Extracts RSA moduli for Fast-GCD (factorable.net) from masscan collected X.509 Certificates. Input needs to be stripped of non-X.509 entries first [use the power of grep(1)!].

extract_rsa_moduli.py

#!/usr/bin/env python
#
# Parsing of `masscan` collected X.509 certificates
# to extract RSA moduli for Fast-GCD (factorable.net).
# ..threaded Python version.     
#
# Authors: Aaron Zauner <azet@azet.org>
# License: CC0 1.0 (https://creativecommons.org/publicdomain/zero/1.0)
#
from __future__ import print_function

import sys, base64, threading, Queue
import ujson as json # best performing JSON lib. for Python
from M2Crypto import X509, RSA

obj = object()

def read_file(name, queue):
    with open(name) as file:
        for line in file:
            queue.put(line)
    queue.put(obj)

def worker(runqueue, printqueue):
    for line in iter(runqueue.get, obj):
        try:
            data = json.loads(str(line))
            der  = data['ports'][0]['service']['banner']
            cert = X509.load_cert_der_string(base64.b64decode(der))
            pub  = cert.get_pubkey()

            printqueue.put(pub.get_modulus())
        except:
            # do nothing on broken certificate
            pass
    printqueue.put(obj)

if __name__ == '__main__':
    filename   = sys.argv[1]
    runqueue   = Queue.Queue()
    printqueue = Queue.Queue()

    threading.Thread(target = read_file, args = (filename, runqueue)).start()
    threading.Thread(target = worker, args = (runqueue, printqueue)).start()

    for line in iter(printqueue.get, obj):
        print(line)