【附工具链接】真香系列-JSFinder实用改造

github链接：https://github.com/Threezh1/JSFinder

python JSFinder.py -u http://www.mi.com
#这个命令会爬取 http://www.mi.com 这单个页面的所有的js链接，并在其中发现url和子域名

python JSFinder.py -u http://www.mi.com -d
#深入一层页面爬取JS，时间会消耗的更长,建议使用-ou 和 -os来指定保存URL和子域名的文件名python JSFinder.py -u http://www.mi.com -d -ou mi_url.txt -os mi_subdomain.txt

python JSFinder.py -f text.txt

python JSFinder.py -f text.txt -j

    thread_num = 0    info = '访问成功'    lock = threading.Lock()    if urls == None:      return None    find_url_all_num = len(urls)    content_url = ""    content_subdomain = ""    if self.args.verify !=0:      print("A total of Find " + str(len(urls)) + " URL:n")      print("-----------------------But further validation is needed-----------------!nnn")      domian_text = requests.get(domian,verify =False).text      print("The length of the page currently visited =>"+str(len(domian_text)))      result ={}      for url in urls:        thread_num += 1        self.therads_op(url, content_url, lock,thread_num,result)        if thread_num == 100:          time.sleep(1)      find_url_success_num = 0      for length,url_list in result.items():        print("-----------------------The return packet length is :{len}------------------------".format(len =length))        for url in url_list:          print(url+"n")          find_url_success_num += 1          content_url+=url+"n"

  def therads_op(self,url,content_url,lock,thread_num,result):    threading.Thread(target=self.request(url,content_url,lock,result),args=(url,content_url,lock,result,))    if lock.acquire():      thread_num -= 1    lock.release()

def request(self,url,content_url,lock,result):   headers = {      "User-Agent": "Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50",   }   try:      resp = requests.get(url,verify = False,timeout = 10,headers=headers)      if resp.status_code != 404 and lock.acquire():         content_url += url + "n"         if result.get(str(len(resp.text)), 0) == 0:            result[str(len(resp.text))] = []            result[str(len(resp.text))].append(url)         else:            result[str(len(resp.text))].append(url)         lock.release()
   except Exception as e:      pass   finally:      try:         lock.release()      except RuntimeError as e:         pass

if self.args.output_html !=None:   table_tr0 = ''   html = html_Template()   total_str = '共url: %s，访问成功：%s，失败 %s' % (find_url_all_num, find_url_success_num, find_url_all_num-find_url_success_num)   if self.args.verify !=0:      for length,url_list in result.items():         for url in url_list:            url_a = "<a href={url}>点击</a>".format(url=url)            table_td = html.TABLE_TMPL % dict(length=length, url=url, result=info,                                      ask_url=url_a, )            table_tr0 += table_td   else:      for url in urls:         url_a = "<a href={url}>点击</a>".format(url=url)         table_td = html.TABLE_TMPL % dict(length="无法获取", url=url, result=info,                                   ask_url=url_a, )         table_tr0 += table_td   output = html.HTML_TMPL % dict(domain=self.args.url,value=total_str, table_tr=table_tr0, )   # 生成html报告   filename = '{date}_{url}.html'.format(date=time.strftime('%Y%m%d%H%M%S'),url = self.args.output_html)   dir = str(os.getcwd())   filename = os.path.join(dir, filename)   with open(filename, 'wb') as f:      f.write(bytes(output, "utf-8"))

链接：https://pan.baidu.com/s/17WIa94fr5EAHgfo4UI6Eyw 提取码：qq0c 复制这段内容后打开百度网盘手机App，操作更方便哦--来自百度网盘超级会员V3的分享