python 自动扫描到文件 python 扫描目录

目标：用Python3写一款小型的web目录扫描工具

功能：1.扫描指定站点

　　　2.指定网站脚本类型来扫描

　　　3.可控线程

　　　4.可保存扫描结果

首先定义一个命令参数的函数

def parse_option():
    parser = argparse.ArgumentParser(description="The Argument of DirScan")
    parser.add_argument("-u","--url",dest="url",help="The Url to Scan")
    parser.add_argument("-e","--extensions",dest="extensions",help="Web Extensions")
    parser.add_argument("-t","--thread",dest="thread",default=10,type=int,help="The Thread to Scan")
    parser.add_argument("-r","--report",action="store_true",help="Save The Result of Scan")
    args = parser.parse_args()
    return args

定义了4个参数，-u用来指定扫描的url，-e用来指定网站类型，-t用来指定线程数，默认为10，-r为保存扫描结果

参数的值传入变量args，然后返回

然后定义一个开始的函数，对url进行处理和启用多线程

def start(url, ext, count):
    queue = Queue() #生成一个队列

    print('\033[34;1m   Status   Url Path\033[0m')

    global url_r #设置为全局变量

    #对传入的url进行处理
    if url.endswith("/"):
        url = url.rstrip("/")
    #对url进行处理方便写入结果
    if url[4] == 's':
        url_r = url.lstrip("https://")
    if url[4] == ':':
        url_r = url.lstrip("http://")

    #打开字典，并和url进行拼接
    f = open('%s.txt' %ext,'r')
    for i in f:
        queue.put(url + i.rstrip('\n'))

    threads = []
    thread_count = count

    for i in range(thread_count):
        threads.append(Dirscan(queue)) #调用多线程
    for t in threads:
        t.start() #开启多线程
    for t in threads:
        t.join()  #等待

 这里用类方法来进行多线程的调用

class Dirscan(threading.Thread):
    def __init__(self,queue):
        threading.Thread.__init__(self)
        self.queue = queue

    def run(self):
        while not self.queue.empty():
            url_path = self.queue.get() #从队列里获取url

            #随机user-agents
            u = open("user-agents.txt", "r")
            headers_list = []
            random_headers = {}
            for i in u:
                headers_list.append(i.strip())
            random_headers["user-agents"] = random.choice(headers_list)
            headers = random_headers

            try:
                r = requests.get(url=url_path, headers=headers, timeout=6,allow_redirects=False)
                status_code = r.status_code
                if status_code == 200:
                    print("\033[32;1m[+]   [%s]    %s\033[0m"%(status_code,url_path))
                    if cmd_args.report: #如果有传入-r参数，则执行write_report()函数来写扫描结果
                        write_report(url_path)
                        return url_path
            except Exception as e:
                print("\033[41;1m%s\033[0m"%e)

然后是写扫描结果的函数

def write_report(url):
    with open("%s.html"%url_r, "a") as r:
        r.write('<a href="'+url+'" target="_blank">'+url+'</a><br>')
        r.close()

最后是程序的入口

if __name__ == '__main__':
    cmd_args = parse_option() #把parse_option()返回的args赋给变量cmd_args
    url = cmd_args.url #把args中的url传给变量url
    extension = cmd_args.extensions #把args中的extensions传给变量extension
    thread = cmd_args.thread #把args中的thread传给变量thread
    start(url,extension,thread) #把三个参数传入start()函数

以html格式保存扫描结果，也方便直接打开扫描结果

最后的完整代码

# -*- coding:utf-8 -*-
__author__ = "MuT6 Sch01aR"

import requests
import argparse
import threading
from queue import Queue
import random

class Dirscan(threading.Thread):
    def __init__(self,queue):
        threading.Thread.__init__(self)
        self.queue = queue

    def run(self):
        while not self.queue.empty():
            url_path = self.queue.get()
            u = open("user-agents.txt", "r")
            headers_list = []
            random_headers = {}
            for i in u:
                headers_list.append(i.strip())
            random_headers["user-agents"] = random.choice(headers_list)
            headers = random_headers
            try:
                r = requests.get(url=url_path, headers=headers, timeout=6,allow_redirects=False)
                status_code = r.status_code
                if status_code == 200:
                    print("\033[32;1m[+]   [%s]    %s\033[0m"%(status_code,url_path))
                    if cmd_args.report:
                        write_report(url_path)
                        return url_path
            except Exception as e:
                print("\033[41;1m%s\033[0m"%e)

def write_report(url):
    with open("%s.html"%url_r, "a") as r:
        r.write('<a href="'+url+'" target="_blank">'+url+'</a><br>')
        r.close()


def start(url, ext, count):
    queue = Queue()

    print('\033[34;1m   Status   Url Path\033[0m')

    global url_r
    if url.endswith("/"):
        url = url.rstrip("/")
    if url[4] == 's':
        url_r = url.lstrip("https://")
    if url[4] == ':':
        url_r = url.lstrip("http://")

    f = open('%s.txt' %ext,'r')
    for i in f:
        queue.put(url + i.rstrip('\n'))

    threads = []
    thread_count = count

    for i in range(thread_count):
        threads.append(Dirscan(queue))
    for t in threads:
        t.start()
    for t in threads:
        t.join()

def parse_option():
    parser = argparse.ArgumentParser(description="The Argument of DirScan")
    parser.add_argument("-u","--url",dest="url",help="The Url to Scan")
    parser.add_argument("-e","--extensions",dest="extensions",help="Web Extensions")
    parser.add_argument("-t","--thread",dest="thread",default=10,type=int,help="The Thread to Scan")
    parser.add_argument("-r","--report",action="store_true",help="Save The Result of Scan")
    args = parser.parse_args()
    return args

if __name__ == '__main__':
    cmd_args = parse_option()
    url = cmd_args.url
    extension = cmd_args.extensions
    thread = cmd_args.thread
    start(url,extension,thread)