mr-rizwan-syed · April 20, 2025 18:44 · Apr 16, 2024 · Feb 1, 2024 · Feb 1, 2024
diff --git a/tldextractor.py b/tldextractor.py
@@ -1,36 +1,56 @@
 import sys
 import tldextract
 
-def extract_apex_domains_from_file(file_path):
-    try:
-        with open(file_path, 'r') as file:
-            subdomains = [line.strip() for line in file.readlines()]
+def is_valid_domain(domain):
+    # Check if the domain contains only alphanumeric characters and hyphens
+    if not domain.replace('-', '').replace('.', '').isalnum():
+        return False
 
-        apex_domains = set()
+    # Check if the domain doesn't end with a period
+    if domain.endswith('.'):
+        return False
 
-        for subdomain in subdomains:
-            # Use tldextract to extract the domain information
-            domain_info = tldextract.extract(subdomain)
+    return True
 
-            # Construct the apex domain
-            apex_domain = f"{domain_info.domain}.{domain_info.suffix}"
+def extract_apex_domains_from_input(input_data):
+    subdomains = input_data.splitlines()
 
+    apex_domains = set()
+
+    for subdomain in subdomains:
+        # Use tldextract to extract the domain information
+        domain_info = tldextract.extract(subdomain)
+
+        # Construct the apex domain
+        apex_domain = f"{domain_info.domain}.{domain_info.suffix}"
+
+        # Check if the apex domain is valid
+        if is_valid_domain(apex_domain):
             # Add to the set to ensure uniqueness
             apex_domains.add(apex_domain)
 
-        return list(apex_domains)
-    except FileNotFoundError:
-        print(f"Error: File '{file_path}' not found.")
-        return []
+    return list(apex_domains)
 
 if __name__ == "__main__":
-    if len(sys.argv) != 2:
-        print("Usage: python script.py <subdomains_file>")
+    if len(sys.argv) == 2:
+        file_path = sys.argv[1]
+        try:
+            with open(file_path, 'r') as file:
+                input_data = file.read()
+        except FileNotFoundError:
+            print(f"Error: File '{file_path}' not found.")
+            sys.exit(1)
+    elif len(sys.argv) == 1:
+        # Read from stdin
+        input_data = sys.stdin.read()
+    else:
+        print("Usage: python script.py [<subdomains_file>]")
         sys.exit(1)
 
-    subdomains_file = sys.argv[1]
-    apex_domains = extract_apex_domains_from_file(subdomains_file)
+    apex_domains = extract_apex_domains_from_input(input_data)
 
-    print("Apex Domains:")
-    for apex_domain in apex_domains:
-        print(apex_domain)
+    if apex_domains:
+        for apex_domain in apex_domains:
+            print(apex_domain)
+    else:
+        print("No valid apex domains found.")
diff --git a/gistfile1.txt → tldextractor.py b/gistfile1.txt → tldextractor.py
diff --git a/gistfile1.txt b/gistfile1.txt
@@ -0,0 +1,36 @@
+import sys
+import tldextract
+
+def extract_apex_domains_from_file(file_path):
+    try:
+        with open(file_path, 'r') as file:
+            subdomains = [line.strip() for line in file.readlines()]
+
+        apex_domains = set()
+
+        for subdomain in subdomains:
+            # Use tldextract to extract the domain information
+            domain_info = tldextract.extract(subdomain)
+
+            # Construct the apex domain
+            apex_domain = f"{domain_info.domain}.{domain_info.suffix}"
+
+            # Add to the set to ensure uniqueness
+            apex_domains.add(apex_domain)
+
+        return list(apex_domains)
+    except FileNotFoundError:
+        print(f"Error: File '{file_path}' not found.")
+        return []
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Usage: python script.py <subdomains_file>")
+        sys.exit(1)
+
+    subdomains_file = sys.argv[1]
+    apex_domains = extract_apex_domains_from_file(subdomains_file)
+
+    print("Apex Domains:")
+    for apex_domain in apex_domains:
+        print(apex_domain)