Extract domain extension (e.g. .com) NOT the domain name (e.g. google.com) from hostname using regex.
input => output
www.google.com => .com
google.com => .com
google.co.uk => .co.uk
www.google.co.uk => .co.uk
sub.google.co.uk => .co.uk
NOT a duplicate of Get domain name without subdomains using JavaScript?
You can manually check for the list of country domains and then the preceding domain segment that appears before it.
That is: <other>.<topLevelDomain>.[optionalCountryCode]
Example below:
function getTopDomain(domain) {
const topDomainExpression = /\w+((\.[a-z]{2,3})(\.(ad|ae|af|ag|ai|al|am|ao|aq|ar|as|at|au|aw|ax|az|ba|bb|bd|be|bf|bg|bh|bi|bj|bl|bm|bn|bo|bq|br|bs|bt|bv|bw|by|bz|ca|cc|cd|cf|cg|ch|ci|ck|cl|cm|cn|co|cr|cu|cv|cw|cx|cy|cz|de|dj|dk|dm|do|dz|ec|ee|eg|er|es|et|fi|fj|fk|fm|fo|fr|ga|gb|gd|ge|gf|gg|gh|gi|gl|gm|gn|gp|gq|gr|gs|gt|gu|gw|gy|hk|hm|hn|hr|ht|hu|id|ie|il|im|in|io|iq|ir|is|it|je|jm|jo|jp|ke|kg|kh|ki|km|kn|kp|kr|kw|ky|kz|la|lb|lc|li|lk|lr|ls|lt|lu|lv|ly|ma|mc|md|me|mf|mg|mh|mk|ml|mm|mn|mo|mp|mq|mr|ms|mt|mu|mv|mw|mx|my|mz|na|nc|ne|nf|ng|ni|nl|no|np|nr|nu|nz|om|pa|pe|pf|pg|ph|pk|pl|pm|pn|pr|ps|pt|pw|py|qa|re|ro|rs|ru|rw|sa|sb|sc|sd|se|sg|sh|si|sj|sk|sl|sm|sn|so|sr|ss|st|sv|sx|sy|sz|tc|td|tf|tg|th|tj|tk|tl|tm|tn|to|tr|tt|tv|tw|tz|ua|ug|uk|us|uy|uz|va|vc|ve|vg|vi|vn|vu|wf|ws|ye|yt|za|zm|zw))?)$/i;
const match = topDomainExpression.exec(domain);
return match[1];
}
function test(input, expectedOutput) {
const output = getTopDomain(input);
console.log(`${output === expectedOutput ? 'PASS' : 'FAIL'}: ${input} (expected: ${expectedOutput}, output: ${output})`);
}
test('www.google.com', '.com');
test('google.com', '.com');
test('google.co.uk', '.co.uk');
test('www.google.co.uk', '.co.uk');
test('sub.google.co.uk', '.co.uk');
test('bit.ly', '.ly');
test('something.co.ly', '.co.ly');
Try this:
function getExtension(hostname){
let e = hostname.slice(hostname.search('.'), hostname.length);
return e;
}
