访问刺探

Readme

脚本功能：

​ 在新建文本文档.txt中提取所有80和443能访问的链接，这能使你极快地信息搜集子域名后进行WEB存活测试（当然，你需要的不仅仅是关注80和443，在此脚本使用后仍需要对子域名的其他端口进行测试，这只是最快提取成功的方式）

脚本环境

• Python3
• 第三方库：requests、gevent

脚本

import requests
from gevent import socket, monkey; monkey.patch_all()
import gevent
from gevent.pool import Pool
from requests.packages.urllib3.exceptions import InsecureRequestWarning
requests.packages.urllib3.disable_warnings (InsecureRequestWarning)


pools = Pool(1000)

headers = {
    'Connection': 'close',
    'Pragma': 'no-cache',
    'Cache-Control': 'no-cache',
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.67 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
    'Accept-Encoding': 'gzip, deflate',
    'Accept-Language': 'zh-CN,zh;q=0.9',
}


urls = []
protocal_urls = []
filename = "新建文本文档.txt"
gevent_list = []
EXCEPTION = ""
EXCEPTION_URL = []
NOT_200 = ""

def handle(url):
    global EXCEPTION
    global NOT_200
    try:
        url = 'http://' + url
        res = requests.get(url=url, headers=headers)
        #print (res.text)
        if 200<= res.status_code <= 400 and len(res.text) > 200:
            print(res.status_code, '     ', url)
            urls.append(url.replace('http://', ''))
            protocal_urls.append(url)
        if 200<= res.status_code <= 400 and len(res.text) < 200:
            #print('[-] too short, len: ', len(res.text), '     ', url)
            urls.append(url.replace('http://', ''))
            protocal_urls.append(url)

        else:
            NOT_200 += (str (res.status_code) + '     ' + url)
            urls.append (url.replace ('http://', ''))
            protocal_urls.append (url)
    except Exception as e:
        EXCEPTION_URL.append(url.replace('http://',''))
        EXCEPTION += ('[--]' + '     ' + url + '   ' +str(e) + '\n')

def handle2(url):
    global EXCEPTION
    global NOT_200
    try:
        url = 'https://' + url
        res = requests.get(url=url, headers=headers, verify=False)
        if (url.replace('https://','')) not in urls:
            if 200<= res.status_code <= 400 and len (res.text) > 200:
                print (res.status_code, '     ', url)
                urls.append (url.replace ('https://', ''))
                protocal_urls.append (url)
            if 200<= res.status_code <= 400 and len (res.text) < 200:
                #print ('[-] too short, len: ', len (res.text), '     ', url)
                urls.append (url.replace ('https://', ''))
                protocal_urls.append (url)
            else:
                NOT_200 += (str (res.status_code) + '     ' + url + '\n')
                urls.append (url.replace ('http://', ''))
                protocal_urls.append (url)
    except Exception as e:
        if (url.replace('https://','')) not in EXCEPTION_URL:
            EXCEPTION += ('[--]' + '     ' + url + '   ' + str (e) + '\n')


f = open(filename, 'r')
lis = f.readlines()
filter = []
for j in lis:
    j = j.strip()
    if j not in filter:
        filter.append(j)
lis = filter
f.close()
print("[+] there are {} links.".format(len(lis)))

for i in lis:
    i = i.strip()
    print(i)
    g = pools.spawn(handle, i)
    gevent_list.append(g)
for g in gevent_list:
    g.join()

gevent_list = []
for i in lis:
    i = i.strip()
    g = pools.spawn(handle2, i)
    gevent_list.append(g)
for g in gevent_list:
    g.join()


#print(NOT_200)
#print(EXCEPTION)