ast lookup of

lookup.py

import os.path
import os
import subprocess
import sys
import logging
import multiprocessing
from multiprocessing import Pool
import time
import socket

# alexa domains are at http://s3.amazonaws.com/alexa-static/top-1m.csv.zip

PROCESS_PROCESSES = 500

def lookup(name):
    try:
        print "%s,%s" % (name, socket.gethostbyname(name))
    except:
        pass

pool = Pool(PROCESS_PROCESSES)

if __name__ == '__main__':

    results = []
    for line in open(sys.argv[1]):
        domain = line.rstrip().split(",")[1]
        results.append(pool.apply_async(lookup, [domain,]))
    for res in results:
        while 1:
            sys.stdout.flush()
            try:
                res.get(10)
                break
            except multiprocessing.TimeoutError:
                pass