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))</pre>
`
说明
常见的备份文件命名如下：
www.zip
www.rar
www.tar.gz
wwwroot.zip
wwwroot.rar
wwwroot.tar.gz
web.zip
web.rar
web.tar.gz
.svn
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~
多线程备份文件扫描
https://img.mrwu.red/wp-content/uploads/2021/03/da11c3d20d2641a39ccc.png
脚本
-- coding: utf-8 --
@Author: mrwu
@Date:   2022-03-07 09:43:19
@Last Modified by:   mrwu
@Last Modified time: 2023-02-08 17:23:53
from queue import Queue
from tqdm import tqdm
import requests
import re
import argparse
import threading
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"}
定义要扫的备份文件
inurl = {"www","wwwroot","web","备份","源码"}
hz = {".zip",".rar",".tar.gz",".7z",".tar",".bz2",".xz"}
urllist = []
def banner():
print('''  ____             _                       _____
|  _ \           | |                     / |
| | ) | __ _ | | ___ _ _ __ ___ | ( ___ __ _ _ __
| _ &lt; / |/ __| |/ / | | | '_ \/ __| \___ \ / __/ _ | ' \
| |) | (| | (|   &lt;| || | |) __ \  **) | (| ( | | | | |
|**/ _,|||\,| ./|/ |__/ **,|| ||
| |

||
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:
domain = url.replace("\n","").replace("http://","").replace("https://","")
for y in hz:
urllist.append(url.replace("\n","")+"/"+domain+y)
for x in inurl:
urllist.append(url.replace("\n","")+"/"+x+y)
return(urllist)

def run(url):
try:
res = requests.get(url, headers=header, stream=True, verify=False, timeout=4)
ctype = res.headers['Content-Type']
ctype = ctype.lower()
    if ctype.find('application'):
        res.close()
    else:
        res.close()
        tqdm.write(&quot;[!] 文件存在 类型：%s 地址：%s&quot;%(ctype,url))
except:
    save(url)

def burst():
while not txt.empty():
pbar.set_description("")
pbar.update(1)
run(txt.get())
if name == 'main':
banner()
parser = argparse.ArgumentParser()
parser.add_argument('-u','--url', default='url.txt',help=&quot;URL文件路径&quot;)
parser.add_argument('-t','--threads', default='60',help=&quot;进程数，不要超过60&quot;)
args = parser.parse_args()

txt = Queue()
for x in open_url(args.url):
    txt.put(x)

threads = []

pbar = tqdm(total=txt.qsize(), desc='开始扫描',colour='#00ff00', position=0, ncols=90)

for i in range(int(args.threads)):
    t = threading.Thread(target = burst)
    t.start()
    threads.append(t)

for t in threads:
    t.join()

tqdm.write(&quot;[ok] 全部任务已结束！&quot;)&lt;/pre&gt;

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关键词，修改代码17行中的 inurl 变量，在其中增加你需要的关键词


感觉用不到代理，所以就没写代理功能


扫描成功的结果是实时显示


用到的模块：Pool tqdm requests argparse 自行安装