1.python编写web目录扫描工具

准备

报错大概率是缩进、缩进、缩进

• requests库
• 御剑字典
• sys
• fake_useragent

# 注意pip版本号，安装py3的
linux:
pip3  install requests 
cmd:
pip install requests  
pip install fake_useragent

记得将字典改成utf-8格式

# webscan.py v1.0
# 用法：python webscan.py url
import requests
import sys
import fake_useragent

headers = {'User-Agent':fake_useragent.UserAgent().random}
print(headers)
#输入要扫的域名或ip
url = sys.argv[1]
with open('php.txt','r') as f:
    for i in f:
        #去除换行符
        i = i.strip()
        a = url + i
        #捕获超时异常，然后直接无视，直接进入下一个循环
        try:
            res = requests.get(a,headers = headers,timeout = 0.5 )
            if res.status_code == 200:
            #字体颜色设置，百度一下你就知道，不解释
                print("\033[1;32;40m %s \033[0m" % (a+'  200'))
            if res.status_code == 403:
                print("\033[1;31;40m %s \033[0m" % (a+'  403'))
            if res.status_code == 302:
                print("\033[1;31;40m %s \033[0m" % (a+'  302'))
            else:
                continue
         except Exception as e:
            pass
f.close()

多进程版本

#用法： webscan.py http://xxxx.com
import requests
import sys
import time
from multiprocessing import Pool


def req(url):
        try:
            res = requests.get(url,timeout=0.5)
            if res.status_code == 200:
             #字体颜色设置，百度一下你就知道，不解释
                print(url+'  200')
            elif res.status_code == 403:
                print(url+'  403')
            elif res.status_code == 302:
                print(url+'  302')
            elif res.status_code == 404:
                print(url+'  404')   
        except Exception as e:
                pass


if __name__ == '__main__':
    url = sys.argv[1].rstrip('/')
    p = Pool(10)
    with open('./php.txt','r') as f:
        for i in f.readlines():
            s=''
            s=url+i.strip()
            #req(s) //单进程单线程
            
            p.apply_async(req,(s,))
        print("------------------start---------------")
        p.close()
        p.join()
        print("-------------------end----------------")

多线程版本

#用法 webscan.py http://x.x.x.x.com
import threading
import sys
import requests
import time

thread_max = threading.BoundedSemaphore(5)

def req(url):
    try:
        res = requests.get(url,timeout=0.5)
        if res.status_code == 200:
             #字体颜色设置，百度一下你就知道，不解释
            print(url+'  200')
        elif res.status_code == 403:
            print(url+'  403')
        elif res.status_code == 302:
            print(url+'  302')
        elif res.status_code == 404:
            print(url+'  404')
    except Exception as e:
        pass


if __name__ == '__main__':
    threads=[]
    #限制线程的最大数量为10
    url=sys.argv[1]
    print("----------------start-------------")
    start=time.time()
    f=open('./php.txt','r') 
    for i in f:
        newUrl=url+i.strip()
        thread_max.acquire()
        t = threading.Thread(target=req, args=(newUrl,))
        threads.append(t)
        t.start()
        thread_max.release()
    for t in threads:
        t.join()    
    f.close()
    end=time.time()
    print("----------------end---------------")
    print(end-start)

PS
造轮子而已，本质上没啥困难的，就是利用此工具学习了下多进程和多线程，仅此而已