hosts_to_domains

#!/usr/bin/env python3

###########
# IMPORTS #
###########

import os
import sys
import argparse

########
# MAIN #
########

if __name__ == '__main__':
    desc = 'Extract domains from the supplied FQDNs and output a list of results.'

    parser = argparse.ArgumentParser(description=desc)
    parser.add_argument('file',
                        nargs='?',
                        type=argparse.FileType('r'),
                        action='store',
                        help='file containing a list of IP addresses split by a newline, otherwise read from STDIN',
                        metavar='FILE',
                        default=sys.stdin)
    parser.add_argument('-s', '--suffixes',
                        nargs='?',
                        type=argparse.FileType('r'),
                        action='store',
                        help='a list of TLDs to use as suffixes to aid identification (default: %s/wordlists/dns/tlds.txt)' % os.path.dirname(os.path.realpath(__file__)),
                        metavar='FILE',
                        default="%s/wordlists/dns/tlds.txt" % os.path.dirname(os.path.realpath(__file__)))
    parser.add_argument('-d', '--depth',
                    type=int,
                    action='store',
                    help='only list domains up to a maximum depth (default: unlimited)',
                    metavar='INT',
                    default=0)
    args = parser.parse_args()

    try:
        hosts = [line.strip() for line in args.file if len(line.strip())>0 and line[0] != '#']
    except KeyboardInterrupt:
        exit()
    
    try:
        suffixes = [line.strip() for line in args.suffixes if len(line.strip())>0 and line[0] != '#']
    except KeyboardInterrupt:
        exit()

    domains = []

    for host in hosts:
        elements = host.split('.')
        # recursively walk through the elements
        # extracting all possible (sub)domains
        while len(elements) >= 2:
            # account for domains stored as hosts
            if len(elements) == 2:
                domain = '.'.join(elements)
            else:
                # drop the host element
                domain = '.'.join(elements[1:])
            if domain not in domains + suffixes:
                    domains.append(domain)
            del elements[0]

    for domain in domains:
        if args.depth < 1:
            print(domain)
        else:
            for suffix in sorted(suffixes, key=lambda x: x.count('.'), reverse=True):
                if domain.lower().endswith('.' + suffix.lower()):
                    sub = domain[:-(len(suffix) + 1)]
                    if sub.count('.') < args.depth:
                        print(domain)
                    break