扫描web目录的Python小脚本

webscan.py:

import argparse
import requests
from concurrent.futures import ThreadPoolExecutor
from multiprocessing import cpu_count
from fake_useragent import UserAgent
from threading import Lock

def read_file():
""" 读取撞库文件 """
with open(file=args.scan_dict, mode='r', encoding='utf-8') as f:
return f.readlines()

def write_file(content):
""" 将撞库成功的url写入到文件中 """
lock = Lock()
lock.acquire()
with open(file=args.scan_output, mode='a', encoding='utf-8') as f:
f.write(content)
lock.release()

def send_msg(line):
""" 整理url并发送请求 """
# http://www.baidu.com/match_result.php

url = "{}{}".format(args.scan_site, line) if "://" in args.scan_site else "{}{}{}".format("http://", args.scan_site, line)
try:
    response = requests.get(url=url, timeout=60, allow_redirects=False, headers={"User-Agent": UserAgent().random})
    if response.status_code == 200:
        write_file('{}
'.format(response.url))
        print(response.url, response.status_code)
except Exception as e:
    print(e, url)

def run():
# 开启线程池，读取任务列表
# 任务列表：撞库文件
t = ThreadPoolExecutor(args.thread_num)
for i in read_file():
t.submit(send_msg, i)

if name == 'main':
parse = argparse.ArgumentParser()
parse.add_argument('--site', dest='scan_site', help='要扫描的服务器', type=str)
parse.add_argument('--dict', dest='scan_dict', help="撞库文件", default='webdict.txt', type=str)
parse.add_argument('--output', dest='scan_output', help="存储撞库成功的路径", default='./output.txt', type=str)
parse.add_argument('--thread', dest='thread_num', help='设置线程数量', default=cpu_count() * 5, type=int)
args = parse.parse_args()
run()

"""
D:dazhuPython.toos
ote>python "09 web目录扫描.py" --site www.7k7k.com
"""

webdict.txt:

网上有很多这样的字典，可以搜索下载。