python - zip 密码破解器中的多线程

Question

我正在学习如何使用字典攻击来破解 zip 文件。这是代码:

import zipfile
from threading import Thread

def extractFile(zFile, password):
    try:
        zFile.extractall(pwd=password)
        print '[+] Found password ' + password + '\n'
    except:
        pass

def main():
    zFile = zipfile.ZipFile('evil.zip')
    passFile = open('dictionary.txt')
    for line in passFile.readlines():
        password = line.strip('\n')
        extractFile(zFile, password)

if __name__ == '__main__':
    main()

我在上面使用线程

import zipfile
from threading import Thread

def extractFile(zFile, password):
    try:
        zFile.extractall(pwd=password)
        print '[+] Found password ' + password + '\n'
    except:
        pass

def main():
    zFile = zipfile.ZipFile('evil.zip')
    passFile = open('dictionary.txt')
    for line in passFile.readlines():
        password = line.strip('\n')
        t = Thread(target=extractFile, args=(zFile, password))
        t.start()

if __name__ == '__main__':
    main()

但是，当我对两个程序进行计时时，完成第一个程序需要 90 秒，但完成第二个程序需要近 300 秒。该词典包含 459026 个条目。我很困惑为什么会发生这种情况。我还尝试将线程限制为 10,20 等。但循环在每个实例上的执行速度仍然更快。有人能解释一下为什么会这样吗？还有是否有机会改进该程序。

编辑我尝试按照 Ray 的建议进行切片，如下所示:

import zipfile
from threading import Thread

def chunks(l, n):
    """Yield successive n-sized chunks from l."""
    for i in xrange(0, len(l), n):
        yield l[i:i+n]

def extractFile(zFile, passwords):
    for password in passwords:
        try:
            zFile.extractall(pwd=password)
            print '[+] Found password ' + password + '\n'
            sys.exit(0)
        except:
            continue

def main():
    zFile = zipfile.ZipFile('evil.zip')
    with open('dictionary.txt', 'rb') as pass_file:
        passwords = [i.strip() for i in pass_file]
    passes = list(chunks(passwords, 10))
    for pas in passes:
        t = Thread(target=extractFile, args=(zFile, pas))
        t.start()

if __name__ == '__main__':
    main()

仍然需要 3-4 分钟

Answer 1

这对于多处理不能正常工作的一个原因；您必须在每个子进程中打开 zip 文件，否则您可能会因共享文件句柄而受到伤害。然后仅创建少量(例如 2 * 核心数)子进程，并让单个子进程测试多个密码。

因此我们得到:

import zipfile
from multiprocessing import Process


def extract_file(passwords):
    with zipfile.ZipFile('evil.zip') as zipf:
        for password in passwords:
            try:
                zipf.extractall(pwd=password)
                print('[+] Found password {}\n'.format(password))
            except Exception as e:
                pass


def main():
    with open('dictionary.txt', 'rb') as pass_file:
        passwords = [i.strip() for i in pass_file]

    N_PROC = 8
    for i in range(N_PROC):
        p = Process(target=extract_file, args=[passwords[i::N_PROC]])
        p.start()


if __name__ == '__main__':
    main()