Extract main domain name from a URL

extract_domain_name.ts

const url = "https://www.lancasterguardian.co.uk/read-this/womens-world-cup-2023-groups-england-to-face-denmark-and-china-see-the-full-draw-3890113";
const url1 = "https://www.tudelft.nl";
const url2 = "https://whatsnew2day.com/world-cup-2023-draw-uswnt-face-vietnam-netherlands-playoff-winner-new-zealand-htmlns_mchannelrssns_campaign1490ito1490/";
const url3 = "https://www.news4jax.com/news/politics/2022/10/22/weapons-shortages-could-mean-hard-calls-for-ukraines-allies/";

const extractAgency = (url = '') => {
  if (url.startsWith('https://t.me/')) return 'TELEGRAM';
  let hostname: string;
  try {
    const u = new URL(url);
    hostname = u.hostname || '';
  } catch {
    console.log('EXCEPTION for url ' + url)
    hostname =
      url
        .replace(/https?:\/\//i, '')
        .split(/[:/]/)
        .pop() || '';
  }
  const parts = hostname.split('.');
  const agency = (
    parts.length <= 2 ? parts[0] : parts.length === 4 ? parts[1] : parts[parts.length - 2]
  ).toUpperCase();
  return (isNaN(+agency)) ? agency : 'UNKNOWN';
};

console.log(extractAgency(url)); // LANCASTERGUARDIAN
console.log(extractAgency(url1)); // TUDELFT
console.log(extractAgency(url2)); // WHATSNEW2DAY
console.log(extractAgency(url3)); // NEWS4JAX

test_flems.md

Flems