From c36dedfdd5eddda0c12bb3dbfdfe4033903b06df Mon Sep 17 00:00:00 2001
From: SukkaW <isukkaw@gmail.com>
Date: Wed, 23 Nov 2022 21:10:16 +0800
Subject: [PATCH] Stricter Phishing domain extraction

---
 Build/build-phishing-domainset.js | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/Build/build-phishing-domainset.js b/Build/build-phishing-domainset.js
index 1e341dce..e2f78a22 100644
--- a/Build/build-phishing-domainset.js
+++ b/Build/build-phishing-domainset.js
@@ -55,7 +55,7 @@ const BLACK_TLD = Array.from(new Set([
 
     const domain = line.charCodeAt(0) === 46 ? line.slice(1) : line;
 
-    if (domain.length > 25) {
+    if (domain.length > 19) {
       const apexDomain = tldts.getDomain(domain, { allowPrivateDomains: true });
 
       if (apexDomain) {
@@ -65,6 +65,11 @@ const BLACK_TLD = Array.from(new Set([
 
         domainCountMap[apexDomain] ||= 0;
         domainCountMap[apexDomain] += 1;
+
+        if (domain.length > 45) {
+          // Add more weight if the domain is long enough
+          domainCountMap[apexDomain] += 1;
+        }
       }
     }
   }