php querylist 抓取需要cookie验证的接口数据

具体是某某品台不多说

上代码

主要是要注意不停地调试找到需要的cookie

具体URL打马赛克 host referer和Origin也是直接抄袭浏览器的即可

主要是通过

$jar = new CookieJar();来存储已经获取到的cookie然后代入下一个方法进行访问

然后 有的request的类型是json的 必须使用

postJson 方法

    /*---------------------------------社会****平台 403----------------------------------------------*/
    public function get_chinanpo_links($page=1,$number=10)
    {
        $url = "https://******.cn/****";
       $url0 = "https://******.cn/****";
       $url1= "https://******.cn/****";
       $url2 = "https://******.cn/****";
       $url3 = "https://******.cn/****";
        echo "<pre>";
        $jar = new CookieJar();

        //第一步 获取到get中返回的cookie   
       // Cache::set('jar', null);

        if (!Cache::get('jar')) {
            $ql = QueryList::get($url, [], ['cookies' => $jar]);
            $jar_128 = $jar;
            $ql = QueryList::post($url0, [], ['cookies' => $jar]);

            Cache::set('jar', $jar);
        } else {
            $jar = Cache::get('jar');
        }
        $cookieArr = $jar->toArray();
        print_r($cookieArr);

        $params1 = [
            'headers' => [
                'Accept' => 'application/json, text/plain, */*',
                'Accept-Encoding' => 'gzip, deflate, br',
                'Cookie' => $cookieArr[0]['Name'] . "=" . $cookieArr[0]['Value'] . "; " . $cookieArr[1]['Name'] . "=" . $cookieArr[1]['Value'],
                'Accept-Language' => 'zh-CN,zh;q=0.9,en;q=0.8',
                'Connection' => 'keep-alive',
                'Content-Length' => 0,
                'Host' => '******',
                'Origin' => '******',
                'Referer' => '******', //不能去掉
                'Sec-Fetch-Dest' => 'empty',
                'Sec-Fetch-Mode' => 'cors',
                'Sec-Fetch-Site' => 'same-origin',
                'User-Agent' => 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
            ]
        ];

        $params2 = [
            //'cookie'=>$jar,
            'headers' => [
                'Accept' => 'application/json, text/plain, */*',
                'Accept-Encoding' => 'gzip, deflate, br',
                'Accept-Language' => 'zh-CN,zh;q=0.9,en;q=0.8',
                'Connection' => 'keep-alive',
                'Content-Length' => 26,
                'Content-Type'=> 'application/json;charset=UTF-8',
                'Cookie' => $cookieArr[0]['Name'] . "=" . $cookieArr[0]['Value'] . "; " . $cookieArr[1]['Name'] . "=" . $cookieArr[1]['Value'],
                        'Host' => '******',
                'Origin' => '******',
                'Referer' => '******', //不能去掉
                'Sec-Fetch-Dest' => 'empty',
                'Sec-Fetch-Mode' => 'cors',
                'Sec-Fetch-Site' => 'same-origin',
                'User-Agent' => 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
            ]
        ];

        $params3 = [
            //'cookie'=>$jar,
            'headers' => [
                'Accept' => 'application/json, text/plain, */*',
                'Accept-Encoding' => 'gzip, deflate, br',
                'Accept-Language' => 'zh-CN,zh;q=0.9,en;q=0.8',
                'Connection' => 'keep-alive',
                'Content-Length' => 15,
                'Content-Type'=> 'application/json;charset=UTF-8',
                'Cookie' => $cookieArr[0]['Name'] . "=" . $cookieArr[0]['Value'] . "; " . $cookieArr[1]['Name'] . "=" . $cookieArr[1]['Value'],
                'Host' => '******',
                'Origin' => '******',
                'Referer' => '******', //不能去掉
                'Sec-Fetch-Dest' => 'empty',
                'Sec-Fetch-Mode' => 'cors',
                'Sec-Fetch-Site' => 'same-origin',
                'User-Agent' => 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'
            ]
        ];

        print_r($params2);

//        try {
//            $ql = QueryList::post($url1, [], $params1);
//        } catch (ClientException  $e) {
//            echo "<pre>";
//            echo $e->getRequest();
//            echo $e->getResponse();
//            exit();
//        }



        try {
            $ql = QueryList::postJson($url2, ['pageNo'=>$page,'pageSize'=>$number], $params2);
        } catch (ClientException  $e) {
            echo "<pre>";
            echo $e->getRequest();
            echo $e->getResponse();
            exit();
        }

//
//                try {
//            $ql = QueryList::post($url3, ['id'=>"000000"], $params3);
//        } catch (ClientException  $e) {
//            echo "<pre>";
//            echo $e->getRequest();
//            echo $e->getResponse();
//            exit();
//        }

        print_r(json_decode($ql->getHtml()));
        exit();


    }

php querylist 抓取需要cookie验证的接口数据

相关推荐