Question

这是程序的源代码，但是对我来说，输出看起来很有趣，但是它可以工作，所以我仍然对此感到满意。但是，如果我使用的线程不正确，那我就想知道以正确的方式工作。

import os
import time
import threading
import urllib.request


max_threads = 10


RED   = '\033[31m'
GREEN = '\033[32m'
ESC   = '\033[0m'


def check(proxy):
    proxy_support = urllib.request.ProxyHandler({'https':proxy})
    opener = urllib.request.build_opener(proxy_support)
    urllib.request.install_opener(opener)
    print(end='\r' + time.strftime('[%H:%M:%S]')+" ~ Trying => " +proxy)
    try:
        urllib.request.urlopen("https://www.google.com", timeout=5)
        time.sleep(1)
        print(end='\r'+time.strftime('[%H:%M:%S]')+" ~"+GREEN+" Good [!] "+ESC +proxy)
        time.sleep(1)        
        with open("CheckedProxies.txt", "a") as appe:
            appe.write(proxy.replace("\n","") + "\n")
    except:
        time.sleep(1)
        print(end='\r'+time.strftime('[%H:%M:%S]')+" ~"+RED+" Bad [!] "+ESC +proxy)
        time.sleep(1)
        pass




try:
    proxies = open("/home/zion/Desktop/proxies.txt", "r").readlines()
except:
    print("File Empty Exiting!")
    exit()

if proxies == "":
    print("File Empty, Enter Proxies In proxies.txt File")

newtxt = open("CheckedProxies.txt","w")
print("Loading "+ str(len(proxies)) +" Proxies From Text File[!]")
time.sleep(3)
for proxy in proxies:
    threading.Thread(target=check, args=(proxy,)).start()
    while threading.activeCount() >= max_threads:
        time.sleep(1)


os.exit()

这是我程序的输出。...

[02:28:02] ~ Trying => 1.0.135.34:8080
[02:28:02] ~ Trying => 1.10.236.214:8080
[02:28:02] ~ Trying => 103.122.255.18:8080
[02:28:02] ~ Trying => 101.231.104.82:80
[02:28:02] ~ Trying => 102.176.160.109:8080
[02:28:02] ~ Trying => 1.179.144.181:8080
[02:28:02] ~ Trying => 103.10.228.221:8080
[02:28:02] ~ Trying => 101.255.40.38:47638
[02:28:02] ~ Trying => 101.108.110.95:3128
[02:28:03] ~ Bad [!] 1.0.135.34:8080
[02:28:03] ~ Bad [!] 101.255.40.38:47638
[02:28:03] ~ Bad [!] 103.10.228.221:8080
[02:28:03] ~ Bad [!] 1.10.236.214:8080
[02:28:03] ~ Bad [!] 101.231.104.82:80
[02:28:05] ~ Trying => 103.215.200.125:8080
[02:28:05] ~ Trying => 101.108.102.231:8080

我认为它会更像这样

[02:28:02] ~ Trying => 127.0.0.1:8080
[02:28:03] ~ Bad [!] 127.0.0.1:80
[02:28:02] ~ Trying => 127.0.0.1:8080
[02:28:03] ~ Bad [!] 127.0.0.1:80
[02:28:02] ~ Trying => 127.0.0.1:47638
[02:28:03] ~ Bad [!] 127.0.0.1:80
[02:28:02] ~ Trying => 127.0.0.1:3128

Answer 1

我不知道为什么在使用多个线程时会期望同步执行。

为了使此代码更好：

使用日志记录而不是打印strftime
使用线程池而不是带有睡眠的while循环
使用请求而不是urllib
使用f字符串格式而不是串联
使用with打开文件以确保它们已正确关闭

import logging
from concurrent.futures.thread import ThreadPoolExecutor
from typing import Tuple

import requests


def is_proxy_ok(proxy: str) -> bool:
    try:
        logging.info(f"Trying {proxy}")
        proxies = {"https": proxy, "http": proxy}
        response = requests.get("https://www.google.com", proxies=proxies, timeout=5)
        response.raise_for_status()
        logging.info(f"OK {proxy}")
        return True
    except requests.RequestException:
        logging.info(f"Bad {proxy}")
        return False


def check_proxy(proxy: str) -> Tuple[bool, str]:
    return is_proxy_ok(proxy), proxy


if __name__ == "__main__":
    logging.basicConfig(format="%(asctime)-15s - %(message)s", level=logging.INFO)
    with open("/home/zion/Desktop/proxies.txt") as proxy_file:
        proxies = [line.strip() for line in proxy_file]
    print(f"Loading {len(proxies)} Proxies From Text File[!]")
    working_proxies = []
    with ThreadPoolExecutor(max_workers=25) as executor:
        for is_working, proxy in executor.map(check_proxy, proxies):
            if is_working:
                working_proxies.append(proxy)
    with open("working_proxies.txt", "w") as out_file:
        print("\n".join(working_proxies), file=out_file)

python3线程输出帮助。这是正确的输出吗？

1 个答案: