From ad112d9f81498b8aecfd44cd52fcf12b053cfe44 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Glauber=20Magalh=C3=A3es?= <glauber.tecinfo@gmail.com>
Date: Mon, 15 Jan 2024 21:46:10 -0300
Subject: [PATCH] remove repeated domains

---
 README.md        |  1 -
 requirements.txt |  1 -
 setup.py         |  2 +-
 src/evilurl.py   | 23 ++++++++---------------
 4 files changed, 9 insertions(+), 18 deletions(-)

diff --git a/README.md b/README.md
index d237fd6..07b7cf6 100644
--- a/README.md
+++ b/README.md
@@ -49,7 +49,6 @@ pip install evilurl
 
 ## Dependencies for Local Installation
 - Python 3
-- idna library
 
 Create a virtualenv
 
diff --git a/requirements.txt b/requirements.txt
index 6eea841..c516d9c 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -2,7 +2,6 @@ certifi==2023.11.17
 charset-normalizer==3.3.2
 docutils==0.20.1
 future==0.18.3
-idna==3.6
 importlib-metadata==7.0.1
 jaraco.classes==3.3.0
 keyring==24.3.0
diff --git a/setup.py b/setup.py
index 1564d57..c1b7507 100644
--- a/setup.py
+++ b/setup.py
@@ -4,7 +4,7 @@
 
 setup(
     name='evilurl',
-    version='0.0.16',
+    version='0.0.17',
     packages=['src'],
     package_data={'src': ['unicode_combinations.json']},
     setup_requires=['wheel'],
diff --git a/src/evilurl.py b/src/evilurl.py
index 1031ec4..2670c2d 100644
--- a/src/evilurl.py
+++ b/src/evilurl.py
@@ -3,7 +3,6 @@
 import sys
 from itertools import product
 from urllib.parse import urlsplit
-import idna
 import json
 
 header = """
@@ -24,13 +23,6 @@ def __init__(self, unicode_combinations, show_domains_only):
         self.unicode_combinations = unicode_combinations
         self.show_domains_only = show_domains_only
 
-    def convert_to_punycode(self, input_string):
-        try:
-            punycode = idna.encode(input_string)
-            return punycode.decode('utf-8')
-        except UnicodeError:
-            return None
-
     def check_domain_registration(self, domain_name):
         try:
             dns = socket.gethostbyname(domain_name)
@@ -65,12 +57,13 @@ def analyze_domain(self, domain):
         combinations = result[0]
         chars = result[1]
 
-        domains = []
+        unique_domains = set()  # Keep track of unique domains
+
         for combination in product(*combinations):
             new_domain = ''.join(combination) + '.' + '.'.join(domain_parts[1:])
-            domains.append(new_domain)
+            unique_domains.add(new_domain)  # Add the domain to the set
 
-        if len(domains) <= 1:
+        if len(unique_domains) <= 1:
             return print(f"IDN homograph attack is not possible for this domain with the current character set")
 
         if not self.show_domains_only:
@@ -79,16 +72,16 @@ def analyze_domain(self, domain):
             print(f"\033[32m[\033[0m*\033[32m]\033[0m Homograph characters used: \033[32m{chars}\033[0m")
 
         if self.show_domains_only:
-            for new_domain in domains[1:]:
+            for new_domain in unique_domains:
                 print(new_domain)
         else:
-            for index, new_domain in enumerate(domains[1:]):
+            for index, new_domain in enumerate(unique_domains):
                 dns = self.check_domain_registration(new_domain)
-                punycode_encoded_domain = self.convert_to_punycode(new_domain)
+                punycode_encoded_domain = new_domain.encode('idna').decode()
                 
                 if new_domain == punycode_encoded_domain:
                     continue
-                
+
                 print(f"\n{index + 1} -------------------------------")
                 print(f"homograph domain: {new_domain}")
                 print(f"punycode: {punycode_encoded_domain}")