python3——url存活性探测脚本（asyncio+aiohttp）

之前跑2000多个url 用requests写的简单脚本跑了两三个小时，属实顶不住，用asyncio+aiohttp写了一个，代码写的可能不咋地，但能跑，出结果没啥问题

# -*- coding: UTF-8 -*-
import time
import asyncio
import sys
import os
import datetime
import aiohttp
import warnings
import concurrent

warnings.filterwarnings("ignore")

if os.path.exists('./scan_result') == 0:
    os.makedirs('./scan_result')

url_result_success = []
tasks = []


def save_result():
    global url_result_success
    print(url_result_success)
    nowTime = datetime.datetime.now().strftime('%Y-%m-%d-%H-%M-%S')
    nowTime = str(nowTime)
    filename = './scan_result/URL_alive_{}.txt'.format(nowTime)
    fn = open(filename, mode='w+')
    fn.write('本次扫描存活个数：' + str(len(url_result_success)) + '\n')
    fn.writelines(url_result_success)


async def check(url, semaphore):
    global url_result_success
    try:
        async with semaphore:
            async with aiohttp.ClientSession(connector=aiohttp.TCPConnector(limit=64, verify_ssl=False)) as session:
                async with session.get(url) as resp:
                    print(url + "    " + str(resp.status))
                    if resp.status == 200:
                        url_result_success.append(url+'\n')
                        return await resp.text()

    except (aiohttp.client_exceptions.ClientConnectorError, concurrent.futures._base.TimeoutError) as e:
        #print(e)
        pass



def run(url_text):
    f = open(url_text, 'r')
    url = f.readlines()
    f.close()
    length = len(url)
    print("本次扫描共探测" + str(length) + "个url的存活情况")
    for i in range(0, length):
        semaphore = asyncio.Semaphore(300)  # 限制并发量为300
        task = asyncio.ensure_future(check("https://"+url[i].strip(), semaphore))
        tasks.append(task)
    result = loop.run_until_complete(asyncio.gather(*tasks))
    #print(result)


if __name__ == '__main__':
    loop = asyncio.get_event_loop()
    run("url.txt")
    # loop.run_until_complete(asyncio.wait(tasks))
    save_result()