Quick-and-dirty script to find sites hosted on CloudFlare

hosted-on-cloudflare.py

#!/usr/bin/python3

import argparse

# pip install urlextract dnspython tldextract
import dns.name
import dns.resolver
import urlextract
import tldextract

def read_urls(infile):
    extractor = urlextract.URLExtract()
    urls = set()
    with open(infile, "r", encoding="UTF-8") as f:
        for line in f:
            urls.update(extractor.find_urls(line))
    return urls

def lookup_hosts(domains, verbose):
    cf = dns.name.from_text('cloudflare.com')
    for domain in domains:
        try:
            answers = dns.resolver.query(domain, 'NS')
            is_cf = any(x.target.is_subdomain(cf) for x in answers)
            if verbose:
                print("%-40s: %s" % (domain, is_cf))
            elif is_cf:
                print(domain)
        except (dns.resolver.NoAnswer, dns.resolver.NXDOMAIN) as e:
            print("%s: %s" % (domain, e))

def get_args():
    parser = argparse.ArgumentParser(description='checks for each url from a file if it is hosted on CloudFlare')

    parser.add_argument(type=str, default=None, metavar='<file>', dest='file',
                        help='input text file with URLs to extract. [UTF-8]')
    parser.add_argument('--verbose', dest='verbose', action='store_true')
    args = parser.parse_args()
    return args


if __name__ == '__main__':
    args = get_args()
    urls = read_urls(args.file)
    domains = (tldextract.extract(url).registered_domain for url in urls)
    lookup_hosts(domains, args.verbose)