mailpop 1.0.9 → 1.0.10

package/dist/extractor.js

@@ -2,9 +2,9 @@ import { load } from 'cheerio';
 import { normalizeEmail } from './utils/normalize.js';
 import { isValidEmail } from './utils/validators.js';
 // Standard email regex for searching inside strings
-const EMAIL_REGEX = /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}/g;
+const EMAIL_REGEX = /[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,10}\b/g;
 // Obfuscated email regex matching "name [at] domain [dot] com", "name(at)domain(dot)com", "name AT domain DOT com"
-const OBFUSCATED_REGEX = /([a-zA-Z0-9._%+-]+)\s*(?:\[at\]|\(at\)|\s+at\s+)\s*([a-zA-Z0-9.-]+)\s*(?:\[dot\]|\(dot\)|\s+dot\s+)\s*([a-zA-Z]{2,})/gi;
+const OBFUSCATED_REGEX = /([a-zA-Z0-9._%+-]+)\s*(?:\[at\]|\(at\)|\s+at\s+)\s*([a-zA-Z0-9.-]+)\s*(?:\[dot\]|\(dot\)|\s+dot\s+)\s*([a-zA-Z]{2,10})\b/gi;
 // Base64 candidate regex for extracting potential base64 encoded strings
 const BASE64_CANDIDATE_REGEX = /\b[a-zA-Z0-9+/]{12,80}={0,2}\b/g;
 /**
@@ -133,6 +133,23 @@ export function classifyEmailType(email) {
     }
     return 'personal';
 }
+/**
+ * Extract text from a cheerio element, inserting spaces between elements
+ * to prevent adjacent tags from concatenating their text content.
+ */
+export function extractTextWithSpaces(elem, $) {
+    if (!elem || elem.length === 0)
+        return '';
+    const htmlParts = [];
+    elem.each((_, el) => {
+        htmlParts.push($(el).html() || '');
+    });
+    const html = htmlParts.join(' ');
+    const cleanHtml = html
+        .replace(/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/gi, ' ')
+        .replace(/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/gi, ' ');
+    return decodeUnicodeEntities(cleanHtml.replace(/<[^>]+>/g, ' '));
+}
 /**
  * Extracts all unique emails from a given HTML string and URL.
  */
@@ -219,7 +236,7 @@ export function extractEmails(html, url, pageTitle, crawlDurationMs) {
     // 3. Header section extraction
     const headerElem = $('header, [id*="header"], [class*="header"]');
     if (headerElem.length > 0) {
-        const headerText = decodeUnicodeEntities(headerElem.text());
+        const headerText = extractTextWithSpaces(headerElem, $);
         let match;
         EMAIL_REGEX.lastIndex = 0;
         while ((match = EMAIL_REGEX.exec(headerText)) !== null) {
@@ -229,7 +246,7 @@ export function extractEmails(html, url, pageTitle, crawlDurationMs) {
     // 4. Footer section extraction
     const footerElem = $('footer, [id*="footer"], [class*="footer"]');
     if (footerElem.length > 0) {
-        const footerText = decodeUnicodeEntities(footerElem.text());
+        const footerText = extractTextWithSpaces(footerElem, $);
         let match;
         EMAIL_REGEX.lastIndex = 0;
         while ((match = EMAIL_REGEX.exec(footerText)) !== null) {
@@ -273,7 +290,7 @@ export function extractEmails(html, url, pageTitle, crawlDurationMs) {
         }
     });
     // 7. Visible Body Text & Obfuscated matches in body
-    const bodyText = decodeUnicodeEntities($('body').text());
+    const bodyText = extractTextWithSpaces($('body'), $);
     // Standard matches in body text
     let bodyMatch;
     EMAIL_REGEX.lastIndex = 0;

package/dist/utils/validators.js

@@ -1,7 +1,7 @@
 import { normalizeDomain } from './normalize.js';
 import { config } from '../config.js';
 import dns from 'dns/promises';
-const EMAIL_REGEX = /^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$/;
+const EMAIL_REGEX = /^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,10}$/;
 const MAX_EMAIL_LENGTH = 254;
 const MAX_LOCAL_PART_LENGTH = 64;
 const REJECTED_PREFIXES = [

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mailpop",
-  "version": "1.0.9",
+  "version": "1.0.10",
   "description": "Production-ready public contact email discovery tool from company websites.",
   "type": "module",
   "main": "dist/index.js",