def start(argv):
    if len(sys.argv) < 4:
        usage()
        sys.exit()
    try:
        opts, args = getopt.getopt(argv, "l:d:b:s:vf:nhcpte:")
    except getopt.GetoptError:
        usage()
        sys.exit()
    try:
        db = stash.stash_manager()
        db.do_init()
    except Exception, e:
        pass
                              "netcraft", "all"):
                usage()
                print "Invalid search engine, try with: baidu, bing, bingapi, crtsh, dogpile, google, googleCSE, virustotal, netcraft, googleplus, google-profiles, linkedin, pgp, twitter, vhost, yahoo, all"
                sys.exit()
            else:
                pass
    print "[-] Starting harvesting process for domain: " + word + "\n"
    if engine == "google":
        print "[-] Searching in Google:"
        search = googlesearch.search_google(word, limit, start)
        search.process()
        all_emails = search.get_emails()
        all_hosts = search.get_hostnames()
        for x in all_hosts:
            try:
                db = stash.stash_manager()
                db.store(word, x, 'host', 'google')
            except Exception, e:
                print e

    if engine == "netcraft":
        print "[-] Searching in Netcraft:"
        search = netcraft.search_netcraft(word)
        search.process()
        all_hosts = search.get_hostnames()
        all_emails = []
        db = stash.stash_manager()
        db.store_all(word, all_hosts, 'host', 'netcraft')

    if engine == "threatcrowd":
        print "[-] Searching in Threatcrowd:"
def start(argv):
    if len(sys.argv) < 4:
        Core.usage()
        sys.exit(1)
    try:
        opts, args = getopt.getopt(argv, 'l:d:b:s:u:vf:nhcgpte:')
    except getopt.GetoptError:
        Core.usage()
        sys.exit(1)
    try:
        db = stash.stash_manager()
        db.do_init()
    except Exception as e:
        pass

    all_emails = []
    all_hosts = []
    all_ip = []
    bingapi = 'yes'
    dnsbrute = False
    dnslookup = False
    dnsserver = ""
    dnstld = False
    filename = ""
    full = []
    google_dorking = False
    host_ip = []
    limit = 500
    ports_scanning = False
    shodan = False
    start = 0
    takeover_check = False
    trello_info = ([], False)
    vhost = []
    virtual = False

    for value in enumerate(opts):
        opt = value[1][0]
        arg = value[1][1]
        opt = str(opt)
        arg = str(arg)
        if opt == '-l':
            limit = int(arg)
        elif opt == '-d':
            word = arg
        elif opt == '-g':
            google_dorking = True
        elif opt == '-s':
            start = int(arg)
        elif opt == '-v':
            virtual = 'basic'
        elif opt == '-f':
            filename = arg
        elif opt == '-n':
            dnslookup = True
        elif opt == '-c':
            dnsbrute = True
        elif opt == '-h':
            shodan = True
        elif opt == '-e':
            dnsserver = arg
        elif opt == '-p':
            ports_scanning = True
        elif opt == '-t':
            dnstld = True
        elif opt == '-b':
            engines = set(arg.split(','))
            supportedengines = set([
                'baidu', 'bing', 'bingapi', 'censys', 'crtsh', 'cymon',
                'dogpile', 'duckduckgo', 'google', 'googleCSE',
                'google-certificates', 'google-profiles', 'hunter', 'linkedin',
                'netcraft', 'pgp', 'securityTrails', 'threatcrowd', 'trello',
                'twitter', 'vhost', 'virustotal', 'yahoo', 'all'
            ])
            if set(engines).issubset(supportedengines):
                print(f'\033[94m[*] Target domain: {word} \n \033[0m')
                for engineitem in engines:
                    if engineitem == 'baidu':
                        print('\033[94m[*] Searching Baidu. \033[0m')
                        try:
                            search = baidusearch.SearchBaidu(word, limit)
                            search.process()
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'baidu')
                            db.store_all(word, all_emails, 'email', 'baidu')
                        except Exception:
                            pass

                    elif engineitem == 'bing' or engineitem == 'bingapi':
                        print('\033[94m[*] Searching Bing. \033[0m')
                        try:
                            search = bingsearch.SearchBing(word, limit, start)
                            if engineitem == 'bingapi':
                                bingapi = 'yes'
                            else:
                                bingapi = 'no'
                            search.process(bingapi)
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'email', 'bing')
                            db.store_all(word, all_hosts, 'host', 'bing')
                        except Exception as e:
                            if isinstance(e, MissingKey):
                                print(e)
                            else:
                                pass

                    elif engineitem == 'censys':
                        print('\033[94m[*] Searching Censys. \033[0m')
                        from discovery import censys
                        # Import locally or won't work
                        search = censys.SearchCensys(word, limit)
                        search.process()
                        all_ip = search.get_ipaddresses()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'censys')
                        db.store_all(word, all_ip, 'ip', 'censys')

                    elif engineitem == 'crtsh':
                        print('\033[94m[*] Searching CRT.sh. \033[0m')
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                    elif engineitem == 'cymon':
                        print('\033[94m[*] Searching Cymon. \033[0m')
                        from discovery import cymon
                        # Import locally or won't work.
                        search = cymon.search_cymon(word)
                        search.process()
                        all_ip = search.get_ipaddresses()
                        db = stash.stash_manager()
                        db.store_all(word, all_ip, 'ip', 'cymon')

                    elif engineitem == 'dogpile':
                        print('\033[94m[*] Searching Dogpile. \033[0m')
                        search = dogpilesearch.SearchDogpile(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'dogpile')
                        db.store_all(word, all_hosts, 'host', 'dogpile')

                    elif engineitem == 'duckduckgo':
                        print('\033[94m[*] Searching DuckDuckGo. \033[0m')
                        from discovery import duckduckgosearch
                        search = duckduckgosearch.SearchDuckDuckGo(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'duckduckgo')
                        db.store_all(word, all_hosts, 'host', 'duckduckgo')

                    elif engineitem == 'google':
                        print('\033[94m[*] Searching Google. \033[0m')
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'google')
                        db.store_all(word, all_emails, 'email', 'google')

                    elif engineitem == 'googleCSE':
                        print(
                            '\033[94m[*] Searching Google Custom Search. \033[0m'
                        )
                        try:
                            search = googleCSE.SearchGoogleCSE(
                                word, limit, start)
                            search.process()
                            search.store_results()
                            all_emails = filter(search.get_emails())
                            db = stash.stash_manager()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db.store_all(word, all_hosts, 'email', 'googleCSE')
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'googleCSE')
                        except Exception as e:
                            if isinstance(e, MissingKey):
                                print(e)
                            else:
                                pass

                    elif engineitem == 'google-certificates':
                        print(
                            '\033[94m[*] Searching Google Certificate transparency report. \033[0m'
                        )
                        search = googlecertificates.SearchGoogleCertificates(
                            word, limit, start)
                        search.process()
                        hosts = filter(search.get_domains())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host',
                                     'google-certificates')

                    elif engineitem == 'google-profiles':
                        print('\033[94m[*] Searching Google profiles. \033[0m')
                        search = googlesearch.search_google(word, limit, start)
                        search.process_profiles()
                        people = search.get_profiles()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'google-profile')

                        if len(people) == 0:
                            print('\n[*] No users found.\n\n')
                        else:
                            print('\n[*] Users found: ' + str(len(people)))
                            print('---------------------')
                            for user in sorted(list(set(people))):
                                print(user)
                        sys.exit(0)

                    elif engineitem == 'hunter':
                        print('\033[94m[*] Searching Hunter. \033[0m')
                        from discovery import huntersearch
                        # Import locally or won't work.
                        try:
                            search = huntersearch.SearchHunter(
                                word, limit, start)
                            search.process()
                            emails = filter(search.get_emails())
                            all_emails.extend(emails)
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'hunter')
                            db.store_all(word, all_emails, 'email', 'hunter')
                        except Exception as e:
                            if isinstance(e, MissingKey):
                                print(e)
                            else:
                                pass

                    elif engineitem == 'linkedin':
                        print('\033[94m[*] Searching Linkedin. \033[0m')
                        search = linkedinsearch.SearchLinkedin(word, limit)
                        search.process()
                        people = search.get_people()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'linkedin')

                        if len(people) == 0:
                            print('\n[*] No users found.\n\n')
                        else:
                            print('\n[*] Users found: ' + str(len(people)))
                            print('---------------------')
                            for user in sorted(list(set(people))):
                                print(user)
                        sys.exit(0)

                    elif engineitem == 'netcraft':
                        print('\033[94m[*] Searching Netcraft. \033[0m')
                        search = netcraft.SearchNetcraft(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                    elif engineitem == 'pgp':
                        print('\033[94m[*] Searching PGP key server. \033[0m')
                        try:
                            search = pgpsearch.SearchPgp(word)
                            search.process()
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'pgp')
                            db.store_all(word, all_emails, 'email', 'pgp')
                        except Exception:
                            pass

                    elif engineitem == 'securityTrails':
                        print('\033[94m[*] Searching SecurityTrails. \033[0m')
                        from discovery import securitytrailssearch
                        try:
                            search = securitytrailssearch.search_securitytrail(
                                word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, hosts, 'host', 'securityTrails')
                            ips = search.get_ips()
                            all_ip.extend(ips)
                            db = stash.stash_manager()
                            db.store_all(word, ips, 'ip', 'securityTrails')
                        except Exception as e:
                            if isinstance(e, MissingKey):
                                print(e)
                            else:
                                pass

                    elif engineitem == 'threatcrowd':
                        print('\033[94m[*] Searching Threatcrowd. \033[0m')
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host',
                                         'threatcrowd')
                        except Exception:
                            pass

                    elif engineitem == 'trello':
                        print('\033[94m[*] Searching Trello. \033[0m')
                        from discovery import trello
                        # Import locally or won't work.
                        search = trello.search_trello(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        info = search.get_urls()
                        hosts = filter(info[0])
                        trello_info = (info[1], True)
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, hosts, 'host', 'trello')
                        db.store_all(word, emails, 'email', 'trello')

                    elif engineitem == 'twitter':
                        print('\033[94m[*] Searching Twitter. \033[0m')
                        search = twittersearch.search_twitter(word, limit)
                        search.process()
                        people = search.get_people()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'twitter')

                        if len(people) == 0:
                            print('\n[*] No users found.\n\n')
                        else:
                            print('\n[*] Users found: ' + str(len(people)))
                            print('---------------------')
                            for user in sorted(list(set(people))):
                                print(user)
                        sys.exit(0)

                    # vhost

                    elif engineitem == 'virustotal':
                        print('\033[94m[*] Searching VirusTotal. \033[0m')
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                    elif engineitem == 'yahoo':
                        print('\033[94m[*] Searching Yahoo. \033[0m')
                        search = yahoosearch.search_yahoo(word, limit)
                        search.process()
                        hosts = search.get_hostnames()
                        emails = search.get_emails()
                        all_hosts.extend(filter(hosts))
                        all_emails.extend(filter(emails))
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'yahoo')
                        db.store_all(word, all_emails, 'email', 'yahoo')

                    elif engineitem == 'all':
                        print(('Full harvest on ' + word))
                        all_emails = []
                        all_hosts = []
                        try:
                            print('[*] Searching Baidu.')
                            search = baidusearch.SearchBaidu(word, limit)
                            search.process()
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'baidu')
                            db.store_all(word, all_emails, 'email', 'baidu')
                        except Exception:
                            pass

                        print('[*] Searching Bing.')
                        bingapi = 'no'
                        search = bingsearch.SearchBing(word, limit, start)
                        search.process(bingapi)
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'bing')
                        all_emails.extend(emails)
                        all_emails = sorted(set(all_emails))
                        db.store_all(word, all_emails, 'email', 'bing')

                        print('[*] Searching Censys.')
                        from discovery import censys
                        search = censys.SearchCensys(word, limit)
                        search.process()
                        ips = search.get_ipaddresses()
                        setips = set(ips)
                        uniqueips = list(setips)  # Remove duplicates.
                        all_ip.extend(uniqueips)
                        hosts = filter(search.get_hostnames())
                        sethosts = set(hosts)
                        uniquehosts = list(sethosts)  # Remove duplicates.
                        all_hosts.extend(uniquehosts)
                        db = stash.stash_manager()
                        db.store_all(word, uniquehosts, 'host', 'censys')
                        db.store_all(word, uniqueips, 'ip', 'censys')

                        print('[*] Searching CRT.sh.')
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                        # cymon

                        # dogpile

                        print('[*] Searching DuckDuckGo.')
                        from discovery import duckduckgosearch
                        search = duckduckgosearch.SearchDuckDuckGo(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'duckduckgo')
                        db.store_all(word, all_hosts, 'host', 'duckduckgo')

                        print('[*] Searching Google.')
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_emails, 'email', 'google')
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'google')

                        print(
                            '[*] Searching Google Certificate transparency report.'
                        )
                        search = googlecertificates.SearchGoogleCertificates(
                            word, limit, start)
                        search.process()
                        domains = filter(search.get_domains())
                        all_hosts.extend(domains)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host',
                                     'google-certificates')

                        try:
                            print('[*] Searching Google profiles.')
                            search = googlesearch.search_google(
                                word, limit, start)
                            search.process_profiles()
                            people = search.get_profiles()
                            db = stash.stash_manager()
                            db.store_all(word, people, 'name',
                                         'google-profile')
                            print('\nUsers from Google profiles:')
                            print('---------------------------')
                            for users in people:
                                print(users)
                        except Exception:
                            pass

                        print('[*] Searching Hunter.')
                        from discovery import huntersearch
                        # Import locally.
                        try:
                            search = huntersearch.SearchHunter(
                                word, limit, start)
                            search.process()
                            emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, hosts, 'host', 'hunter')
                            all_emails.extend(emails)
                            all_emails = sorted(set(all_emails))
                            db.store_all(word, all_emails, 'email', 'hunter')
                        except Exception as e:
                            if isinstance(e, MissingKey):
                                print(e)
                            else:
                                pass

                        # linkedin

                        print('[*] Searching Netcraft.')
                        search = netcraft.SearchNetcraft(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                        print('[*] Searching PGP key server.')
                        try:
                            search = pgpsearch.SearchPgp(word)
                            search.process()
                            emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            sethosts = set(hosts)
                            uniquehosts = list(sethosts)  # Remove duplicates.
                            all_hosts.extend(uniquehosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'PGP')
                            all_emails.extend(emails)
                            db = stash.stash_manager()
                            db.store_all(word, all_emails, 'email', 'PGP')
                        except Exception:
                            pass

                        print('[*] Searching Threatcrowd.')
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host',
                                         'threatcrowd')
                        except Exception:
                            pass

                        print('[*] Searching Trello.')
                        from discovery import trello
                        # Import locally or won't work.
                        search = trello.search_trello(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        info = search.get_urls()
                        hosts = filter(info[0])
                        trello_info = (info[1], True)
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, hosts, 'host', 'trello')
                        db.store_all(word, emails, 'email', 'trello')

                        try:
                            print('[*] Searching Twitter.')
                            search = twittersearch.search_twitter(word, limit)
                            search.process()
                            people = search.get_people()
                            db = stash.stash_manager()
                            db.store_all(word, people, 'name', 'twitter')
                            print('\nUsers from Twitter:')
                            print('-------------------')
                            for user in people:
                                print(user)
                        except Exception:
                            pass

                        # vhost

                        print('[*] Searching VirusTotal.')
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                        print('[*] Searching Yahoo.')
                        search = yahoosearch.search_yahoo(word, limit)
                        search.process()
                        hosts = search.get_hostnames()
                        emails = search.get_emails()
                        all_hosts.extend(filter(hosts))
                        all_emails.extend(filter(emails))
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'yahoo')
                        db.store_all(word, all_emails, 'email', 'yahoo')
            else:
                print('\033[93m[!] Invalid source.\n\n \033[0m')
                sys.exit(1)

    # Sanity check to see if all_emails and all_hosts are defined.
    try:
        all_emails
    except NameError:
        print(
            '\n\n\033[93m[!] No emails found because all_emails is not defined.\n\n \033[0m'
        )
        sys.exit(1)
    try:
        all_hosts
    except NameError:
        print(
            '\n\n\033[93m[!] No hosts found because all_hosts is not defined.\n\n \033[0m'
        )
        sys.exit(1)

    # Results
    if len(all_ip) == 0:
        print('\n[*] No IPs found.')
    else:
        print('\n[*] IPs found: ' + str(len(all_ip)))
        print('-------------------')
        ips = sorted(ipaddress.ip_address(line.strip()) for line in all_ip)
        print('\n'.join(map(str, ips)))

    if len(all_emails) == 0:
        print('\n[*] No emails found.')
    else:
        print('\n[*] Emails found: ' + str(len(all_emails)))
        print('----------------------')
        print(('\n'.join(sorted(list(set(all_emails))))))

    if len(all_hosts) == 0:
        print('\n[*] No hosts found.\n\n')
    else:
        print('\n[*] Hosts found: ' + str(len(all_hosts)))
        print('---------------------')
        all_hosts = sorted(list(set(all_hosts)))
        full_host = hostchecker.Checker(all_hosts)
        full = full_host.check()
        for host in full:
            ip = host.split(':')[1]
            print(host)
            if ip != 'empty':
                if host_ip.count(ip.lower()):
                    pass
                else:
                    host_ip.append(ip.lower())

        db = stash.stash_manager()
        db.store_all(word, host_ip, 'ip', 'DNS-resolver')

    if trello_info[1] is True:
        trello_urls = trello_info[0]
        if trello_urls == []:
            print('\n[*] No URLs found.')
        else:
            total = len(trello_urls)
            print('\n[*] URLs found: ' + str(total))
            print('--------------------')
            for url in sorted(list(set(trello_urls))):
                print(url)

    # DNS brute force
    dnsres = []
    if dnsbrute is True:
        print('\n[*] Starting DNS brute force.')
        a = dnssearch.dns_force(word, dnsserver, verbose=True)
        res = a.process()
        print('\n[*] Hosts found after DNS brute force:')
        print('-------------------------------------')
        for y in res:
            print(y)
            dnsres.append(y.split(':')[0])
            if y not in full:
                full.append(y)
        db = stash.stash_manager()
        db.store_all(word, dnsres, 'host', 'dns_bruteforce')

    # Port scanning
    if ports_scanning is True:
        print('\n\n[*] Scanning ports (active).\n')
        for x in full:
            host = x.split(':')[1]
            domain = x.split(':')[0]
            if host != 'empty':
                print(('[*] Scanning ' + host))
                ports = [21, 22, 80, 443, 8080]
                try:
                    scan = port_scanner.PortScan(host, ports)
                    openports = scan.process()
                    if len(openports) > 1:
                        print(('\t[*] Detected open ports: ' +
                               ','.join(str(e) for e in openports)))
                    takeover_check = 'True'
                    if takeover_check == 'True':
                        if len(openports) > 0:
                            search_take = takeover.take_over(domain)
                            search_take.process()
                except Exception as e:
                    print(e)

    # DNS reverse lookup
    dnsrev = []
    if dnslookup is True:
        print('\n[*] Starting active queries.')
        analyzed_ranges = []
        for x in host_ip:
            print(x)
            ip = x.split(':')[0]
            range = ip.split('.')
            range[3] = '0/24'
            s = '.'
            range = s.join(range)
            if not analyzed_ranges.count(range):
                print('[*] Performing reverse lookup in ' + range)
                a = dnssearch.dns_reverse(range, True)
                a.list()
                res = a.process()
                analyzed_ranges.append(range)
            else:
                continue
            for x in res:
                if x.count(word):
                    dnsrev.append(x)
                    if x not in full:
                        full.append(x)
        print('Hosts found after reverse lookup (in target domain):')
        print('----------------------------------------------------')
        for xh in dnsrev:
            print(xh)

    # DNS TLD expansion
    dnstldres = []
    if dnstld is True:
        print('[*] Starting DNS TLD expansion.')
        a = dnssearch.dns_tld(word, dnsserver, verbose=True)
        res = a.process()
        print('\n[*] Hosts found after DNS TLD expansion:')
        print('----------------------------------------')
        for y in res:
            print(y)
            dnstldres.append(y)
            if y not in full:
                full.append(y)

    # Virtual hosts search
    if virtual == 'basic':
        print('\n[*] Virtual hosts:')
        print('------------------')
        for l in host_ip:
            search = bingsearch.SearchBing(l, limit, start)
            search.process_vhost()
            res = search.get_allhostnames()
            for x in res:
                x = re.sub(r'[[\<\/?]*[\w]*>]*', '', x)
                x = re.sub('<', '', x)
                x = re.sub('>', '', x)
                print((l + '\t' + x))
                vhost.append(l + ':' + x)
                full.append(l + ':' + x)
        vhost = sorted(set(vhost))
    else:
        pass

    # Shodan
    shodanres = []
    import texttable
    tab = texttable.Texttable()
    header = [
        'IP address', 'Hostname', 'Org', 'Services:Ports', 'Technologies'
    ]
    tab.header(header)
    tab.set_cols_align(['c', 'c', 'c', 'c', 'c'])
    tab.set_cols_valign(['m', 'm', 'm', 'm', 'm'])
    tab.set_chars(['-', '|', '+', '#'])
    tab.set_cols_width([15, 20, 15, 15, 18])
    host_ip = list(set(host_ip))
    if shodan is True:
        print('\n\n[*] Shodan DB search (passive):\n')
        try:
            for ip in host_ip:
                print(('\tSearching for: ' + ip))
                shodan = shodansearch.search_shodan()
                rowdata = shodan.search_ip(ip)
                time.sleep(2)
                tab.add_row(rowdata)
            printedtable = tab.draw()
            print('\n [*] Shodan results:')
            print('-------------------')
            print(printedtable)
        except Exception as e:
            print(
                f'[!] Error occurred in theHarvester - Shodan search module: {e}'
            )
    else:
        pass

    # Here we need to add explosion mode.
    # We have to take out the TLDs to do this.
    recursion = None
    if recursion:
        start = 0
        for word in vhost:
            search = googlesearch.search_google(word, limit, start)
            search.process(google_dorking)
            emails = search.get_emails()
            hosts = search.get_hostnames()
            print(emails)
            print(hosts)
    else:
        pass

    # Reporting
    if filename != "":
        try:
            print('NEW REPORTING BEGINS.')
            db = stash.stash_manager()
            scanboarddata = db.getscanboarddata()
            latestscanresults = db.getlatestscanresults(word)
            previousscanresults = db.getlatestscanresults(word,
                                                          previousday=True)
            latestscanchartdata = db.latestscanchartdata(word)
            scanhistorydomain = db.getscanhistorydomain(word)
            pluginscanstatistics = db.getpluginscanstatistics()
            generator = statichtmlgenerator.htmlgenerator(word)
            HTMLcode = generator.beginhtml()
            HTMLcode += generator.generatelatestscanresults(latestscanresults)
            HTMLcode += generator.generatepreviousscanresults(
                previousscanresults)
            graph = reportgraph.graphgenerator(word)
            HTMLcode += graph.drawlatestscangraph(word, latestscanchartdata)
            HTMLcode += graph.drawscattergraphscanhistory(
                word, scanhistorydomain)
            HTMLcode += generator.generatepluginscanstatistics(
                pluginscanstatistics)
            HTMLcode += generator.generatedashboardcode(scanboarddata)
            HTMLcode += '<p><span style="color: #000000;">Report generated on ' + str(
                datetime.datetime.now()) + '</span></p>'
            HTMLcode += '''
            </body>
            </html>
            '''
            Html_file = open('report.html', 'w')
            Html_file.write(HTMLcode)
            Html_file.close()
            print('NEW REPORTING FINISHED!')
            print('[*] Saving files.')
            html = htmlExport.htmlExport(all_emails, full, vhost, dnsres,
                                         dnsrev, filename, word, shodanres,
                                         dnstldres)
            save = html.writehtml()
        except Exception as e:
            print(e)
            print('Error creating the file.')
        try:
            filename = filename.split('.')[0] + '.xml'
            file = open(filename, 'w')
            file.write('<?xml version="1.0" encoding="UTF-8"?><theHarvester>')
            for x in all_emails:
                file.write('<email>' + x + '</email>')
            for x in full:
                x = x.split(':')
                if len(x) == 2:
                    file.write('<host>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</host>')
                else:
                    file.write('<host>' + x + '</host>')
            for x in vhost:
                x = x.split(':')
                if len(x) == 2:
                    file.write('<vhost>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</vhost>')
                else:
                    file.write('<vhost>' + x + '</vhost>')
            if shodanres != []:
                shodanalysis = []
                for x in shodanres:
                    res = x.split('SAPO')
                    file.write('<shodan>')
                    file.write('<host>' + res[0] + '</host>')
                    file.write('<port>' + res[2] + '</port>')
                    file.write('<banner><!--' + res[1] + '--></banner>')
                    reg_server = re.compile('Server:.*')
                    temp = reg_server.findall(res[1])
                    if temp != []:
                        shodanalysis.append(res[0] + ':' + temp[0])
                    file.write('</shodan>')
                if shodanalysis != []:
                    shodanalysis = sorted(set(shodanalysis))
                    file.write('<servers>')
                    for x in shodanalysis:
                        file.write('<server>' + x + '</server>')
                    file.write('</servers>')

            file.write('</theHarvester>')
            file.flush()
            file.close()
            print('Files saved!')
        except Exception as er:
            print(f'Error saving XML file: {er}')
        print('\n\n')
        sys.exit(0)
Exemple #4
0
def start(argv):

    if len(sys.argv) < 4:
        usage()
        sys.exit()
    try:
        opts, args = getopt.getopt(argv, "l:d:b:s:u:vf:nhcgpte:")
    except getopt.GetoptError:
        usage()
        sys.exit()
    try:
        db = stash.stash_manager()
        db.do_init()
    except Exception as e:
        pass
    start = 0
    host_ip = []
    filename = ""
    bingapi = "yes"
    dnslookup = False
    dnsbrute = False
    dnstld = False
    shodan = False
    vhost = []
    virtual = False
    ports_scanning = False
    takeover_check = False
    google_dorking = False
    limit = 500
    full = []
    dnsserver = ""
    for value in enumerate(opts):
        opt = value[1][0]
        arg = value[1][1]
        opt = str(opt)
        arg = str(arg)
        if opt == '-l':
            limit = int(arg)
        elif opt == '-d':
            word = arg
        elif opt == '-g':
            google_dorking = True
        elif opt == '-s':
            start = int(arg)
        elif opt == '-v':
            virtual = "basic"
        elif opt == '-f':
            filename = arg
        elif opt == '-n':
            dnslookup = True
        elif opt == '-c':
            dnsbrute = True
        elif opt == '-h':
            shodan = True
        elif opt == '-e':
            dnsserver = arg
        elif opt == '-p':
            ports_scanning = True
        elif opt == '-t':
            dnstld = True
        elif opt == '-b':
            engines = set(arg.split(','))
            supportedengines = set([
                "baidu", "bing", "crtsh", "censys", "cymon", "bingapi",
                "dogpile", "google", "googleCSE", "virustotal", "threatcrowd",
                "googleplus", "google-profiles", 'google-certificates',
                "linkedin", "pgp", "twitter", "trello", "vhost", "yahoo",
                "netcraft", "hunter", "all"
            ])
            if set(engines).issubset(supportedengines):
                print("found supported engines")
                print(("[-] Starting harvesting process for domain: " + word +
                       "\n"))
                for engineitem in engines:
                    if engineitem == "google":
                        print("[-] Searching in Google:")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        for x in all_hosts:
                            try:
                                db = stash.stash_manager()
                                db.store(word, x, 'host', 'google')
                            except Exception as e:
                                print(e)

                    if engineitem == "netcraft":
                        print("[-] Searching in Netcraft:")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                    if engineitem == "google-certificates":
                        print(
                            "[-] Searching in Google Certificate transparency report.."
                        )
                        search = googlecertificates.search_googlecertificates(
                            word, limit, start)
                        search.process()
                        all_hosts = search.get_domains()
                        all_emails = []
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host',
                                     'google-certificates')

                    if engineitem == "threatcrowd":
                        print("[-] Searching in Threatcrowd:")
                        search = threatcrowd.search_threatcrowd(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'threatcrowd')

                    if engineitem == "virustotal":
                        print("[-] Searching in Virustotal:")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                    if engineitem == "crtsh":
                        print("[-] Searching in CRT.sh:")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                    if engineitem == "googleCSE":
                        print("[-] Searching in Google Custom Search:")
                        search = googleCSE.search_googleCSE(word, limit, start)
                        search.process()
                        search.store_results()
                        all_emails = search.get_emails()
                        db = stash.stash_manager()
                        all_hosts = search.get_hostnames()
                        db.store_all(word, all_hosts, 'email', 'googleCSE')
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'googleCSE')

                    elif engineitem == "bing" or engineitem == "bingapi":
                        print("[-] Searching in Bing:")
                        search = bingsearch.search_bing(word, limit, start)
                        if engineitem == "bingapi":
                            bingapi = "yes"
                        else:
                            bingapi = "no"
                        search.process(bingapi)
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "dogpile":
                        print("[-] Searching in Dogpilesearch..")
                        search = dogpilesearch.search_dogpile(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "pgp":
                        print("[-] Searching in PGP key server..")
                        search = pgpsearch.search_pgp(word)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'pgp')
                        db = stash.stash_manager()
                        db.store_all(word, all_emails, 'emails', 'pgp')

                    elif engineitem == "yahoo":
                        print("[-] Searching in Yahoo..")
                        search = yahoosearch.search_yahoo(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'yahoo')
                        db.store_all(word, all_emails, 'emails', 'yahoo')

                    elif engineitem == "baidu":
                        print("[-] Searching in Baidu..")
                        search = baidusearch.search_baidu(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'baidu')
                        db.store_all(word, all_emails, 'emails', 'baidu')

                    elif engineitem == "googleplus":
                        print("[-] Searching in Google+ ..")
                        search = googleplussearch.search_googleplus(
                            word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Google+:")
                        print("====================")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "twitter":
                        print("[-] Searching in Twitter ..")
                        search = twittersearch.search_twitter(word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Twitter:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "linkedin":
                        print("[-] Searching in Linkedin..")
                        search = linkedinsearch.search_linkedin(word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Linkedin:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "google-profiles":
                        print("[-] Searching in Google profiles..")
                        search = googlesearch.search_google(word, limit, start)
                        search.process_profiles()
                        people = search.get_profiles()
                        print("Users from Google profiles:")
                        print("---------------------------")
                        for users in people:
                            print(users)
                        sys.exit()

                    elif engineitem == "hunter":
                        print("[-] Searching in Hunter:")
                        from discovery import huntersearch
                        #import locally or won't work
                        search = huntersearch.search_hunter(word, limit, start)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "censys":
                        print("[-] Searching in Censys:")
                        from discovery import censys
                        #import locally or won't work
                        search = censys.search_censys(word)
                        search.process()
                        all_emails = []
                        all_ip = search.get_ipaddresses()
                        all_hosts = search.get_hostnames()
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'censys')
                        db.store_all(word, all_ip, 'ip', 'censys')

                    elif engineitem == "cymon":
                        print("[-] Searching in Cymon:")
                        from discovery import cymon
                        #import locally or won't work
                        search = cymon.search_cymon(word)
                        search.process()
                        all_emails = []
                        all_hosts = []
                        all_ip = search.get_ipaddresses()
                        db = stash.stash_manager()
                        db.store_all(word, all_ip, 'ip', 'cymon')

                    elif engineitem == "trello":
                        print("[-] Searching in Trello:")
                        from discovery import trello
                        #import locally or won't work
                        search = trello.search_trello(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_urls()
                        for x in all_hosts:
                            print(x)
                        sys.exit()

                    elif engineitem == "all":
                        print(("Full harvest on " + word))
                        all_emails = []
                        all_hosts = []

                        print("[-] Searching in Google..")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'google')
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'google')

                        print("[-] Searching in PGP Key server..")
                        search = pgpsearch.search_pgp(word)
                        search.process()
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'PGP')
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'PGP')

                        print("[-] Searching in Netcraft server..")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                        print("[-] Searching in ThreatCrowd server..")
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = search.get_hostnames()
                            all_hosts.extend(hosts)
                            all_emails = []
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host',
                                         'threatcrowd')
                        except Exception:
                            pass

                        print("[-] Searching in CRTSH server..")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                        print("[-] Searching in Virustotal server..")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                        print("[-] Searching in Bing..")
                        bingapi = "no"
                        search = bingsearch.search_bing(word, limit, start)
                        search.process(bingapi)
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'bing')
                        all_emails.extend(emails)
                        #Clean up email list, sort and uniq
                        all_emails = sorted(set(all_emails))

                        print("[-] Searching in Hunter:")
                        from discovery import huntersearch
                        #import locally
                        search = huntersearch.search_hunter(word, limit, start)
                        search.process()
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'hunter')
                        all_emails.extend(emails)
                        all_emails = sorted(set(all_emails))

                        print(
                            "[-] Searching in Google Certificate transparency report.."
                        )
                        search = googlecertificates.search_googlecertificates(
                            word, limit, start)
                        search.process()
                        domains = search.get_domains()
                        all_hosts.extend(domains)

                        print("[-] Searching in Cymon:")
                        from discovery import cymon
                        search = cymon.search_cymon(word)
                        search.process()
                        all_emails = []
                        all_ip = search.get_ipaddresses()
                        db = stash.stash_manager()
                        db.store_all(word, all_ip, 'ip', 'cymon')

                        print("[-] Searching in Censys:")
                        from discovery import censys
                        search = censys.search_censys(word)
                        search.process()
                        all_emails = []
                        all_ip = search.get_ipaddresses()
                        all_hosts = search.get_hostnames()
                        db = stash.stash_manager()
                        db.store_all(word, all_ip, 'ip', 'censys')
                        db.store_all(word, all_hosts, 'host', 'censys')

            else:
                usage()
                print(
                    "Invalid search engine, try with: baidu, bing, bingapi, crtsh, censys, cymon, dogpile, google, googleCSE, virustotal, netcraft, googleplus, google-profiles, linkedin, pgp, twitter, vhost, yahoo, hunter, all"
                )
                sys.exit()

    #Results############################################################
    print("\n\033[1;32;40mHarvesting results")
    if (len(all_ip) == 0):
        print("No IP addresses found")
    else:
        print("\033[1;33;40m \n[+] IP addresses found in search engines:")
        print("------------------------------------")
        for i in all_ip:
            print(i)
    print("\n\n[+] Emails found:")
    print("------------------")

    #Sanity check to see if all_emails and all_hosts is defined
    try:
        all_emails
    except NameError:
        print('No emails found as all_emails is not defined.')
        sys.exit()
    try:
        all_hosts
    except NameError:
        print('No hosts found as all_hosts is not defined.')
        sys.exit()

    if all_emails == []:
        print("No emails found")
    else:
        print(("\n".join(all_emails)))

    print("\033[1;33;40m \n[+] Hosts found in search engines:")
    print("------------------------------------")
    if all_hosts == [] or all_emails is None:
        print("No hosts found")
    else:
        total = len(all_hosts)
        print(("\nTotal hosts: " + str(total) + "\n"))
        all_hosts = sorted(set(all_hosts))
        print("\033[94m[-] Resolving hostnames IPs...\033[1;33;40m \n ")
        full_host = hostchecker.Checker(all_hosts)
        full = full_host.check()
        for host in full:
            ip = host.split(':')[1]
            print(host)
            if ip != "empty":
                if host_ip.count(ip.lower()):
                    pass
                else:
                    host_ip.append(ip.lower())

    #DNS Brute force####################################################
    dnsres = []
    if dnsbrute == True:
        print("\n\033[94m[-] Starting DNS brute force: \033[1;33;40m")
        a = dnssearch.dns_force(word, dnsserver, verbose=True)
        res = a.process()
        print("\n\033[94m[-] Hosts found after DNS brute force:")
        print("---------------------------------------")
        for y in res:
            print(y)
            dnsres.append(y.split(':')[0])
            if y not in full:
                full.append(y)
        db = stash.stash_manager()
        db.store_all(word, dnsres, 'host', 'dns_bruteforce')

    #Port Scanning #################################################
    if ports_scanning == True:
        print("\n\n\033[1;32;40m[-] Scanning ports (active):\n")
        for x in full:
            host = x.split(':')[1]
            domain = x.split(':')[0]
            if host != "empty":
                print(("- Scanning : " + host))
                ports = [80, 443, 22, 8080, 21]
                try:
                    scan = port_scanner.port_scan(host, ports)
                    openports = scan.process()
                    if len(openports) > 1:
                        print(("\t\033[91m Detected open ports: " +
                               ','.join(str(e)
                                        for e in openports) + "\033[1;32;40m"))
                    takeover_check = 'True'
                    if takeover_check == 'True':
                        if len(openports) > 0:
                            search_take = takeover.take_over(domain)
                            search_take.process()
                except Exception as e:
                    print(e)

    #DNS reverse lookup#################################################
    dnsrev = []
    if dnslookup == True:
        print("\n[+] Starting active queries:")
        analyzed_ranges = []
        for x in host_ip:
            print(x)
            ip = x.split(":")[0]
            range = ip.split(".")
            range[3] = "0/24"
            s = '.'
            range = s.join(range)
            if not analyzed_ranges.count(range):
                print(("\033[94m[-]Performing reverse lookup in : " + range +
                       "\033[1;33;40m"))
                a = dnssearch.dns_reverse(range, True)
                a.list()
                res = a.process()
                analyzed_ranges.append(range)
            else:
                continue
            for x in res:
                if x.count(word):
                    dnsrev.append(x)
                    if x not in full:
                        full.append(x)
        print("Hosts found after reverse lookup (in target domain):")
        print("---------------------------------")
        for xh in dnsrev:
            print(xh)

    #DNS TLD expansion###################################################
    dnstldres = []
    if dnstld == True:
        print("[-] Starting DNS TLD expansion:")
        a = dnssearch.dns_tld(word, dnsserver, verbose=True)
        res = a.process()
        print("\n[+] Hosts found after DNS TLD expansion:")
        print("------------------------------------------")
        for y in res:
            print(y)
            dnstldres.append(y)
            if y not in full:
                full.append(y)

    #Virtual hosts search###############################################
    if virtual == "basic":
        print("\n[+] Virtual hosts:")
        print("------------------")
        for l in host_ip:
            search = bingsearch.search_bing(l, limit, start)
            search.process_vhost()
            res = search.get_allhostnames()
            for x in res:
                x = re.sub(r'[[\<\/?]*[\w]*>]*', '', x)
                x = re.sub('<', '', x)
                x = re.sub('>', '', x)
                print((l + "\t" + x))
                vhost.append(l + ":" + x)
                full.append(l + ":" + x)
        vhost = sorted(set(vhost))
    else:
        pass
    #Shodan search####################################################
    shodanres = []
    shodanvisited = []
    if shodan == True:
        print("\n\n\033[1;32;40m[-] Shodan DB search (passive):\n")
        if full == []:
            print('No host to search, exiting.')
            sys.exit()

        for x in full:
            try:
                ip = x.split(":")[1]
                if not shodanvisited.count(ip):
                    print(("\tSearching for: " + ip))
                    a = shodansearch.search_shodan(ip)
                    shodanvisited.append(ip)
                    results = a.run()
                    #time.sleep(2)
                    for res in results['data']:
                        shodanres.append(
                            str("%s:%s - %s - %s - %s," %
                                (res['ip_str'], res['port'], res['os'],
                                 res['isp'])))
            except Exception as e:
                pass
        print("\n [+] Shodan results:")
        print("------------------")
        for x in shodanres:
            print(x)
    else:
        pass

    ###################################################################
    # Here i need to add explosion mode.
    # Tengo que sacar los TLD para hacer esto.
    recursion = None
    if recursion:
        start = 0
        for word in vhost:
            search = googlesearch.search_google(word, limit, start)
            search.process(google_dorking)
            emails = search.get_emails()
            hosts = search.get_hostnames()
            print(emails)
            print(hosts)
    else:
        pass

    #Reporting#######################################################
    if filename != "":
        try:
            print("[+] Saving files...")
            html = htmlExport.htmlExport(all_emails, full, vhost, dnsres,
                                         dnsrev, filename, word, shodanres,
                                         dnstldres)
            save = html.writehtml()
        except Exception as e:
            print(e)
            print("Error creating the file")
        try:
            filename = filename.split(".")[0] + ".xml"
            file = open(filename, 'w')
            file.write('<?xml version="1.0" encoding="UTF-8"?><theHarvester>')
            for x in all_emails:
                file.write('<email>' + x + '</email>')

            for x in full:
                x = x.split(":")
                if len(x) == 2:
                    file.write('<host>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</host>')
                else:
                    file.write('<host>' + x + '</host>')
            for x in vhost:
                x = x.split(":")
                if len(x) == 2:
                    file.write('<vhost>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</vhost>')
                else:
                    file.write('<vhost>' + x + '</vhost>')

            if shodanres != []:
                shodanalysis = []
                for x in shodanres:
                    res = x.split("SAPO")
                    # print " res[0] " + res[0] # ip/host
                    # print " res[1] " + res[1] # banner/info
                    # print " res[2] " + res[2] # port
                    file.write('<shodan>')
                    #page.h3(res[0])
                    file.write('<host>' + res[0] + '</host>')
                    #page.a("Port :" + res[2])
                    file.write('<port>' + res[2] + '</port>')
                    #page.pre(res[1])
                    file.write('<banner><!--' + res[1] + '--></banner>')

                    reg_server = re.compile('Server:.*')
                    temp = reg_server.findall(res[1])
                    if temp != []:
                        shodanalysis.append(res[0] + ":" + temp[0])

                    file.write('</shodan>')
                if shodanalysis != []:
                    shodanalysis = sorted(set(shodanalysis))
                    file.write('<servers>')
                    for x in shodanalysis:
                        #page.pre(x)
                        file.write('<server>' + x + '</server>')
                    file.write('</servers>')

            file.write('</theHarvester>')
            file.flush()
            file.close()
            print("Files saved!")
        except Exception as er:
            print(("Error saving XML file: " + str(er)))
        sys.exit()
Exemple #5
0
def start(argv):
    if len(sys.argv) < 4:
        Core.usage()
        sys.exit(1)
    try:
        opts, args = getopt.getopt(argv, "l:d:b:s:u:vf:nhcgpte:")
    except getopt.GetoptError:
        Core.usage()
        sys.exit(1)
    try:
        db = stash.stash_manager()
        db.do_init()
    except Exception as e:
        pass
    start = 0
    host_ip = []
    all_hosts = []
    all_emails = []
    filename = ""
    bingapi = "yes"
    dnslookup = False
    dnsbrute = False
    dnstld = False
    shodan = False
    vhost = []
    virtual = False
    ports_scanning = False
    takeover_check = False
    google_dorking = False
    limit = 500
    all_ip = []
    full = []
    trello_info = ([], False)
    dnsserver = ""
    for value in enumerate(opts):
        opt = value[1][0]
        arg = value[1][1]
        opt = str(opt)
        arg = str(arg)
        if opt == '-l':
            limit = int(arg)
        elif opt == '-d':
            word = arg
        elif opt == '-g':
            google_dorking = True
        elif opt == '-s':
            start = int(arg)
        elif opt == '-v':
            virtual = "basic"
        elif opt == '-f':
            filename = arg
        elif opt == '-n':
            dnslookup = True
        elif opt == '-c':
            dnsbrute = True
        elif opt == '-h':
            shodan = True
        elif opt == '-e':
            dnsserver = arg
        elif opt == '-p':
            ports_scanning = True
        elif opt == '-t':
            dnstld = True
        elif opt == '-b':
            engines = set(arg.split(','))
            supportedengines = set([
                'baidu', 'bing', 'bingapi', 'censys', 'crtsh', 'cymon',
                'dogpile', 'google', 'googleCSE', 'google-certificates',
                'google-profiles', 'hunter', 'linkedin', 'netcraft', 'pgp',
                'securityTrails', 'threatcrowd', 'trello', 'twitter', 'vhost',
                'virustotal', 'yahoo', 'all'
            ])
            if set(engines).issubset(supportedengines):
                print(("[-] Target domain: " + word + "\n"))
                for engineitem in engines:
                    if engineitem == "baidu":
                        print("[-] Searching in Baidu.")
                        try:
                            search = baidusearch.search_baidu(word, limit)
                            search.process()
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'baidu')
                            db.store_all(word, all_emails, 'email', 'baidu')
                        except Exception:
                            pass

                    elif engineitem == "bing" or engineitem == "bingapi":
                        print("[-] Searching in Bing.")
                        try:
                            search = bingsearch.search_bing(word, limit, start)
                            if engineitem == "bingapi":
                                bingapi = "yes"
                            else:
                                bingapi = "no"
                            search.process(bingapi)
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'email', 'bing')
                            db.store_all(word, all_hosts, 'host', 'bing')
                        except Exception as e:
                            if isinstance(e, MissingKey):  # Sanity check.
                                print(e)
                            else:
                                pass

                    elif engineitem == "censys":
                        print("[-] Searching in Censys.")
                        from discovery import censys
                        # Import locally or won't work
                        search = censys.search_censys(word, limit)
                        search.process()
                        all_ip = search.get_ipaddresses()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'censys')
                        db.store_all(word, all_ip, 'ip', 'censys')

                    elif engineitem == "crtsh":
                        print("[-] Searching in CRT.sh.")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                    elif engineitem == "cymon":
                        print("[-] Searching in Cymon.")
                        from discovery import cymon
                        # Import locally or won't work.
                        search = cymon.search_cymon(word)
                        search.process()
                        all_ip = search.get_ipaddresses()
                        db = stash.stash_manager()
                        db.store_all(word, all_ip, 'ip', 'cymon')

                    elif engineitem == "dogpile":
                        print("[-] Searching in Dogpilesearch.")
                        search = dogpilesearch.search_dogpile(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'email', 'dogpile')
                        db.store_all(word, all_hosts, 'host', 'dogpile')

                    elif engineitem == "google":
                        print("[-] Searching in Google.")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'google')
                        db.store_all(word, all_emails, 'email', 'google')

                    elif engineitem == "googleCSE":
                        print("[-] Searching in Google Custom Search.")
                        try:
                            search = googleCSE.search_googleCSE(
                                word, limit, start)
                            search.process()
                            search.store_results()
                            all_emails = filter(search.get_emails())
                            db = stash.stash_manager()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db.store_all(word, all_hosts, 'email', 'googleCSE')
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'googleCSE')
                        except Exception as e:
                            if isinstance(e, MissingKey):  # Sanity check.
                                print(e)
                            else:
                                pass

                    elif engineitem == "google-certificates":
                        print(
                            "[-] Searching in Google Certificate transparency report."
                        )
                        search = googlecertificates.search_googlecertificates(
                            word, limit, start)
                        search.process()
                        hosts = filter(search.get_domains())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host',
                                     'google-certificates')

                    elif engineitem == "google-profiles":
                        print("[-] Searching in Google profiles.")
                        search = googlesearch.search_google(word, limit, start)
                        search.process_profiles()
                        people = search.get_profiles()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'google-profile')
                        print("\nUsers from Google profiles:")
                        print("---------------------------")
                        for users in people:
                            print(users)
                        sys.exit()

                    elif engineitem == "hunter":
                        print("[-] Searching in Hunter.")
                        from discovery import huntersearch
                        # Import locally or won't work.
                        try:
                            search = huntersearch.search_hunter(
                                word, limit, start)
                            search.process()
                            emails = filter(search.get_emails())
                            all_emails.extend(emails)
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'hunter')
                            db.store_all(word, all_emails, 'email', 'hunter')
                        except Exception as e:
                            if isinstance(e, MissingKey):  # Sanity check.
                                print(e)
                            else:
                                pass

                    elif engineitem == "linkedin":
                        print("[-] Searching in Linkedin.")
                        search = linkedinsearch.search_linkedin(word, limit)
                        search.process()
                        people = search.get_people()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'linkedin')
                        print("\nUsers from Linkedin:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "netcraft":
                        print("[-] Searching in Netcraft.")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                    elif engineitem == "pgp":
                        print("[-] Searching in PGP key server.")
                        try:
                            search = pgpsearch.search_pgp(word)
                            search.process()
                            all_emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'pgp')
                            db.store_all(word, all_emails, 'email', 'pgp')
                        except Exception:
                            pass

                    elif engineitem == 'securityTrails':
                        print("[-] Searching in SecurityTrails.")
                        from discovery import securitytrailssearch
                        try:
                            search = securitytrailssearch.search_securitytrail(
                                word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, hosts, 'host', 'securityTrails')
                            ips = search.get_ips()
                            all_ip.extend(ips)
                            db = stash.stash_manager()
                            db.store_all(word, ips, 'ip', 'securityTrails')
                        except Exception as e:
                            if isinstance(e, MissingKey):  # Sanity check.
                                print(e)
                            else:
                                pass

                    elif engineitem == "threatcrowd":
                        print("[-] Searching in Threatcrowd.")
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host',
                                         'threatcrowd')
                        except Exception:
                            pass

                    elif engineitem == "trello":
                        print("[-] Searching in Trello.")
                        from discovery import trello
                        # Import locally or won't work.
                        search = trello.search_trello(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        info = search.get_urls()
                        hosts = filter(info[0])
                        trello_info = (info[1], True)
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, hosts, 'host', 'trello')
                        db.store_all(word, emails, 'email', 'trello')

                    elif engineitem == "twitter":
                        print("[-] Searching in Twitter.")
                        search = twittersearch.search_twitter(word, limit)
                        search.process()
                        people = search.get_people()
                        db = stash.stash_manager()
                        db.store_all(word, people, 'name', 'twitter')
                        print("\nUsers from Twitter:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    # vhost

                    elif engineitem == "virustotal":
                        print("[-] Searching in VirusTotal.")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                    elif engineitem == "yahoo":
                        print("[-] Searching in Yahoo.")
                        search = yahoosearch.search_yahoo(word, limit)
                        search.process()
                        hosts = search.get_hostnames()
                        emails = search.get_emails()
                        all_hosts.extend(filter(hosts))
                        all_emails.extend(filter(emails))
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'yahoo')
                        db.store_all(word, all_emails, 'email', 'yahoo')

                    elif engineitem == "all":
                        print(("Full harvest on " + word))
                        all_emails = []
                        all_hosts = []

                        # baidu

                        print("[-] Searching in Bing.")
                        bingapi = "no"
                        search = bingsearch.search_bing(word, limit, start)
                        search.process(bingapi)
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'bing')
                        all_emails.extend(emails)
                        all_emails = sorted(set(all_emails))
                        db.store_all(word, all_emails, 'email', 'bing')

                        print("[-] Searching in Censys.")
                        from discovery import censys
                        search = censys.search_censys(word, limit)
                        search.process()
                        ips = search.get_ipaddresses()
                        setips = set(ips)
                        uniqueips = list(setips)  # Remove duplicates.
                        all_ip.extend(uniqueips)
                        hosts = filter(search.get_hostnames())
                        sethosts = set(hosts)
                        uniquehosts = list(sethosts)  # Remove duplicates.
                        all_hosts.extend(uniquehosts)
                        db = stash.stash_manager()
                        db.store_all(word, uniquehosts, 'host', 'censys')
                        db.store_all(word, uniqueips, 'ip', 'censys')

                        print("[-] Searching in CRTSH server.")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'CRTsh')

                        # cymon

                        # dogpile

                        print("[-] Searching in Google.")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = filter(search.get_emails())
                        hosts = filter(search.get_hostnames())
                        all_emails.extend(emails)
                        db = stash.stash_manager()
                        db.store_all(word, all_emails, 'email', 'google')
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'google')

                        print(
                            "[-] Searching in Google Certificate transparency report."
                        )
                        search = googlecertificates.search_googlecertificates(
                            word, limit, start)
                        search.process()
                        domains = filter(search.get_domains())
                        all_hosts.extend(domains)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host',
                                     'google-certificates')

                        # googleplus

                        # google-certificates

                        # google-profiles

                        print("[-] Searching in Hunter.")
                        from discovery import huntersearch
                        # Import locally.
                        try:
                            search = huntersearch.search_hunter(
                                word, limit, start)
                            search.process()
                            emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, hosts, 'host', 'hunter')
                            all_emails.extend(emails)
                            all_emails = sorted(set(all_emails))
                            db.store_all(word, all_emails, 'email', 'hunter')
                        except Exception as e:
                            if isinstance(e, MissingKey):  # Sanity check.
                                print(e)
                            else:
                                pass

                        # linkedin

                        print("[-] Searching in Netcraft server.")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'netcraft')

                        print("[-] Searching in PGP key server.")
                        try:
                            search = pgpsearch.search_pgp(word)
                            search.process()
                            emails = filter(search.get_emails())
                            hosts = filter(search.get_hostnames())
                            sethosts = set(hosts)
                            uniquehosts = list(sethosts)  # Remove duplicates.
                            all_hosts.extend(uniquehosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host', 'PGP')
                            all_emails.extend(emails)
                            db = stash.stash_manager()
                            db.store_all(word, all_emails, 'email', 'PGP')
                        except Exception:
                            pass

                        print("[-] Searching in ThreatCrowd server.")
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = filter(search.get_hostnames())
                            all_hosts.extend(hosts)
                            db = stash.stash_manager()
                            db.store_all(word, all_hosts, 'host',
                                         'threatcrowd')
                        except Exception:
                            pass

                        print("[-] Searching in Trello.")
                        from discovery import trello
                        # Import locally or won't work.
                        search = trello.search_trello(word, limit)
                        search.process()
                        emails = filter(search.get_emails())
                        all_emails.extend(emails)
                        info = search.get_urls()
                        hosts = filter(info[0])
                        trello_info = (info[1], True)
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, hosts, 'host', 'trello')
                        db.store_all(word, emails, 'email', 'trello')

                        # twitter

                        # vhost

                        print("[-] Searching in VirusTotal server.")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = filter(search.get_hostnames())
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'virustotal')

                        # yahoo
            else:
                print("[!] Invalid source.\n\n")
                sys.exit(1)

    # Results
    print("\n\033[1;32;40mHarvesting results")
    if len(all_ip) == 0:
        print("No IP addresses found.")
    else:
        print("\033[1;33;40m \n[+] IP addresses found:")
        print("-----------------------")
        print("Total IP addresses: " + str(len(all_ip)) + "\n")
        for ip in sorted(list(set(all_ip))):
            print(ip)
    print("\n[+] Emails found:")
    print("-----------------")

    # Sanity check to see if all_emails and all_hosts are defined.
    try:
        all_emails
    except NameError:
        print('No emails found as all_emails is not defined.')
        sys.exit(1)
    try:
        all_hosts
    except NameError:
        print('No hosts found as all_hosts is not defined.')
        sys.exit(1)

    if all_emails == []:
        print("No emails found.")
    else:
        print("Total emails: " + str(len(all_emails)) + "\n")
        print(("\n".join(sorted(list(set(all_emails))))))

    print("\033[1;33;40m \n[+] Hosts found:")
    print("----------------")
    if all_hosts == []:
        print("No hosts found.")
    else:
        total = len(all_hosts)
        print(("Total hosts: " + str(total) + "\n"))
        all_hosts = sorted(list(set(all_hosts)))
        for host in all_hosts:
            print(host)
        print("\033[94m \n[-] Resolving hostnames to IPs.\033[1;33;40m")
        print("------------------------------")
        full_host = hostchecker.Checker(all_hosts)
        full = full_host.check()
        for host in full:
            ip = host.split(':')[1]
            print(host)
            if ip != "empty":
                if host_ip.count(ip.lower()):
                    pass
                else:
                    host_ip.append(ip.lower())

        db = stash.stash_manager()
        db.store_all(word, host_ip, 'ip', 'DNS-resolver')

    if trello_info[1] is True:  # Indicates user selected Trello.
        print("\033[1;33;40m \n[+] URLs found from Trello:")
        print("--------------------------")
        trello_urls = trello_info[0]
        if trello_urls == []:
            print('\nNo Trello URLs found.')
        else:
            total = len(trello_urls)
            print(("\nTotal URLs: " + str(total) + "\n"))
            for url in sorted(list(set(trello_urls))):
                print(url)

    # DNS Brute force
    dnsres = []
    if dnsbrute is True:
        print("\n\033[94m[-] Starting DNS brute force. \033[1;33;40m")
        a = dnssearch.dns_force(word, dnsserver, verbose=True)
        res = a.process()
        print("\n\033[94m[-] Hosts found after DNS brute force:")
        print("-------------------------------------")
        for y in res:
            print(y)
            dnsres.append(y.split(':')[0])
            if y not in full:
                full.append(y)
        db = stash.stash_manager()
        db.store_all(word, dnsres, 'host', 'dns_bruteforce')

    # Port Scanning
    if ports_scanning is True:
        print("\n\n\033[1;32;40m[-] Scanning ports (active).\n")
        for x in full:
            host = x.split(':')[1]
            domain = x.split(':')[0]
            if host != "empty":
                print(("- Scanning " + host))
                ports = [21, 22, 80, 443, 8080]
                try:
                    scan = port_scanner.PortScan(host, ports)
                    openports = scan.process()
                    if len(openports) > 1:
                        print(("\t\033[91m Detected open ports: " +
                               ','.join(str(e)
                                        for e in openports) + "\033[1;32;40m"))
                    takeover_check = 'True'
                    if takeover_check == 'True':
                        if len(openports) > 0:
                            search_take = takeover.take_over(domain)
                            search_take.process()
                except Exception as e:
                    print(e)

    # DNS reverse lookup
    dnsrev = []
    if dnslookup is True:
        print("\n[+] Starting active queries.")
        analyzed_ranges = []
        for x in host_ip:
            print(x)
            ip = x.split(":")[0]
            range = ip.split(".")
            range[3] = "0/24"
            s = '.'
            range = s.join(range)
            if not analyzed_ranges.count(range):
                print(("\033[94m[-] Performing reverse lookup in " + range +
                       "\033[1;33;40m"))
                a = dnssearch.dns_reverse(range, True)
                a.list()
                res = a.process()
                analyzed_ranges.append(range)
            else:
                continue
            for x in res:
                if x.count(word):
                    dnsrev.append(x)
                    if x not in full:
                        full.append(x)
        print("Hosts found after reverse lookup (in target domain):")
        print("----------------------------------------------------")
        for xh in dnsrev:
            print(xh)

    # DNS TLD expansion
    dnstldres = []
    if dnstld == True:
        print("[-] Starting DNS TLD expansion.")
        a = dnssearch.dns_tld(word, dnsserver, verbose=True)
        res = a.process()
        print("\n[+] Hosts found after DNS TLD expansion:")
        print("----------------------------------------")
        for y in res:
            print(y)
            dnstldres.append(y)
            if y not in full:
                full.append(y)

    # Virtual hosts search
    if virtual == "basic":
        print("\n[+] Virtual hosts:")
        print("------------------")
        for l in host_ip:
            search = bingsearch.search_bing(l, limit, start)
            search.process_vhost()
            res = search.get_allhostnames()
            for x in res:
                x = re.sub(r'[[\<\/?]*[\w]*>]*', '', x)
                x = re.sub('<', '', x)
                x = re.sub('>', '', x)
                print((l + "\t" + x))
                vhost.append(l + ":" + x)
                full.append(l + ":" + x)
        vhost = sorted(set(vhost))
    else:
        pass

    # Shodan search
    shodanres = []
    shodanvisited = []
    if shodan is True:
        print("\n\n\033[1;32;40m[-] Shodan DB search (passive):\n")
        if full == []:
            print('No host to search, exiting.')
            sys.exit(1)
        for x in full:
            try:
                ip = x.split(":")[1]
                if not shodanvisited.count(ip):
                    print(("\tSearching for: " + ip))
                    a = shodansearch.search_shodan(ip)
                    shodanvisited.append(ip)
                    results = a.run()
                    for res in results['data']:
                        shodanres.append(
                            str("%s:%s - %s - %s - %s," %
                                (res['ip_str'], res['port'], res['os'],
                                 res['isp'])))
            except Exception as e:
                pass
        print("\n [+] Shodan results:")
        print("-------------------")
        for x in shodanres:
            print(x)
    else:
        pass

    # Here we need to add explosion mode.
    # Tengo que sacar los TLD para hacer esto.
    recursion = None
    if recursion:
        start = 0
        for word in vhost:
            search = googlesearch.search_google(word, limit, start)
            search.process(google_dorking)
            emails = search.get_emails()
            hosts = search.get_hostnames()
            print(emails)
            print(hosts)
    else:
        pass

    # Reporting
    if filename != "":
        try:
            print("NEW REPORTING BEGINS.")
            db = stash.stash_manager()
            scanboarddata = db.getscanboarddata()
            latestscanresults = db.getlatestscanresults(word)
            previousscanresults = db.getlatestscanresults(word,
                                                          previousday=True)
            latestscanchartdata = db.latestscanchartdata(word)
            scanhistorydomain = db.getscanhistorydomain(word)
            pluginscanstatistics = db.getpluginscanstatistics()
            generator = statichtmlgenerator.htmlgenerator(word)
            HTMLcode = generator.beginhtml()
            HTMLcode += generator.generatelatestscanresults(latestscanresults)
            HTMLcode += generator.generatepreviousscanresults(
                previousscanresults)
            graph = reportgraph.graphgenerator(word)
            HTMLcode += graph.drawlatestscangraph(word, latestscanchartdata)
            HTMLcode += graph.drawscattergraphscanhistory(
                word, scanhistorydomain)
            HTMLcode += generator.generatepluginscanstatistics(
                pluginscanstatistics)
            HTMLcode += generator.generatedashboardcode(scanboarddata)
            HTMLcode += '<p><span style="color: #000000;">Report generated on ' + str(
                datetime.datetime.now()) + '</span></p>'
            HTMLcode += '''
            </body>
            </html>
            '''
            Html_file = open("report.html", "w")
            Html_file.write(HTMLcode)
            Html_file.close()
            print("NEW REPORTING FINISHED!")
            print("[+] Saving files.")
            html = htmlExport.htmlExport(all_emails, full, vhost, dnsres,
                                         dnsrev, filename, word, shodanres,
                                         dnstldres)
            save = html.writehtml()
        except Exception as e:
            print(e)
            print("Error creating the file.")
        try:
            filename = filename.split(".")[0] + ".xml"
            file = open(filename, 'w')
            file.write('<?xml version="1.0" encoding="UTF-8"?><theHarvester>')
            for x in all_emails:
                file.write('<email>' + x + '</email>')
            for x in full:
                x = x.split(":")
                if len(x) == 2:
                    file.write('<host>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</host>')
                else:
                    file.write('<host>' + x + '</host>')
            for x in vhost:
                x = x.split(":")
                if len(x) == 2:
                    file.write('<vhost>' + '<ip>' + x[1] + '</ip><hostname>' +
                               x[0] + '</hostname>' + '</vhost>')
                else:
                    file.write('<vhost>' + x + '</vhost>')
            if shodanres != []:
                shodanalysis = []
                for x in shodanres:
                    res = x.split("SAPO")
                    file.write('<shodan>')
                    file.write('<host>' + res[0] + '</host>')
                    file.write('<port>' + res[2] + '</port>')
                    file.write('<banner><!--' + res[1] + '--></banner>')
                    reg_server = re.compile('Server:.*')
                    temp = reg_server.findall(res[1])
                    if temp != []:
                        shodanalysis.append(res[0] + ":" + temp[0])
                    file.write('</shodan>')
                if shodanalysis != []:
                    shodanalysis = sorted(set(shodanalysis))
                    file.write('<servers>')
                    for x in shodanalysis:
                        file.write('<server>' + x + '</server>')
                    file.write('</servers>')

            file.write('</theHarvester>')
            file.flush()
            file.close()
            print("Files saved!")
        except Exception as er:
            print(("Error saving XML file: " + str(er)))
        sys.exit()
Exemple #6
0
def start(argv):

    if len(sys.argv) < 4:
        usage()
        sys.exit()
    try:
        opts, args = getopt.getopt(argv, "l:d:b:s:u:vf:nhcgpte:")
    except getopt.GetoptError:
        usage()
        sys.exit()
    try:
        db=stash.stash_manager()
        db.do_init()
    except Exception as e:
        pass
    start = 0
    host_ip = []
    filename = ""
    bingapi = "yes"
    dnslookup = False
    dnsbrute = False
    dnstld = False
    shodan = False
    vhost = []
    virtual = False
    ports_scanning = False
    takeover_check = False
    google_dorking = False
    limit = 500
    dnsserver = ""
    for value in enumerate(opts):
        opt = value[1][0]
        arg = value[1][1]
        opt = str(opt)
        arg = str(arg)
        if opt == '-l':
            limit = int(arg)
        elif opt == '-d':
            word = arg
        elif opt == '-g':
            google_dorking = True
        elif opt == '-s':
            start = int(arg)
        elif opt == '-v':
            virtual = "basic"
        elif opt == '-f':
            filename = arg
        elif opt == '-n':
            dnslookup = True
        elif opt == '-c':
            dnsbrute = True
        elif opt == '-h':
            shodan = True
        elif opt == '-e':
            dnsserver = arg
        elif opt == '-p':
            ports_scanning = True
        elif opt == '-t':
            dnstld = True
        elif opt == '-b':
            engines = set(arg.split(','))
            supportedengines = set(["baidu","bing","crtsh","bingapi","dogpile","google","googleCSE","virustotal","threatcrowd","googleplus","google-profiles",'google-certificates',"linkedin","pgp","twitter","vhost","yahoo","netcraft","hunter","all"])
            if set(engines).issubset(supportedengines):
                print("found supported engines")
                print(("[-] Starting harvesting process for domain: " + word +  "\n"))
                for engineitem in engines:
                    if engineitem == "google":
                        print("[-] Searching in Google:")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        for x in all_hosts:
                            try:
                                db=stash.stash_manager()
                                db.store(word,x,'host','google')
                            except Exception as e:
                                print(e)
                    
                    if engineitem == "netcraft":
                        print("[-] Searching in Netcraft:")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','netcraft')
                        
                    if engineitem == "google-certificates":
                        print ("[-] Searching in Google Certificate transparency report..")
       	                search = googlecertificates.search_googlecertificates(word, limit, start)
                        search.process()
                        all_hosts = search.get_domains()
                        all_emails = []
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','google-certificates')

                    if engineitem == "threatcrowd":
                        print("[-] Searching in Threatcrowd:")
                        search = threatcrowd.search_threatcrowd(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','threatcrowd')
                
                    if engineitem == "virustotal":
                        print("[-] Searching in Virustotal:")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','virustotal')
                

                    if engineitem == "crtsh":
                        print("[-] Searching in CRT.sh:")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        all_hosts = search.get_hostnames()
                        all_emails = []
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','CRTsh')

                    if engineitem == "googleCSE":
                        print("[-] Searching in Google Custom Search:")
                        search = googleCSE.search_googleCSE(word, limit, start)
                        search.process()
                        search.store_results()
                        all_emails = search.get_emails()
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'email','googleCSE')
                        all_hosts = search.get_hostnames()
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','googleCSE')

                    elif engineitem == "bing" or engineitem == "bingapi":
                        print("[-] Searching in Bing:")
                        search = bingsearch.search_bing(word, limit, start)
                        if engineitem == "bingapi":
                            bingapi = "yes"
                        else:
                            bingapi = "no"
                        search.process(bingapi)
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "dogpile":
                        print("[-] Searching in Dogpilesearch..")
                        search = dogpilesearch.search_dogpile(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "pgp":
                        print("[-] Searching in PGP key server..")
                        search = pgpsearch.search_pgp(word)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','pgp')
                        db=stash.stash_manager()
                        db.store_all(word,all_emails,'emails','pgp')

                    elif engineitem == "yahoo":
                        print("[-] Searching in Yahoo..")
                        search = yahoosearch.search_yahoo(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "baidu":
                        print("[-] Searching in Baidu..")
                        search = baidusearch.search_baidu(word, limit)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "googleplus":
                        print("[-] Searching in Google+ ..")
                        search = googleplussearch.search_googleplus(word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Google+:")
                        print("====================")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "twitter":
                        print("[-] Searching in Twitter ..")
                        search = twittersearch.search_twitter(word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Twitter:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "linkedin":
                        print("[-] Searching in Linkedin..")
                        search = linkedinsearch.search_linkedin(word, limit)
                        search.process()
                        people = search.get_people()
                        print("Users from Linkedin:")
                        print("-------------------")
                        for user in people:
                            print(user)
                        sys.exit()

                    elif engineitem == "google-profiles":
                        print("[-] Searching in Google profiles..")
                        search = googlesearch.search_google(word, limit, start)
                        search.process_profiles()
                        people = search.get_profiles()
                        print("Users from Google profiles:")
                        print("---------------------------")
                        for users in people:
                            print(users)
                        sys.exit()

                    elif engineitem == "hunter":
                        print("[-] Searching in Hunter:")
                        from discovery import huntersearch
                        #import locally or won't work
                        search = huntersearch.search_hunter(word, limit, start)
                        search.process()
                        all_emails = search.get_emails()
                        all_hosts = search.get_hostnames()

                    elif engineitem == "all":
                        print(("Full harvest on " + word))
                        all_emails = []
                        all_hosts = []
                    
                        print("[-] Searching in Google..")
                        search = googlesearch.search_google(word, limit, start)
                        search.process(google_dorking)
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_emails.extend(emails)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'email','google')
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','google')
                        
                        print("[-] Searching in PGP Key server..")
                        search = pgpsearch.search_pgp(word)
                        search.process()
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','PGP')
                        all_emails.extend(emails)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'email','PGP')
                        
                        print("[-] Searching in Netcraft server..")
                        search = netcraft.search_netcraft(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','netcraft')

                        print("[-] Searching in ThreatCrowd server..")
                        try:
                            search = threatcrowd.search_threatcrowd(word)
                            search.process()
                            hosts = search.get_hostnames()
                            all_hosts.extend(hosts)
                            all_emails = []
                            db=stash.stash_manager()
                            db.store_all(word,all_hosts,'host','threatcrowd')
                        except Exception: pass

                        """print("[-] Searching in CRTSH server..")
                        search = crtsh.search_crtsh(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','CRTsh')"""

                        print("[-] Searching in Virustotal server..")
                        search = virustotal.search_virustotal(word)
                        search.process()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','virustotal')

                        print("[-] Searching in Bing..")
                        bingapi = "no"
                        search = bingsearch.search_bing(word, limit, start)
                        search.process(bingapi)
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db=stash.stash_manager()
                        db.store_all(word,all_hosts,'host','bing')
                        all_emails.extend(emails)
                        #Clean up email list, sort and uniq
                        all_emails=sorted(set(all_emails))

                        print("[-] Searching in Hunter:")
                        from discovery import huntersearch
                        #import locally
                        search = huntersearch.search_hunter(word, limit, start)
                        search.process()
                        emails = search.get_emails()
                        hosts = search.get_hostnames()
                        all_hosts.extend(hosts)
                        db = stash.stash_manager()
                        db.store_all(word, all_hosts, 'host', 'hunter')
                        all_emails.extend(emails)
                        all_emails = sorted(set(all_emails))

                        print ("[-] Searching in Google Certificate transparency report..")
                        search = googlecertificates.search_googlecertificates(word, limit, start)
                        search.process()
                        domains = search.get_domains()
	                    all_hosts.extend(domains)




            else:
            #if engine not in ("baidu", "bing", "crtsh","bingapi","dogpile","google", "googleCSE","virustotal","threatcrowd", "googleplus", "google-profiles","linkedin", "pgp", "twitter", "vhost", "yahoo","netcraft","all"):
                usage()
                print("Invalid search engine, try with: baidu, bing, bingapi, crtsh, dogpile, google, googleCSE, virustotal, netcraft, googleplus, google-profiles, linkedin, pgp, twitter, vhost, yahoo, hunter, all")
                sys.exit()