Fork of TheNewBoston(Bucky) Website scanner.

#coding: utf-8;
#Credit: Creuilcreuil;

from tld import get_tld;
import urllib.request;
import argparse;
import io;
import os;

ROOT_DIR = 'Websites';

def create_dir(directory, quiet=False):
    if not os.path.exists( directory ):
        if not quiet:
            print( "Creating new directory, '{}'.".format( directory ) );

        os.makedirs( directory );

    else:
        if not quiet:
            print( "Directory allready exists, '{}'.".format( directory ) );

def write_file(path, data, quiet=False):
    if not quiet:
        print( "Writing '{}'.".format( path ) );

    with open( path, 'w' ) as file:
        file.write( data );

def get_domain_name(url, quiet=False):
    if not quiet:
        print( "Getting domain name,'{}'.".format( url ) );

    return get_tld( url );

def get_ip_address(url, quiet=False):
    if not quiet:
        print( "Getting ip address from '{}'.".format( url ) );

    process = os.popen( 'host {}'.format( url ) );
    result = str( process.read() );
    marker = result.find( 'has address' ) + 12;

    return result[marker:].splitlines()[0];

def get_nmap(options, ip, quiet=False):
    if not quiet:
        print( "Performing 'nmap' scan on {}".format( ip ) );

    process = os.popen( "nmap {0} {1}".format( options, ip ) );
    result = str( process.read() );

    return result;

def get_robots_txt(url, quiet=False):
    if not quiet:
        print( "Downloading 'robot.txt' from '{}'".format( url ) );

    if not url.endswith( '/' ):
        url += '/';

    request = urllib.request.urlopen( '{}robots.txt'.format( url ), data=None );
    data = io.TextIOWrapper( request, encoding='utf-8' );

    return data.read();

def get_whois(domain_name, quiet=False):
    if not quiet:
        print( "Getting 'whois' info from '{}'.".format( domain_name ) );

    process = os.popen( 'whois {}'.format( domain_name ) );
    result = str( process.read() );

    return result;

def gather_info(url, quiet=False):

    print( "Gathering info from '{}'.".format( url ) );

    domain_name = get_domain_name( url, quiet );
    ip_address = get_ip_address( domain_name, quiet );
    nmap = get_nmap( '-F', ip_address, quiet );
    robots_txt = get_robots_txt( url, quiet );
    whois = get_whois( domain_name, quiet );

    data = {
        'domain_name':domain_name, 'ip_address':ip_address, 'nmap':nmap,
        'robots_txt':robots_txt, 'whois':whois,
    };

    create_report( data, quiet );

def create_report( data, quiet ):
    project_dir = '{0}/{1}'.format( ROOT_DIR, data['domain_name'] );
    create_dir( project_dir, quiet );

    print( "Savign report in '{}'.".format( project_dir ) );

    for key, value in data.items():
        file = '{0}/{1}.txt'.format( project_dir, key );

        if not quiet:
            print( 'Savign {}'.format( file ) );

        write_file( file, value, quiet );


    print( "Done with '{}'.\n".format( data['domain_name'] ) );

def Main():
    create_dir( ROOT_DIR );

    parser = argparse.ArgumentParser();

    parser.add_argument('url_list', help='website to gather info.', type=str );
    parser.add_argument('-l', '--list', help='<url> is website list.', action='store_true' );
    parser.add_argument('-q', '--quiet', help='silent mode.', action='store_true' );

    args = parser.parse_args();

    if args.url_list and not args.list:
        gather_info( args.url, args.quiet );

    elif args.url_list and args.list:
        print( "Loading website list '{}'".format( args.url_list ) );

        with open( args.url_list, 'r' ) as file:
            data = file.read().split('\n')[:-1];

            for line in data:
                gather_info( line, args.quiet );

        print( "Done with website list '{}'.\n".format( args.url_list ) );

if __name__ == '__main__':
    Main();