Last active
April 20, 2025 18:44
-
-
Save mr-rizwan-syed/8933e5183fd8313d24cf854f8a4e9fcd to your computer and use it in GitHub Desktop.
The script takes list of subdomains and extracts their apex (root) domains using the tldextract library, and prints the unique set of apex domains.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import sys | |
| import tldextract | |
| def is_valid_domain(domain): | |
| # Check if the domain contains only alphanumeric characters and hyphens | |
| if not domain.replace('-', '').replace('.', '').isalnum(): | |
| return False | |
| # Check if the domain doesn't end with a period | |
| if domain.endswith('.'): | |
| return False | |
| return True | |
| 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) | |
| if __name__ == "__main__": | |
| 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) | |
| apex_domains = extract_apex_domains_from_input(input_data) | |
| if apex_domains: | |
| for apex_domain in apex_domains: | |
| print(apex_domain) | |
| else: | |
| print("No valid apex domains found.") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment