How to Build an Email Finder That Actually Works (Node.js)

#webdev #javascript #node #tutorial

Email finders are one of the most valuable scraping tools. Here is how to build one that finds real emails.

Method 1: Scrape from Websites

const cheerio = require("cheerio");

async function findEmails(url) {
  const res = await fetch(url, { headers: { "User-Agent": "EmailBot/1.0" } });
  const html = await res.text();
  const $ = cheerio.load(html);
  $("script, style").remove();
  const text = $("body").text();

  const emails = [...new Set(
    (text.match(/[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g) || [])
    .filter(e => !e.includes("example.com") && !e.includes("noreply"))
  )];

  // Also check mailto links
  $("a[href^=mailto:]").each((i, el) => {
    const e = $(el).attr("href").replace("mailto:","").split("?")[0];
    if (!emails.includes(e)) emails.push(e);
  });

  return emails;
}

Method 2: Pattern-Based Guessing

function guessEmails(name, domain) {
  const [first, last] = name.toLowerCase().split(" ");
  return [
    `${first}@${domain}`,
    `${first}.${last}@${domain}`,
    `${first[0]}${last}@${domain}`,
    `${first}${last[0]}@${domain}`,
    `${first}_${last}@${domain}`
  ];
}
// Then verify with SMTP check or API

Method 3: Common Pages to Check

Most company emails are on:

/contact
/about
/team
/support
Footer of any page

const pages = ["/contact", "/about", "/team", "/support"];
const allEmails = [];
for (const page of pages) {
  const emails = await findEmails(domain + page);
  allEmails.push(...emails);
}
const unique = [...new Set(allEmails)];