网站备份文件批量扫描python脚本

单线程备份文件扫描

脚本

import requests
import re

# 使用方法：
#     在这个路径添加 D:\Desktop\url.txt  url.txt 的文件   在文件中添加带 http:// 或者 https:// 的域名，一行一个
#     将13和15行中的 D:\Desktop\url.txt 改为 url.txt 即可读取脚本目录下的 url.txt 文件内容

proxy = {"http": "127.0.0.1:8080"} #代理
## inurl 定义要扫的备份文件
inurl = {"/www.zip","/www.rar","/www.tar.gz","/wwwroot.zip","/wwwroot.rar","/wwwroot.tar.gz","/web.zip","/web.rar","/web.tar.gz","/.svn"}
hz = {".zip",".rar",".tar.gz"} # 指定备份文件后缀  后面自动生成为 xxx.com.zip 样式的格式

count = len(open(r'D:\Desktop\url.txt', 'r').readlines())
count = count * 13  # inurl + hz 的总和
with open(r"D:\Desktop\url.txt") as f:
    n = 0
    data = []
    nodata = []
    for line in f:
        line = line.replace("\n","").split()
        try:
            for x in line:
                for s in list(inurl):
                    url = x + s
                    n = n+1
                    html = requests.get(url,allow_redirects=False)
                    html.encoding = 'utf-8'
                    html = html.status_code
                    if html == 200 :
                        data.append(url)
                        print('进程：(%s/%s) ----- 状态：%s ----- 文件存在 ----- 目标：%s'%(n,count,html,url) )
                    else:
                        print('进程：(%s/%s) ----- 状态：%s ----- 不存在 ----- 目标：%s'%(n,count,html,url) )

                if x.startswith("https://"):
                    for index in hz:
                        url = x + '/' + x.replace("https://","") + index
                        n = n+1
                        html = requests.get(url,allow_redirects=False)
                        html.encoding = 'utf-8'
                        html = html.status_code
                        if html == 200 :
                            data.append(url)
                            print('进程：(%s/%s) ----- 状态：%s ----- 文件存在 ----- 目标：%s'%(n,count,html,url) )
                        else:
                            print('进程：(%s/%s) ----- 状态：%s ----- 不存在 ----- 目标：%s'%(n,count,html,url) )
                elif x.startswith("http://"):
                        for index in hz:
                            url = x + '/' + x.replace("http://","") + index
                            n = n+1
                            html = requests.get(url,allow_redirects=False)
                            html.encoding = 'utf-8'
                            html = html.status_code
                            if html == 200 :
                                data.append(url)
                                print('进程：(%s/%s) ----- 状态：%s ----- 文件存在 ----- 目标：%s'%(n,count,html,url) )
                            else:
                                print('进程：(%s/%s) ----- 状态：%s ----- 不存在 ----- 目标：%s'%(n,count,html,url) )
        except:
            nodata.append(url)
            print('进程：(%s/%s) ----- 状态：%s ----- 无法访问 ----- 目标：%s'%(count,n,html,url) )

    print('扫描完成')
    print('-----------成功的结果-----------')
    print("\n".join(str(i) for i in data))
    print('-----------无法访问的-----------')
    print("\n".join(str(i) for i in nodata))

说明

常见的备份文件命名如下：

本脚本的作用是扫描如上备份文件以及带域名的备份文件（www.xx.com/www.xx.com.zip等）是否存在，喜欢的可以收藏~

多进程备份文件扫描

脚本

# -*- coding: utf-8 -*-
# @Author: mrwu
# @Date:   2022-03-07 09:43:19
# @Last Modified by:   mrwu
# @Last Modified time: 2022-07-01 18:08:38

from multiprocessing import Pool
from tqdm import tqdm
import requests
import re
import argparse
requests.packages.urllib3.disable_warnings()  #关闭ssl控制台报错

header = {"User-Agent": "Mozilla/5.0 (iPhone; CPU iPhone OS 13_2_3 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Version/13.0.3 Mobile/15E148 Safari/604.1"}
## inurl 定义要扫的备份文件
inurl = {"/www.zip","/www.rar","/www.tar.gz","/www.gz","/wwwroot.zip","/wwwroot.rar","/wwwroot.tar.gz","/wwwroot.gz","/web.zip","/web.rar","/web.tar.gz","/web.gz","/七月修复weipan.zip","/weipan.zip","/weipan.rar","/weipan.tar.gz"}
hz = {".zip",".rar",".tar.gz"}

urllist = []

def banner():
    print('''  ____             _                       _____                 
 |  _ \           | |                     / ____|                
 | |_) | __ _  ___| | ___   _ _ __  ___  | (___   ___ __ _ _ __  
 |  _ < / _` |/ __| |/ / | | | '_ \/ __|  \___ \ / __/ _` | '_ \ 
 | |_) | (_| | (__|   <| |_| | |_) \__ \  ____) | (_| (_| | | | |
 |____/ \__,_|\___|_|\_\\__,_| .__/|___/ |_____/ \___\__,_|_| |_|
                             | |                                 
                             |_|                                 

 Author:MrWu           Blog:www.mrwu.red        
                                               ''')

def save(data):
    f = open(r'fail_url.txt', 'a',encoding='utf-8')
    f.write(data + '\n')
    f.close()

def open_url(url):
    with open(url) as f:
        for url in f:
            url = url.replace("\n","").split()
            for x in url:
                for index in hz:
                    if x.startswith("https://"):
                        url1 = x + '/' + x.replace("https://","") + index
                    if x.startswith("http://"):
                        url1 = x + '/' + x.replace("http://","") + index
                    urllist.append(url1)
                for s in list(inurl):
                    url = x + s
                    urllist.append(url)
    return(urllist)

def run(url):
    try:
        #代理
        # proxy = {"socks": "127.0.0.1:7890"} #代理
        # html = requests.get(url, headers=header,verify=False,timeout=(2,2), proxies=proxy)
        #代理
        html = requests.get(url, headers=header,verify=False,timeout=(2,2))
        html.encoding = 'utf-8'
        code = html.status_code
        html = html.headers['Content-Type']
        result = "application" in html 
        result2 = "application/json" in html
        if result == True and result2 == False:
            print('\033[1;31m[!] 目标：%s ----- 文件存在 ----- 状态码：%s\033[0m'%(url,code))
    except Exception as e:
        save(url)

if __name__ == '__main__':
    banner()

    parser = argparse.ArgumentParser()
    parser.add_argument('-u','--url', default='url.txt',help="URL文件路径")
    parser.add_argument('-t','--threads', default='20',help="进程数，不要超过60")
    args = parser.parse_args()

    urllist = open_url(args.url)
    po = Pool(int(args.threads)) #最高60
    #进度条显示
    pbar = tqdm(total=len(urllist))
    pbar.set_description('正在扫描')
    update = lambda *args: pbar.update()
    #进度条显示
    for url in urllist:
        po.apply_async(run,(url,), callback=update)
    po.close()
    po.join()

说明

• -u 参数指定要扫描的url字典文件路径，默认脚本文件目录下的 url.txt 文件，一行一个
• -t 参数指定扫描的进程数，默认20，不要超过60，进程太高可能导致扫描不准确
• URL.txt 文件中的URL地址一定得带协议头，如：https://www.baidu.com 否则会报错
• 无法访问的URL地址会自动存放到脚本目录下的 fail_url.txt 文件中
• 如果需要增加备份文件字典，修改代码16行中的 inurl 变量
• 感觉用不到代理，所以就没详细写代理功能，如果需要用到代理，取消58,59行注释，并注释61行，反之如果不需要代理，则取消61行注释，注释58,59行
• 扫描成功的结果是实时加红显示
• 用到的模块：Pool tqdm requests argparse 自行安装