php使用curl绕过CDN安全验证,用于采集需要Cookie验证的网站数据

<?php
//curl模拟提交,绕过安全检查验证
$url="http://www.xxx.com/others/getdata.php";
$post = array(
    'username' => '***',
    'password' => '***',
    'submit' => '现在登录'
);
//1.获取网站的cookie值
$cookie = getCookie($api, $post, 1);
//echo $cookie;
//2.携带cookie访问网址
$html=fetch_url($api,$cookie);
//3.检查json格式
$data=jsonReplaceValue($html);
$json = json_decode($data,1);
echo $json;
die;

/**
 * 实现登录并返回cookie值
 * @param $url
 * @param array $params
 * @param array $headers
 * @return bool|mixed|string
 */
function getCookie($url, $params = [], $headers = [])
{
	$useragent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.89 Safari/537.36';
    $timeout= 120;
	$httpInfo = array();
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_HEADER, 1);
    curl_setopt($ch, CURLOPT_HTTP_VERSION, CURL_HTTP_VERSION_1_1);
    curl_setopt($ch, CURLOPT_USERAGENT, $useragent);
    curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
    curl_setopt($ch, CURLOPT_TIMEOUT, $timeout);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

    curl_setopt($ch, CURLOPT_POST, true);
    curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($params));
    curl_setopt($ch, CURLOPT_URL, $url);

    $response = curl_exec($ch);
    if ($response === FALSE) {
        return false;
    }

    curl_close($ch);
    // 解析HTTP数据流
    list($header, $body) = explode("\r\n\r\n", $response);
	// 解析COOKIE
    preg_match_all("/set\-cookie:([^\r\n]*)/i", $header, $matches);
        //echo "<pre>";
	//var_dump($matches);
	//die;
	// 请求的时候headers带上cookie就可以了
	$cookie1 = explode(';', $matches[0][0])[0];
	$cookie1=str_replace("Set-Cookie: ","",$cookie1).";";
    $cookie2 = explode(';', $matches[0][1])[0];
	$cookie2=str_replace("Set-Cookie: ","",$cookie2);
    return $cookie1.$cookie2;
}
/**
 * 传入cookie开始访问请求
  * @param $url
 * @param $cookie
 * @return bool|string
 */
function fetch_url($url,$cookie) {
	$useragent = 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_8_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.89 Safari/537.36';
	$timeout= 120;
	$ch = curl_init($url);
	curl_setopt($ch, CURLOPT_FAILONERROR, true);
	curl_setopt($ch, CURLOPT_HEADER, 0);
	curl_setopt($ch,CURLOPT_COOKIE,$cookie);
	// 关闭https验证
	curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);
	curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
	curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true );
	curl_setopt($ch, CURLOPT_ENCODING, "" );
	curl_setopt($ch, CURLOPT_RETURNTRANSFER, true );
	curl_setopt($ch, CURLOPT_AUTOREFERER, true );
	curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout );
	curl_setopt($ch, CURLOPT_TIMEOUT, $timeout );
	curl_setopt($ch, CURLOPT_MAXREDIRS, 10 );
	curl_setopt($ch, CURLOPT_USERAGENT, $useragent);
	$content = curl_exec($ch);
	if(curl_errno($ch))
	{
		echo 'Error:' . curl_error($ch);
	}
	else
	{
		return $content;        
	}
	curl_close($ch);
}

//json中给值增加上双引号
function jsonReplaceValue($str) 
{	
  $str=preg_replace('/[\x00-\x1F\x80-\xFF]/', '', $str);
  if(preg_match('/":\w/', $str)){
    $str =  preg_replace('/"([^"]+)":\s*(\d+)/', '"\1": "\2"', $str);
  }
  return $str;
}

需要注意的一点:在解析COOKIE那里,需要根据实际获取到的$matches来分析,比如我上面有两个“Set-Cookie”,所以我取了2次,然后再合并

  • 0
    点赞
  • 4
    收藏
    觉得还不错? 一键收藏
  • 0
    评论

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值