var string = "https://example.com/app/something";
var string = "example.com/app/something";
new URL(string.origin)
If string have protocol all ok, and if not. have error Failed to construct 'URL': Invalid URL(…)
How can I obtain the root domain without using regex?
The question is still a bit unclear, and I'm not entirely sure how you're getting that string, but just for the sake of argument, here's a quick solution:
function getHostname(str)
{
str = (/^\w+:\/\//.test(str) ? "" : "http://") + str
return new URL(str).hostname;
}
console.log(getHostname("https://example.com/app/something"));
console.log(getHostname("example.com/app/something"));
Yes, technically, this technically does use a regular expression to check if the protocol is present, but it uses the URL class actually parse the host name.
Regex example:
var example1 = "www.example1.com/test/path";
var example2 = "https://example2.com/test/path";
var example3 = "http://subdomain.example3.com/test/path";
function getDomain(str) {
var matches = str.match(/^(?:https?:\/\/)?((?:[-A-Za-z0-9]+\.)+[A-Za-z]{2,6})/);
if (!matches || matches.length < 2) return '';
return matches[1];
}
console.log(getDomain(example1));
console.log(getDomain(example2));
console.log(getDomain(example3));
References:
https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/String/match
http://regexr.com/
If I understand your question correctly, you want to check if the URL contains either the http or https protocol. This can easily be done with string functions built into JavaScript as shown below.
var string = window.location;
if (string.includes('http') || string.includes('https'))
{
//Do your logic here
}
UPDATE: Alternatively, you could use substring functionality shown below.
var string = window.location;
if (string.indexOf('http') == 0)
{
//Do your logic here
}
Note that this will also verify that the http is at the beginning of the string and not just thrown in willy nilly.
Related
Here is my code:
var url="https://muijal-ip-dev-ed.my.salesforce.com/apexpages/setup/viewApexPage.apexp?id=066415642TPaE";
In this string i need only
url="https://muijal-ip-dev-ed.my.salesforce.com/"
i need string upto "com/" rest of the string should be removed.
In modern browsers you can use URL()
var url=new URL("https://muijal-ip-dev-ed.my.salesforce.com/apexpages/setup/viewApexPage.apexp?id=066415642TPaE");
console.log(url.origin)
For unsupported browsers use regex
use javascript split
url = url.split(".com");
url = url[0] + ".com";
That should leave you with the wanted string if the Url is well formed.
You can use locate then substr like this:
var url = url.substr(0, url.locate(".com"));
locate returns you the index of the string searched for and then substr will cut from the beginning until that index~
Substring function should handle that nicely:
function clipUrl(str, to, include) {
if (include === void 0) {
include = false;
}
return str.substr(0, str.indexOf(to) + (include ? to.length : 0));
}
console.log(clipUrl("https://muijal-ip-dev-ed.my.salesforce.com/apexpages/setup/viewApexPage.apexp?id=066415642TPaE", ".com", true));
If the URL API (as suggested by another answer) isn't available you can reliably use properties of the HTMLAnchorElement interface as a workaround if you want to avoid using regular expressions.
var a = document.createElement('a');
a.href = 'https://muijal-ip-dev-ed.my.salesforce.com/apexpages/setup/viewApexPage.apexp?id=066415642TPaE';
console.log(a.protocol + '//' + a.hostname);
I have a whitelist where users can enter specific URLs/URL patterns (only targetting http and https.
I would like to transfrom and compare these URL/URL patterns so that the wildcard selector (*) can be used like so
user enters: example.*/test
I want to transform this to: *//*.example.*/test
so that it matches: http://www.example.com/test, https://example.co.uk/test
Another example:
user enters: http://www.*.com/*
I want to transform this to: http://www.*.com/*
so that it matches: http://www.blah.com/test, http://www.other.com/null.html
and
user enters: www.example.com/*
I want to transform this to: *//www.example.com/*
so that it matches: http://www.example.com/testtwo, https://www.example.com/arfg
The reason I want to insert a leading protocol (if it wasn't included by the user) is because I am using this to compare against the current tab URL.
I get this array of URL strings and would like to compare them with the current url, but am having trouble matching all use cases:
"isNotWhitelisted" : function(){
var whitelist = MyObject.userLists.whitelist;
var currentUrl = document.location.href;
for(var i=0; i<whitelist.length; i++){
var regexListItem = new RegExp(whitelist[i].toString().replace(".", "\\.").replace("*", ".+"));
if(currentUrl.match(regexListItem)) {
return false;
}
}
return true;
},
Firstly, the regex conversion matches end cases (e.g. example.com/* but not kinds like example.*/about
This is part of a Chrome extension, is there not a better/easier way to do this maybe using inbuilt methods?
Thanks for any help in advance.
whitelist.forEach(function(listItem){
var rgx = new RegExp(listItem.replace(/\./g,'\\.').replace(/\*/g,'.*'));
if(rgx.test(url)) {
// current URL matches URL/URL pattern in whitelist array!
}
})
If you dont replace, the pattern 'www.*.com' match also to 'wwwocom'.
If you want use another special characters you can use this:
var rgx = new RegExp(listItem.replace(/(\.|\[|\]|\{|\}|\(|\)|\+|\?|\\|\$|\^)/g,'\\$1').replace(/\*/g,'.*'));
If you want a greedy matching, I think you need request the user enter the pattern in this format: *://*/*
You can check this in this way:
var special_char_rgx = /(\.|\[|\]|\{|\}|\(|\)|\+|\?|\\|\/|\$|\^|\|)/g; // I think that all...
var asterisk_rgx = /\*/g;
var pattern_rgx = /^([^:\/]+):\/\/([^\/]+)\/(.*)$/g;
function addPatern(pattern, whitelist) {
var str_pattern = pattern.replace(asterisk_rgx,'\\*');
var isMatch = pattern_rgx.test(str_pattern);
if (isMatch) {
pattern = pattern.replace(special_char_rgx,'\\$1').replace(asterisk_rgx, '.+');
whitelist.push(new RegExp('^'+pattern + '$'));
}
pattern_rgx.lastIndex = 0; // Otherwise RegExp.test save this value and destroy the tests!
return isMatch;
}
If you want handle the protocol/ domain/ path in different ways you can do it that way:
if (isMatch) {
var protocol = RegExp.$1;
var domain= RegExp.$2;
var path_query = RegExp.$3;
// Your logic...
}
Hm, m.b. create RegExp from whitelist items? If it works as you expected:
new RegExp('example.com/*').test('http://example.com/aaaa')
Just create regexp from each item in whitelist
whitelist.forEach(function(item) {
new RegExp(item).match(URL);
});
I'm writing a JavaScript function to extract a segment out of a URL that appears to the right of a designated segment.
For instance, if this is my URL ...
mysite.com/cat/12/dog/34?test=123
... I would like to be able to pass 'cat' to the function and get 12, and later pass 'dog' to the function and have it return 34. I found this answer on StackOverflow to extract the URL segment, but it uses a string literal. And I'm having difficulty concatenating a passed in value.
jQuery to parse our a part of a url path
Here is my code. In this, rather than hard coding 'cat' into the pattern match, I would like to pass 'cat' into the segmentName parameter and have the regular expression match on that.
var url = "www.mysite.com/cat/12/dog/34?test=123";
alert(getNextSegmentAfterSegmentName(url, 'cat'));
function getNextSegmentAfterSegmentName(currentPath, segmentName) {
var nextSegment = "";
segmentName = segmentName.toLowerCase();
//var currentPath = window.location.pathname.toLowerCase();
if (currentPath.indexOf(segmentName) >= 0) {
var path = currentPath.split('?')[0]; // Strip querystring
// How do I concatenate segmentName into this?
var matches = path.match(/\/cat\/([^\/]+)/);
if (matches) {
nextSegment = matches[1];
}
}
return nextSegment;
}
Here is a jsfiddle example:
http://jsfiddle.net/Stormjack/2Ebsv/
Thanks for your help!
You need to create a RegExp object if you want to create regex using some string variable:
path.match(new RegExp("\/" + segmentName + "\/([^\/]+)"));
I need to build a string from the data contained in this url using javascript/jQuery:
http://www.example.com/members/admin/projects/?projectid=41
The string returned should look as follows:
/ajax/projects.php?projectid=41
Obviously if there is no query string present, the method should still return a string of the same format minus the query string. e.g.
http://www.example.com/members/admin/messages/
should return...
/ajax/messages.php
I've made numerous attempts, all met without success due to my poor grasp of regular expressions, and it feels as though the ore I rad on the subject the more I am confusing myself.
If someone could help it would be greatly appreciated.
EDIT: The 'admin' portion of the url is a users 'username' and could be anything.
Here's a function that will take your URL and return a new one according to the rules you've listed above:
function processURL(url) {
var base = "", query = "";
var matches = url.match(/([^\/\?]+)(\/$|$|\?|\/\?)/);
if (matches) {
base = matches[1];
matches = url.match(/\?[^\?]+$/);
if (matches) {
query = matches[0];
}
}
return("/ajax/" + base + ".php" + query);
}
And, a test app that shows it working on a bunch of URLs: http://jsfiddle.net/jfriend00/UbDfn/
Input URLs:
var urls = [
"http://www.example.com/members/admin/projects/?projectid=41",
"http://www.example.com/members/bob/messages/",
"http://www.example.com/members/jill/projects/",
"http://www.example.com/members/alice/projects?testid=99",
"http://www.example.com/members/admin/projects/?testid=99"
];
Output results:
/ajax/projects.php?projectid=41
/ajax/messages.php
/ajax/projects.php
/ajax/projects.php?testid=99
/ajax/projects.php?testid=99
To explain, the first regular expression looks for:
a slash
followed by one or more characters that is not a slash and not a question mark
followed by one of the four sequences
/$ a slash at the end of the string
$ end of the string
? a question mark
/? a slash followed by a question mark
The point of this regex is to get the last segment of the path that comes before either the end of the string or the query parameters and it's tolerant of whether the last trailing slash is there or not and whether there are any query parameters.
I know exactly what you are trying to do. In order to do it your way just split your string on question mark and then use last item form your array.
var data = your_url.split('?');
var newUrl = '/ajax/projects.php' + (data.length > 1 ? data[length-1] : "");
and you will have your url.
But what you can do is execute same url using your Script just add one parameter IsAjax=true and then check it in codebehind and execute your ajax logic.
e.g.
$('#somelink').onclick(function(){
$.ajax({ url: $(this).href, data { IsAjax: true } .... }
});
Using this way you will have more robust app.
I'll assume that by
http://www.example.com/members/admin/messages/
should return...
/ajax/members.php
you meant - should return...
/ajax/messages.php
If that is the case try
var query = url.split('?');
var paths = query[0].split('/');
var path = paths.pop();
if (path == '') //when there is trailing slash
path = paths.pop();
if (query.length == 1) //no query string
newurl = '/ajax/' + path + '.php';
else //query string
newurl = '/ajax/' + path + '.php?' + query[1];
I'm sure it can be made simpler and better, but that might give you a start.
var str = "http://www.example.com/members/admin/projects/?projectid=41";
var newStr = "/ajax/" + str.split("/").slice(-2).join(".php");
console.log(newStr);
I am looking for a javascript function/regex to extract *.com from a URI... (to be done on client side)
It should work for the following cases:
siphone.com = siphone.com
qwr.siphone.com = siphone.com
www.qwr.siphone.com = siphone.com
qw.rock.siphone.com = siphone.com
<http://www.qwr.siphone.com> = siphone.com
Much appreciated!
Edit: Sorry, I missed a case:
http://www.qwr.siphone.com/default.htm = siphone.com
I guess this regex should work for a few cases:
/[\w]+\.(com|ca|org|net)/
I'm not good with JavaScript, but there should be a library for splitting URIs out there, right?
According to that link, here's a "strict" regex:
/^(?:([^:\/?#]+):)?(?:\/\/((?:(([^:#]*)(?::([^:#]*))?)?#)?([^:\/?#]*)(?::(\d*))?))?((((?:[^?#\/]*\/)*)([^?#]*))(?:\?([^#]*))?(?:#(.*))?)/
As you can see, you're better off just using the "library". :)
This should do it. I added a few cases for some nonmatches.
var cases = [
"siphone.com",
"qwr.siphone.com",
"www.qwr.siphone.com",
"qw.rock.siphone.com",
"<http://www.qwr.siphone.com>",
"hamstar.corm",
"cheese.net",
"bro.at.me.come",
"http://www.qwr.siphone.com/default.htm"];
var grabCom = function(str) {
var result = str.match("(\\w+\\.com)\\W?|$");
if(result !== null)
return result[1];
return null;
};
for(var i = 0; i < cases.length; i++) {
console.log(grabCom(cases[i]));
}
var myStrings = [
'siphone.com',
'qwr.siphone.com',
'www.qwr.siphone.com',
'qw.rock.siphone.com',
'<http://www.qwr.siphone.com>'
];
for (var i = 0; i < myStrings.length; i++) {
document.write( myStrings[i] + '=' + myStrings[i].match(/[\w]+\.(com)/gi) + '<br><br>');
}
I've placed given demo strings to the myStrings array.
i - is index to iterate through this array. The following line does the matching trick:
myStrings[i].match(/[\w]+\.(com)/gi)
and returns the value of siphone.com. If you'd like to match .net and etc. - add (com|net|other) instead of just (com).
Also you may find the following link useful: Regular expressions Cheat Sheet
update: missed case works too %)
You could split the string then search for the .com string like so
var url = 'music.google.com'
var parts = url.split('.');
for(part in parts) {
if(part == 'com') {
return true;
}
{
uri = "foo.bar.baz.com"
uri.split(".").slice(-2).join(".") // returns baz.com
This assumes that you want just the hostname and tld. It also assumes that there is no path information either.
Updated now that you also need to handle uris with paths you could do:
uri.split(".").slice(-2).join(".").split("/")[0]
Use regexp to do that. This way modifications to the detections are quite easy.
var url = 'www.siphone.com';
var domain = url.match(/[^.]\.com/i)[0];
If you use url.match(/(([^.]+)\.com)[^a-z]/i)[1] instead. You can assure that the ".com" is not followed by any other characters.