I need to extract all the urls from an ip list, i wrote this python script, but i have issue extracting the same ip multiple times (more threads are created with the same ip). Could anyone Improve on my solution using multithreading ?
Sorry for my english Thanks all
import urllib2, os, re, sys, os, time, httplib, thread, argparse, random
try:
ListaIP = open(sys.argv[1], "r").readlines()
except(IOError):
print "Error: Check your IP list path\n"
sys.exit(1)
def getIP():
if len(ListaIP) != 0:
value = random.sample(ListaIP, 1)
ListaIP.remove(value[0])
return value
else:
print "\nListaIPs sa terminat\n"
sys.exit(1)
def extractURL(ip):
print ip + '\n'
page = urllib2.urlopen('http://sameip.org/ip/' + ip)
html = page.read()
links = re.findall(r'href=[\'"]?([^\'" >]+)', html)
outfile = open('2.log', 'a')
outfile.write("\n".join(links))
outfile.close()
def start():
while True:
if len(ListaIP) != 0:
test = getIP()
IP = ''.join(test).replace('\n', '')
extractURL(IP)
else:
break
for x in range(0, 10):
thread.start_new_thread( start, () )
while 1:
pass
osonce; no need to import it twice.