Python大法之告彆指令碼小子—資訊資產收集類指令碼編寫

1：網頁中發現關鍵字
2：特定檔案的MD5（主要是靜態檔案、不一定要是MD5）
3：指定URL的關鍵字
4：指定URL的TAG樣式

#-*- coding: UTF-8 -*-
import requests
import json
 
def what_cms(url):
        essay-headers = {
                ‘Connection’: ‘keep-alive’,
                ‘Pragma’: ‘no-cache’,
                ‘Cache-Control’: ‘no-cache’,
                ‘Upgrade-Insecure-Requests’: ‘1’,
         ‘User-Agent’: ‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36’,
  

‘Accept’: ‘text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8’,
                ‘DNT’: ‘1’,
                ‘Accept-Encoding’: ‘gzip, deflate’,
                ‘Accept-Language’: ‘zh-CN,zh;q=0.9,en;q=0.8’
                    }
        post={
                ‘hash’:’0eca8914342fc63f5a2ef5246b7a3b14_7289fd8cf7f420f594ac165e475f1479′,
                ‘url’:url,
        }
r=requests.post(url=’http://whatweb.bugscaner.com/what/’, 

data=post, essay-headers=essay-headers)
        dic=json.loads(r.text)
                 if dic[‘cms’]==”:
                print ‘Sorry,Unidentified……..’
        else:
                print ‘CMS:’ + dic[‘cms’]
if __name__ == ‘__main__’:
             url=raw_input(‘PLEASE INPUT YOUR TARGET:’)
             what_cms(url)

範例：連結||||關鍵字||||CMS別稱
/data/admin/allowurl.txt||||dedecms||||DedeCMS(織夢)
/data/index.html||||dedecms||||DedeCMS(織夢)
/data/js/index.html||||dedecms||||DedeCMS(織夢)
/data/mytag/index.html||||dedecms||||DedeCMS(織夢)
/data/sessions/index.html||||dedecms||||DedeCMS(織夢)
/data/textdata/index.html||||dedecms||||DedeCMS(織夢)
/dede/action/css_body.css||||dedecms||||DedeCMS(織夢)
/dede/css_body.css||||dedecms||||DedeCMS(織夢)
/dede/templets/article_coonepage_rule.htm||||dedecms||||DedeCMS(織夢)
/include/alert.htm||||dedecms||||DedeCMS(織夢)
/member/images/base.css||||dedecms||||DedeCMS(織夢)
/member/js/box.js||||dedecms||||DedeCMS(織夢)
/php/modpage/readme.txt||||dedecms||||DedeCMS(織夢)
/plus/sitemap.html||||dedecms||||DedeCMS(織夢)
/setup/license.html||||dedecms||||DedeCMS(織夢)
/special/index.html||||dedecms||||DedeCMS(織夢)
/templets/default/style/dedecms.css||||dedecms||||DedeCMS(織夢)
/company/template/default/search_list.htm||||dedecms||||DedeCMS(織夢)

#-*- coding: UTF-8 -*-
import os
import threading
import urllib2
 
identification = False
g_index = 0
lock = threading.Lock()
 
def list_file(dir):
    files = os.listdir(dir)
    return  files
 
def request_url(url=”, data=None, essay-header={}):
    page_content = ”
    request = urllib2.Request(url, data, essay-header)
 
try:
        response = urllib2.urlopen(request)
        page_content = response.read()
    except Exception, e:
        pass
 
    return page_content
 
def whatweb(target):
    global identification
    global g_index
    global cms
 
while True:
        if identification:
            break
 
        if g_index > len(cms)-1:
            break
 
        lock.acquire()
        eachline = cms[g_index]
        g_index = g_index + 1
        lock.release()
 
        if len(eachline.strip())==0 or eachline.startswith(‘#’):
            pass
        else:
            url, pattern, cmsname = eachline.split(‘||||’)
            html = request_url(target+url)
            rate = float(g_index)/float(len(cms))
            ratenum = int(100*rate)
 
if pattern.upper() in html.upper():
                identification = True
         print ” CMS：%s，Matched URL：%s” % (cmsname.strip(‘\n’).strip(‘\r’), url)
                break
    return
 
 if __name__ == ‘__main__’:
    print ”’
          __        ___           _    ____ __  __ ____ 
          \ \      / / |__   __ _| |_ / ___|  \/  / ___|
           \ \ /\ / /| ‘_ \ / _` | __| |   | |\/| \___ \
            \ V  V / | | | | (_| | |_| |___| |  | |___) |
             \_/\_/  |_| |_|\__,_|\__|\____|_|  |_|____/
    ”’
threadnum = int(raw_input(‘ Please input your threadnum:’))
target_url = raw_input(‘ Please input your target:’)
 
f = open(‘./cms.txt’)
cms = f.readlines()
threads = []
 
if target_url.endswith(‘/’):
target_url = target_url[:-1]
 
iftarget_url.startswith(‘http://’)or target_url.startswith(‘https://’):
pass
else:
target_url = ‘http://’ + target_url
 
for i in range(threadnum):
t = threading.Thread(target=whatweb, args=(target_url,))
        threads.append(t)
 
print ‘ The number of threads is %d’ % threadnum
print ‘Matching…….’
for t in threads:
t.start()
 
for t in threads:
t.join()
 
print ” All threads exit”