#!/usr/bin/env python from urlparse import urlparse import sys,getopt def parseme(i,o): for line in i: domain=urlparse(line)[1] if domain is not None: domainshort=domain[4:] '''could use rstrip here but weird results sometimes''' o.write("%s \n" % domain) if domain[:3] == "www": o.write("%s \n" % domainshort) o.close() def main(): infile = open(sys.argv[1],'r') outfile = open(sys.argv[2],'w') parseme(infile,outfile) if __name__ == "__main__": main()