end of string (for now we don't have top level domain names with one character).

Here's a regular expression which might fit the bill (it's very long):
/^(?:\u0066\u0069\u006C\u0065\u003A\u002F{2}(?:\u002F{2}(?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*\u0040)?(?:\u005B(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){6}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){5}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){4}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A)?[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){3}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,3}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,4}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,5}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,6}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2})\u005D|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?\u002E)+[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?))(?:\u003A(?:\u0030-\u0035\u0030-\u0039{0,4}|\u0036\u0030-\u0034\u0030-\u0039{3}|\u0036\u0035\u0030-\u0034\u0030-\u0039{2}|\u0036\u0035\u0035\u0030-\u0032\u0030-\u0039|\u0036\u0035\u0035\u0033\u0030-\u0035))?(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*|\u002F(?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])+(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*)?|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])+(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*)|[\u0041-\u005A\u0061-\u007A][\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002B\u002D\u002E]*\u003A(?:\u002F{2}(?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*\u0040)?(?:\u005B(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){6}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){5}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){4}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A)?[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){3}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,3}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,4}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035]))|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,5}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}|(?:(?:[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4}\u003A){0,6}[\u0030-\u0039\u0041-\u0046\u0061-\u0066]{1,4})?\u003A{2})\u005D|(?:(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])\u002E){3}(?:[\u0030-\u0039]|[\u0031-\u0039][\u0030-\u0039]|\u0031[\u0030-\u0039]{2}|\u0032[\u0030-\u0034][\u0030-\u0039]|\u0032\u0035[\u0030-\u0035])|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?\u002E)+[\u0041-\u005A\u0061-\u007A\u0030-\u0039](?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D]+)?[\u0041-\u005A\u0061-\u007A\u0030-\u0039])?))(?:\u003A(?:\u0030-\u0035\u0030-\u0039{0,4}|\u0036\u0030-\u0034\u0030-\u0039{3}|\u0036\u0035\u0030-\u0034\u0030-\u0039{2}|\u0036\u0035\u0035\u0030-\u0032\u0030-\u0039|\u0036\u0035\u0035\u0033\u0030-\u0035))?(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*|\u002F(?:(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])+(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*)?|(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])+(?:\u002F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)*)(?:\u003F(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040\u002F\u003F]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)?(?:\u0023(?:[\u0041-\u005A\u0061-\u007A\u0030-\u0039\u002D\u002E\u005F\u007E\u0021\u0024\u0026\u0027\u0028\u0029\u002A\u002B\u002C\u003B\u003D\u003A\u0040\u002F\u003F]|\u0025[\u0030-\u0039\u0041-\u0046\u0061-\u0066][\u0030-\u0039\u0041-\u0046\u0061-\u0066])*)?)$/
There are some caveats to its usage, namely it does not validate URIs which contain additional information after the user name (e.g. "username:password"). Also, only IPv6 addresses can be contained within the IP literal syntax and the "IPvFuture" syntax is currently ignored and will not validate against this regular expression. Port numbers are also constrained to be between 0 and 65,535. Also, only the file scheme can use triple slashes (e.g. "file:///etc/sysconfig") and can ignore both the query and fragment parts of a URI. Finally, it is geared towards regular URIs and not IRIs, hence the extensive focus on the ASCII character set.
This regular expression could be expanded upon, but it's already complex and long enough as it is. I also cannot guarantee it's going to be "100% accurate" or "bug free", but it should correctly validate URIs for all schemes.
You will need to do additional verification for any scheme-specific requirements or do URI normalization as this regular expression will validate a very broad range of URIs.

Try edit your isValidURL function as follows:
function isValidURL(url) {
var encodedURL = encodeURIComponent(url);
var isValid = false;
$.ajax({
url: "http://query.yahooapis.com/v1/public/yql?q=select%20*%20from%20html%20where%20url%3D%22" + encodedURL + "%22&format=json",
type: "get",
async: false,
dataType: "json",
success: function(data) {
isValid = data.query.results != null;
},
error: function(){
isValid = false;
}
});
return isValid;
}
This should do the trick.

regex detect url and prepend http:// [duplicate]

This question already has answers here:
Adding http:// to all links without a protocol
(4 answers)
Closed 8 years ago.
I would like to detect url's that are entered in a text input. I have the following code which prepends http:// to the beginning of what has been entered:
var input = $(this);
var val = input.val();
if (val && !val.match(/^http([s]?):\/\/.*/)) {
input.val('http://' + val);
}
How would I go about adapting this to only append the http:// if it contains a string followed by a tld? At the moment if I enter a string for example:
Hello. This is a test
the http:// will get appended to hello, even though it's not a url. Any help would be greatly appreciated.

This simple function works for me. We don't care about the real existence of a TLD domain to gain speed, rather we check the syntax like example.com.
Sorry, I've forgotten that VBA trim() is not intrinsic function in js, so:
// Removes leading whitespaces
function LTrim(value)
{
var re = /\s*((\S+\s*)*)/;
return value.replace(re, "$1");
}
// Removes ending whitespaces
function RTrim(value)
{
var re = /((\s*\S+)*)\s*/;
return value.replace(re, "$1");
}
// Removes leading and ending whitespaces
function trim(value)
{
return LTrim(RTrim(value));
}
function hasDomainTld(strAddress)
{
var strUrlNow = trim(strAddress);
if(strUrlNow.match(/[,\s]/))
{
return false;
}
var i, regex = new RegExp();
regex.compile("[A-Za-z0-9\-_]+\\.[A-Za-z0-9\-_]+$");
i = regex.test(strUrlNow);
regex = null;
return i;
}
So your code, $(this) is window object, so I pass the objInput through an argument, using classical js instead of jQuery:
function checkIt(objInput)
{
var val = objInput.value;
if(val.match(/http:/i)) {
return false;
}
else if (hasDomainTld(val)) {
objInput.value = 'http://' + val;
}
}
Please test yourself: http://jsfiddle.net/SDUkZ/8/

The best solution i have found is to use the following regex:
/\.[a-zA-Z]{2,3}/
This detects the . after the url, and characters for the extension with a limit of 2/3 characters.
Does this seem ok for basic validation? Please let me know if you see any problems that could arise.
I know that it will detect email address's but this wont matter in this instance.

You need to narrow down your requirements first as URL detection with regular expressions can be very tricky. These are just a few situations where your parser can fail:
IDNs (госуслуги.рф)
Punycode cases (xn--blah)
New TLD being registered (.amazon)
SEO-friendly URLs (domain.com/Everything you need to know about RegEx.aspx)
We recently faced a similar problem and what we ended up doing was a simple check whether the URL starts with either http://, https://, or ftp:// and prepending with http:// if it doesn't start with any of the mentioned schemes. Here's the implementation in TypeScript:
public static EnsureAbsoluteUri(uri: string): string {
var ret = uri || '', m = null, i = -1;
var validSchemes = ko.utils.arrayMap(['http', 'https', 'ftp'], (i) => { return i + '://' });
if (ret && ret.length) {
m = ret.match(/[a-z]+:\/\//gi);
/* Checking against a list of valid schemes and prepending with "http://" if check fails. */
if (m == null || !m.length || (i = $.inArray(m[0].toLowerCase(), validSchemes)) < 0 ||
(i >= 0 && ret.toLowerCase().indexOf(validSchemes[i]) != 0)) {
ret = 'http://' + ret;
}
}
return ret;
}
As you can see, we're not trying to be smart here as we can't predict every possible URL form. Furthermore, this method is usually executed against field values we know are meant to be URLs so the change of misdetection is minimal.
Hope this helps.

How to remove a second hash added by the user?

I am using a lot of hashes in my URL for displaying messages and stuff, but I have a problem. It is fine when you click on a conversation to read it:
But, look what happens when the user attaches another hash to the end: (the subject disappears because the JavaScript gets confused)
(Click images to view larger versions)
How can I remove that second hash if there is one? I did this in Gmail before and it automatically removed them. So, how can I do this with my system? Here's my hash code:
if (window.location.hash) {
var messageID = window.location.hash.replace('#!/message/', '');
var msgSubject = $('#subject_' + messageID).text();
//the below code checks if conversation exists
$.get('tools.php?type=id_check&id=' + messageID, function(data) {
if (data == 'true') {
setTimeout(function() {
readMessage(messageID, msgSubject);
}, 200);
}
else {
alertBox('The requested conversation does not exist.', 2500);
window.location = '#';
}
});
}
Thanks in advance!

You can try
var matches = window.location.hash.match(/#!\/message\/(\d+)/);
if (matches) {
var messageId = matches[1];
// ...
}
This will capture a series of only digits after #!/message/. If the hash contains #!/message/123, then matches will be an array
['#!/message/123', '123']
and so matches[1] will contain the message id. If there is anything before or after it in the hash, it will be ignored. If there are no matches, matches will be null.

Improving regex for parsing YouTube / Vimeo URLs

I've made a function (in JavaScript) that takes an URL from either YouTube or Vimeo. It figures out the provider and ID for that particular video (demo: http://jsfiddle.net/csjwf/).
function parseVideoURL(url) {
var provider = url.match(/http:\/\/(:?www.)?(\w*)/)[2],
id;
if(provider == "youtube") {
id = url.match(/http:\/\/(?:www.)?(\w*).com\/.*v=(\w*)/)[2];
} else if (provider == "vimeo") {
id = url.match(/http:\/\/(?:www.)?(\w*).com\/(\d*)/)[2];
} else {
throw new Error("parseVideoURL() takes a YouTube or Vimeo URL");
}
return {
provider : provider,
id : id
}
}
It works, however as a regex Novice, I'm looking for ways to improve it. The input I'm dealing with, typically looks like this:
http://vimeo.com/(id)
http://youtube.com/watch?v=(id)&blahblahblah.....
1) Right now I'm doing three separate matches, would it make sense to try and do everything in one single expression? If so, how?
2) Could the existing matches be more concise? Are they unnecessarily complex? or perhaps insufficient?
3) Are there any YouTube or Vimeo URL's that would fail being parsed? I've tried quite a few and so far it seems to work pretty well.
To summarize: I'm simply looking for ways improve the above function. Any advice is greatly appreciated.

Here's my attempt at the regex, which covers most updated cases:
function parseVideo(url) {
// - Supported YouTube URL formats:
// - http://www.youtube.com/watch?v=My2FRPA3Gf8
// - http://youtu.be/My2FRPA3Gf8
// - https://youtube.googleapis.com/v/My2FRPA3Gf8
// - Supported Vimeo URL formats:
// - http://vimeo.com/25451551
// - http://player.vimeo.com/video/25451551
// - Also supports relative URLs:
// - //player.vimeo.com/video/25451551
url.match(/(https?\/\/)(player.|www.)?(vimeo\.com|youtu(be\.com|\.be|be\.googleapis\.com))\/(video\/|embed\/|watch\?v=|v\/)?([A-Za-z0-9._%-]*)(\&\S+)?/);
var type = null;
if (RegExp.$3.indexOf('youtu') > -1) {
type = 'youtube';
} else if (RegExp.$3.indexOf('vimeo') > -1) {
type = 'vimeo';
}
return {
type: type,
id: RegExp.$6
};
}

Regex is wonderfully terse but can quickly get complicated.
http://jsfiddle.net/8nagx2sk/
function parseYouTube(str) {
// link : //youtube.com/watch?v=Bo_deCOd1HU
// share : //youtu.be/Bo_deCOd1HU
// embed : //youtube.com/embed/Bo_deCOd1HU
var re = /\/\/(?:www\.)?youtu(?:\.be|be\.com)\/(?:watch\?v=|embed\/)?([a-z0-9_\-]+)/i;
var matches = re.exec(str);
return matches && matches[1];
}
function parseVimeo(str) {
// embed & link: http://vimeo.com/86164897
var re = /\/\/(?:www\.)?vimeo.com\/([0-9a-z\-_]+)/i;
var matches = re.exec(str);
return matches && matches[1];
}
Sometimes simple code is nicer to your fellow developers.
https://jsfiddle.net/vkg02mhp/1/
// protocol and www nuetral
function getVideoId(str, prefixes) {
const cleaned = str.replace(/^(https?:)?\/\/(www\.)?/, '');
for(const prefix of prefixes) {
if (cleaned.startsWith(prefix))
return cleaned.substr(prefix.length)
}
return undefined;
}
function getYouTubeId(url) {
return getVideoId(url, [
'youtube.com/watch?v=',
'youtu.be/',
'youtube.com/embed/'
]);
}
function getVimeoId(url) {
return getVideoId(url, [
'vimeo.com/'
]);
}
Which do you prefer to update?

I am not sure about your question 3), but provided that your induction on the url forms is correct, the regexes can be combined into one as follows:
/http:\/\/(?:www.)?(?:(vimeo).com\/(.*)|(youtube).com\/watch\?v=(.*?)&)/
You will get the match under different positions (1st and 2nd matches if vimeo, 3rd and 4th matches if youtube), so you just need to handle that.
Or, if you are quite sure that vimeo's id only includes numbers, then you can do:
/http:\/\/(?:www.)?(vimeo|youtube).com\/(?:watch\?v=)?(.*?)(?:\z|&)/
and the provider and the id will apprear under 1st and 2nd match, respcetively.

Here is my regex
http://jsfiddle.net/csjwf/1/

For Vimeo, Don't rely on Regex as Vimeo tends to change/update their URL pattern every now and then. As of October 2nd, 2017, there are in total of six URL schemes Vimeo supports.
https://vimeo.com/*
https://vimeo.com/*/*/video/*
https://vimeo.com/album/*/video/*
https://vimeo.com/channels/*/*
https://vimeo.com/groups/*/videos/*
https://vimeo.com/ondemand/*/*
Instead, use their API to validate vimeo URLs. Here is this oEmbed (doc) API which takes an URL, checks its validity and return a object with bunch of video information(check out the dev page). Although not intended but we can easily use this to validate whether a given URL is from Vimeo or not.
So, with ajax it would look like this,
var VIMEO_BASE_URL = "https://vimeo.com/api/oembed.json?url=";
var yourTestUrl = "https://vimeo.com/23374724";
$.ajax({
url: VIMEO_BASE_URL + yourTestUrl,
type: 'GET',
success: function(data) {
if (data != null && data.video_id > 0)
// Valid Vimeo url
else
// not a valid Vimeo url
},
error: function(data) {
// not a valid Vimeo url
}
});

about sawa's answer :
a little update on the second regex :
/http:\/\/(?:www\.)?(vimeo|youtube)\.com\/(?:watch\?v=)?(.*?)(?:\z|$|&)/
(escaping the dots prevents from matching url of type www_vimeo_com/… and $ added…)
here is the same idea for matching the embed urls :
/http:\/\/(?:www\.|player\.)?(vimeo|youtube)\.com\/(?:embed\/|video\/)?(.*?)(?:\z|$|\?)/

FWIW, I just used the following to validate and parse both YouTube and Vimeo URLs in an app. I'm sure you could add parentheses to parse out the specific things you're looking for...
/^(?:https?:\/\/)?(?:www\.)?(?:youtu\.be\/|youtube\.com\/(?:embed\/|v\/|watch\?v=|watch\?.+&v=))((\w|-){11})(?:\S+)?$|^(https?:\/\/)?(www.)?(player.)?vimeo.com\/([a-z]*\/)*([0-9]{6,11})[?]?.*$/
^^ This is just a combination of 2 separate expressions using | (or) to join them. Here are the original 2 expressions separately:
/^(?:https?:\/\/)?(?:www\.)?(?:youtu\.be\/|youtube\.com\/(?:embed\/|v\/|watch\?v=|watch\?.+&v=))((\w|-){11})(?:\S+)?$/
/^(https?:\/\/)?(www.)?(player.)?vimeo.com\/([a-z]*\/)*([0-9]{6,11})[?]?.*$/
I'm no expert, but it seems to work according to Rubular. Hopefully this helps someone out in the future.

3) Your regex does not match https url's. I haven't tested it, but I guess the "http://" part would become "http(s)?://". Note that this would change the matching positions of the provider and id.

Just in case here is a php version
/*
* parseVideo
* #param (string) $url
* mi-ca.ch 27.05.2016
* parse vimeo & youtube id
* format url for iframe embed
* https://regex101.com/r/lA0fP4/1
*/
function parseVideo($url) {
$re = "/(http:|https:|)\\/\\/(player.|www.)?(vimeo\\.com|youtu(be\\.com|\\.be|be\\.googleapis\\.com))\\/(video\\/|embed\\/|watch\\?v=|v\\/)?([A-Za-z0-9._%-]*)(\\&\\S+)?/";
preg_match($re, $url, $matches);
if(strrpos($matches[3],'youtu')>-1){
$type='youtube';
$src='https://www.youtube.com/embed/'.$matches[6];
}else if(strrpos($matches[3],'vimeo')>-1){
$type="vimeo";
$src='https://player.vimeo.com/video/'.$matches[6];
}else{
return false;
}
return array(
'type' => $type // return youtube or vimeo
,'id' => $matches[6] // return the video id
,'src' => $src // return the src for iframe embed
);
}

I had a task to enable adding a dropbox videos. So the same input should take href, check it and transform to the playable link which I can then insert in .
const getPlayableUrl = (url) => {
// Check youtube and vimeo
let firstCheck = url.match(/(http:|https:|)\/\/(player.|www.)?(vimeo\.com|youtu(be\.com|\.be|be\.googleapis\.com))\/(video\/|embed\/|watch\?v=|v\/)?([A-Za-z0-9._%-]*)(\&\S+)?/);
if (firstCheck) {
if (RegExp.$3.indexOf('youtu') > -1) {
return "//www.youtube.com/embed/" + RegExp.$6;
} else if (RegExp.$3.indexOf('vimeo') > -1) {
return 'https://player.vimeo.com/video/' + RegExp.$6
}
} else {
// Check dropbox
let candidate = ''
if (url.indexOf('.mp4') !== -1) {
candidate = url.slice(0, url.indexOf('.mp4') + 4)
} else if (url.indexOf('.m4v') !== -1) {
candidate = url.slice(0, url.indexOf('.m4v') + 4)
} else if (url.indexOf('.webm') !== -1) {
candidate = url.slice(0, url.indexOf('.webm') + 5)
}
let secondCheck = candidate.match(/(http:|https:|)\/\/(player.|www.)?(dropbox\.com)\/(s\/|embed\/|watch\?v=|v\/)?([A-Za-z0-9._%-]*\/)?(.*)/);
if (secondCheck) {
return 'https://dropbox.com/' + RegExp.$4 + RegExp.$5 + RegExp.$6 + '?raw=1'
} else {
throw Error("Not supported video resource.");
}
}
}

I based myself the previous answers but I needed more out the regex.
Maybe it worked in 2011 but in 2019 the syntax has changed a bit. So this is a refresh.
The regex will allow us to detect weather the url is Youtube or Vimeo.
I've added Capture group to easily retrieve the videoID.
If ran with Case insensitive setting please remove the (?i).
(?:(?i)(?:https:|http:)?\/\/)?(?:(?i)(?:www\.youtube\.com\/(?:embed\/|watch\?v=)|youtu\.be\/|youtube\.googleapis\.com\/v\/)(?<YoutubeID>[a-z0-9-_]{11,12})|(?:vimeo\.com\/|player\.vimeo\.com\/video\/)(?<VimeoID>[0-9]+))
https://regex101.com/r/PVdjg0/2

Use this Regex devs:This works like Makhan(react js,Javascript)
^(http\:\/\/|https\:\/\/)?((www\.)?(vimeo\.com\/)([0-9]+)$)|((www\.youtube\.com|youtu\.be)\/.+$)

js function to get filename from url

I have a url like http://www.example.com/blah/th.html
I need a javascript function to give me the 'th' value from that.
All my urls have the same format (2 letter filenames, with .html extension).
I want it to be a safe function, so if someone passes in an empty url it doesn't break.
I know how to check for length, but I should be checking for null to right?

var filename = url.split('/').pop()

Why so difficult?
var filename = url.split('/').pop().split('#')[0].split('?')[0];

Use the match function.
function GetFilename(url)
{
if (url)
{
var m = url.toString().match(/.*\/(.+?)\./);
if (m && m.length > 1)
{
return m[1];
}
}
return "";
}

Similar to the others, but...I've used Tom's simple script - a single line,
then you can use the filename var anywhere:
http://www.tomhoppe.com/index.php/2008/02/grab-filename-from-window-location/
var filename = location.pathname.substr(location.pathname.lastIndexOf("/")+1);

This should work for all cases
function getFilenameFromUrl(url) {
const pathname = new URL(url).pathname;
const index = pathname.lastIndexOf('/');
return pathname.substring(index + 1) // if index === -1 then index+1 will be 0
}

In addition to the existing answers, I would recommend using URL() constructor (works both in browsers and Node.js) because you can be sure your URL is valid:
const url = 'https://test.com/path/photo123.png?param1=1&param2=2#hash';
let filename = '';
try {
filename = new URL(url).pathname.split('/').pop();
} catch (e) {
console.error(e);
}
console.log(`filename: ${filename}`);

A regex solution which accounts for URL query and hash identifier:
function fileNameFromUrl(url) {
var matches = url.match(/\/([^\/?#]+)[^\/]*$/);
if (matches.length > 1) {
return matches[1];
}
return null;
}
JSFiddle here.

Because cases tend to fail with custom code, I looked up to the JavaScript URL class. Alas, it chokes on relative URLs! Also, it doesn't have a property to get the file name. Not epic.
There has to be a good library out there which solves this common problem. Behold URI.js. All you need is a simple statement like the following:
let file = new URI(url).filename()
Then we can create a simple function that does null checks and removes the file extension:
function fileName(url) {
if (url === null || typeof url === 'undefined')
return ''
let file = new URI(url).filename() // File name with file extension
return file.substring(0, file.lastIndexOf('.')) // Remove the extension
}
Here's a snippet with test cases to play around with. All cases pass except drive paths.
test('Dots in file name without URL', 'dotted.file.name.png', 'dotted.file.name')
test('Dots in file name with URL', 'http://example.com/file.name.txt', 'file.name')
test('Lengthy URL with parameters', '/my/folder/filename.html#dssddsdsd?toto=33&dududu=podpodpo', 'filename')
test('URL with hash', '/my/folder/filename.html#dssddsdsd', 'filename')
test('URL with query strings', '/my/folder/filename.html?toto=33&dududu=podpodp', 'filename')
test('Hash after query string', 'http://www.myblog.com/filename.php?year=2019#06', 'filename')
test('Query parameter with file path character', 'http://www.example.com/filename.zip?passkey=1/2', 'filename')
test('Query parameter with file path character and hash', 'http://www.example.com/filename.html?lang=en&user=Aan9u/o8ai#top', 'filename')
test('Asian characters', 'http://example.com/文件名.html', '文件名')
test('URL without file name', 'http://www.example.com', '')
test('Null', null, '')
test('Undefined', undefined, '')
test('Empty string', '', '')
test('Drive path name', 'C:/fakepath/filename.csv', 'filename')
function fileName(url) {
if (url === null || typeof url === 'undefined')
return ''
let file = new URI(url).filename() // File name with file extension
return file.substring(0, file.lastIndexOf('.')) // Remove the extension
}
function test(description, input, expected) {
let result = fileName(input)
let pass = 'FAIL'
if (result === expected)
pass = 'PASS'
console.log(pass + ': ' + description + ': ' + input)
console.log(' => "' + fileName(input) + '"')
}
<script src="https://cdn.jsdelivr.net/gh/medialize/URI.js#master/src/URI.js"></script>
Results
PASS: Dots in file name without URL: dotted.file.name.png
=> "dotted.file.name"
PASS: Dots in file name with URL: http://example.com/file.name.txt
=> "file.name"
PASS: Lengthy URL with parameters: /my/folder/filename.html#dssddsdsd?toto=33&dududu=podpodpo
=> "filename"
PASS: URL with hash: /my/folder/filename.html#dssddsdsd
=> "filename"
PASS: URL with query strings: /my/folder/filename.html?toto=33&dududu=podpodp
=> "filename"
PASS: Hash after query string: http://www.myblog.com/filename.php?year=2019#06
=> "filename"
PASS: Query parameter with file path character: http://www.example.com/filename.zip?passkey=1/2
=> "filename"
PASS: Query parameter with file path character and hash: http://www.example.com/filename.html?lang=en&user=Aan9u/o8ai#top
=> "filename"
PASS: Asian characters: http://example.com/文件名.html
=> "文件名"
PASS: URL without file name: http://www.example.com
=> ""
PASS: Null: null
=> ""
PASS: Undefined: undefined
=> ""
PASS: Empty string:
=> ""
FAIL: Drive path name: C:/fakepath/filename.csv
=> ""
This solution is for you if you're too lazy to write custom code and don't mind using a library to do work for you. It isn't for you if you want to code golf the solution.

those will not work for lenghty url like
"/my/folder/questions.html#dssddsdsd?toto=33&dududu=podpodpo"
here I expect to get "questions.html".
So a possible (slow) solution is as below
fname=function(url)
{ return url?url.split('/').pop().split('#').shift().split('?').shift():null }
then you can test that in any case you get only the filename.
fname("/my/folder/questions.html#dssddsdsd?toto=33&dududu=podpodpo")
-->"questions.html"
fname("/my/folder/questions.html#dssddsdsd")
-->"questions.html"
fname("/my/folder/questions.html?toto=33&dududu=podpodpo")
"-->questions.html"
(and it works for null)
(I would love to see a faster or smarter solution)

This answer only works in browser environment. Not suitable for node.
function getFilename(url) {
const filename = decodeURIComponent(new URL(url).pathname.split('/').pop());
if (!filename) return 'index.html'; // some default filename
return filename;
}
function filenameWithoutExtension(filename) {
return filename.replace(/^(.+?)(?:\.[^.]*)?$/, '$1');
}
Here are two functions:
first one get filename from url
second one get filename without extension from a full filename
For parsing URL, new an URL object should be the best choice. Also notice that URL do not always contain a filename.
Notice: This function try to resolve filename from an URL. But it do NOT guarantee that the filename is valid and suitable for use:
Some OS disallow certain character in filename (e.g. : in windows, \0 in most OS, ...);
Some filename may reserved by OS (e.g. CON in windows);
Some filename may make user unhappy to handle it (e.g. a file named "--help" in Linux)
Test it out:
function getFilename(url) {
const filename = decodeURIComponent(new URL(url).pathname.split('/').pop());
if (!filename) return 'index.html'; // some default filename
return filename;
}
function test(url) {
console.log('Filename: %o\nUrl: %o', getFilename(url), url);
}
test('http://www.example.com');
test('http://www.example.com/');
test('http://www.example.com/name.txt');
test('http://www.example.com/path/name.txt');
test('http://www.example.com/path/name.txt/realname.txt');
test('http://www.example.com/page.html#!/home');
test('http://www.example.com/page.html?lang=en&user=Aan9u/o8ai#top');
test('http://www.example.com/%E6%96%87%E4%BB%B6%E5%90%8D.txt')

I'd use the substring function combined with lastIndexOf. This will allow for filenames with periods in them e.g. given http://example.com/file.name.txt this gives file.name unlike the accepted answer that would give file.
function GetFilename(url)
{
if (url)
{
return url.substring(url.lastIndexOf("/") + 1, url.lastIndexOf("."));
}
return "";
}

Using jQuery with the URL plugin:
var file = jQuery.url.attr("file");
var fileNoExt = file.replace(/\.(html|htm)$/, "");
// file == "th.html", fileNoExt = "th"

For node and browsers, based on #pauls answer but solving issues with hash and more defensive:
export function getFileNameFromUrl(url) {
const hashIndex = url.indexOf('#')
url = hashIndex !== -1 ? url.substring(0, hashIndex) : url
return (url.split('/').pop() || '').replace(/[\?].*$/g, '')
}
Few cases:
describe('getFileNameFromUrl', () => {
it('absolute, hash and no extension', () => {
expect(getFileNameFromUrl(
'https://foo.bar/qs/bar/js-function-to-get-filename-from-url#comment95124061_53560218'))
.toBe('js-function-to-get-filename-from-url')
})
it('relative, extension and parameters', () => {
expect(getFileNameFromUrl('../foo.png?ar=8')).toBe('foo.png')
})
it('file name with multiple dots, hash with slash', () => {
expect(getFileNameFromUrl('questions/511761/js-function.min.js?bar=9.9&y=1#/src/jjj?=9.9')).toBe('js-function.min.js')
})
})

This should handle anything you throw at it (absolute URLs, relative URLs, complex AWS URLs, etc). It includes an optional default or uses a psuedorandom string if neither a filename nor a default were present.
function parseUrlFilename(url, defaultFilename = null) {
let filename = new URL(url, "https://example.com").href.split("#").shift().split("?").shift().split("/").pop(); //No need to change "https://example.com"; it's only present to allow for processing relative URLs.
if(!filename) {
if(defaultFilename) {
filename = defaultFilename;
//No default filename provided; use a pseudorandom string.
} else {
filename = Math.random().toString(36).substr(2, 10);
}
}
return filename;
}
Props to #hayatbiralem for nailing the order of the split()s.

Similarly to what #user2492653 suggested, if all you want is the name of the file like Firefox gives you, then you the split() method, which breaks the string into an array of components, then all you need to do it grab the last index.
var temp = url.split("//");
if(temp.length > 1)
return temp[temp.length-1] //length-1 since array indexes start at 0
This would basically break C:/fakepath/test.csv into {"C:", "fakepath", "test.csv"}

my 2 cents
the LastIndexOf("/") method in itself falls down if the querystrings contain "/"
We all know they "should" be encoded as %2F but it would only take one un-escaped value to cause problems.
This version correctly handles /'s in the querystrings and has no reliance on .'s in the url
function getPageName() {
//#### Grab the url
var FullUrl = window.location.href;
//#### Remove QueryStrings
var UrlSegments = FullUrl.split("?")
FullUrl = UrlSegments[0];
//#### Extract the filename
return FullUrl.substr(FullUrl.lastIndexOf("/") + 1);
}

Try this
url.substring(url.lastIndexOf('/')+1, url.length)

url? url.substring(url.lastIndexOf('/')+1, url.lastIndexOf('.')):''
Safety is as asked for. when url is null or undefined the result is ''.
Removes all of the path with ':', dots and any symbol including the last '/'.
This gives the true answer 'th' as asked and not 'th.index'. That is very important of course to have it work at all.
It allows filename to have several periods!
Not asked, but you can also have a query string without '/' and '.'
It is a corrected answer from Abhishek Sharma so I gave him an upvote. So genious and minimal one-liner - I saw it there :)

function getFileNameWithoutExtension(url) {
if (typeof url !== 'string') throw new Error('url must be a string');
// Remove the QueryString
return url.replace(/\?.*$/, '')
// Extract the filename
.split('/').pop()
// Remove the extension
.replace(/\.[^.]+$/, '');
}
This will return news from this URL http://www.myblog.com/news.php?year=2019#06.

ES6 syntax based on TypeScript
Actually, the marked answer is true but if the second if doesn't satisfy the function returns undefined, I prefer to write it like below:
const getFileNameFromUrl = (url: string): string => {
if (url) {
const tmp = url.split('/');
const tmpLength = tmp.length;
return tmpLength ? tmp[tmpLength - 1] : '';
}
return '';
};
For my problem, I need to have the file extension.

Simple Function (Using RegEx Pattern)
function pathInfo(s) {
s=s.match(/(.*?\/)?(([^/]*?)(\.[^/.]+?)?)(?:[?#].*)?$/);
return {path:s[1],file:s[2],name:s[3],ext:s[4]};
}
var sample='/folder/another/file.min.js?query=1';
var result=pathInfo(sample);
console.log(result);
/*
{
"path": "/folder/another/",
"file": "file.min.js",
"name": "file.min",
"ext": ".js"
}
*/
console.log(result.name);

Using RegEx
Let´s say you have this url:
http://127.0.0.1:3000/pages/blog/posts/1660345251.html
Using the following line of code:
var filename = location.pathname.replace(/[\D]/g, "");
Will return:
1660345251
Notice that this number is Unix Time, which returns your local time no matter where you are in the World (this should give you really unique post names for this blog example).
.replace(/[\D]/g, ""), replaces any non-digit character with an empty string. /[\D]/g says non-digit, and "" says empty string. More about it: here for numbers and here for letters.
More about RegEx, here. There are lots of RegEx tools out there that can help you out to get better results in the returning value for filename.
Extra code: Unix Time to Local Time
var humanDate = new Date(0);
var timestamp = entries[index].timestamp;
humanDate.setUTCSeconds(timestamp);
humanDate is for my local time:
Fri Aug 12 2022 20:00:51 GMT-0300 (Argentina Standard Time)
Credits for this code, here.

function getFilenameFromUrlString(url) {
const response = {
data: {
filename: ""
},
error: ""
};
try {
response.data.filename = new URL(url).pathname.split("/").pop();
} catch (e) {
response.error = e.toString();
}
return response;
}
For tests check this:
https://codesandbox.io/s/get-filename-from-url-string-wqthx1

from How to get the file name from a full path using JavaScript?
var filename = fullPath.replace(/^.*[\\\/]/, '')

Categories

Resources