[v0id_v0mit]

Proxy leecher, leeches proxies of a list of urls.
It extracts the ip:port from the page and stores it, and the sorts it.
It reads the urls from a file and stores the proxies in another, it also makes a list of the sites it found proxies on.


http://pastebin.com/G12CHaEB
http://darkpy.net/python/pypb.py

Code

'''
Created on 28. des. 2010

@author: v0mit
'''
import urllib, threading, re, sys, Queue, time

if len(sys.argv) < 2:
    sys.exit("Usage python pypb.py <proxylist.txt> [-t threads] [-l leechlist] [-s sort]")
    
version = 0001
    
        
def getorders():
    name = sys.argv[1]
    try:
        maxThreads = int(sys.argv[sys.argv.index("-t")+1])
    except ValueError: maxThreads = 40
    try:
        leechlist = sys.argv[sys.argv.index("-l")+1]
    except: leechlist = "sites.txt"
    try:
        if sys.argv.index("-s"): bSort = True
    except ValueError: bSort = False
    
    
    return [name, maxThreads, leechlist, bSort]


def printlogo():
    print("\t          ___            _ _   ")
    print("\t         / _ \          (_) |  ")
    print("\t __   __| | | |_ __ ___  _| |_ ")
    print("\t \ \ / /| | | | '_ ` _ \| | __|")
    print("\t  \ V / | |_| | | | | | | | |_ ")
    print("\t   \_/   \___/|_| |_| |_|_|\__|")
    print("\tversion:%s    [email protected]\n" % version)
    

def sort():
    proxylist = open(orders[0], "r")
    setList = set()
    nCounter = 0
    
    for aaa in proxylist:
        aaa = aaa.strip()
        setList.add(aaa)
        nCounter += 1
        
    proxylist.close()
    proxylist = open(orders[0], "wb")
    for bbb in setList:
        proxylist.write(bbb+"\n")
            
    proxylist.close()
          
    print("%s proxies in list, %s unique proxies in list." % (nCounter, len(setList)))

class scan_thread(threading.Thread):
    def run (self):
        while True:
            url = threadPool.get()
            try:
                get = urllib.urlopen(url)
            except IOError:
                threadPool.task_done()
                continue
            data = get.read()
            validProxies = re.findall('(?:[\d]{1,3})\.(?:[\d]{1,3})\.(?:[\d]{1,3})\.(?:[\d]{1,3})\:(?:[\d]{2,5})', data)
            print("[*] %s proxies found at %s" % (len(validProxies), url))
            for proxy in validProxies:
                proxylist.write(proxy+"\n")
                
            if len(validProxies) > 0:
                good_sites.write(url+"\n")
            threadPool.task_done()
                

orders = getorders()
printlogo()

try:
    proxylist = open(orders[0], "a")
except IOError:
    print("[!] Could not create/open %s" % orders[0])
    
try:
    sites = open(orders[2], "rb")
except IOError:
    print("[!] Could not open %s" % orders[2])
    sys.exit()
    
try:
    good_sites = open("good_sites.txt", "wb")
except IOError:
    print("[!] Could not create good_sites.txt")
    sys.exit()

threadPool = Queue.Queue(0)

for x in xrange(orders[1]):
    scan_thread().start()
    
while True:
    for url in sites:
        url = url.strip()
        if url.startswith("http://"):
            threadPool.put(url)
        else:
            threadPool.put("http://"+url)
    while True:
        if threadPool.empty():
            break
        time.sleep(1)
        
    threadPool.join()
    break

print("[*] Done leeching.")
proxylist.close()
good_sites.close()
if orders[3]:sort()

A list with some good working urls:
http://darkpy.net/python/good_sites.txt
http://pastebin.com/WSfUZyhk

[Arata Goru]

How do I use this python tool on Ubuntu?

Pls, guide me .. I am new to Ubuntu Linux.

Thank you