PHP CURL模擬登錄抓取數據

1、CURL模擬登錄的方法

<?php
/**
 * Created by PhpStorm.
 * User: kungyu
 * Date: 2015/11/26
 * Time: 15:56
 */
function login_post($url, $cookie, $header){ //方法採用的的是GET請求,若是POST請求,增加一個傳入參數 $post
    $curl = curl_init();
    curl_setopt($curl,CURLOPT_URL,$url);
    curl_setopt($curl, CURLOPT_HTTPHEADER, $header);
    curl_setopt($curl, CURLOPT_HEADER, 0);
    curl_setopt($curl, CURLOPT_RETURNTRANSFER, true);
    curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie);
    /*curl_setopt($curl, CURLOPT_POST, 1);*/                                 //POST 請求需要開啓該處註釋
    curl_setopt($curl, CURLOPT_NOBODY, true);
    /* curl_setopt($curl, CURLOPT_POSTFIELDS, http_build_query($post));*/    //POST 請求需要開啓該處註釋
    $res = curl_exec($curl);
    curl_close($curl);
    return $res;
}

function get_content($url, $cookie,$post) {
$header = array (
    'Accept:text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
    "Cache-Control:max-age=0",
    /*"Accept-Encoding:gzip, deflate",*/
    "Accept-Language:zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3",
    "Connection:keep-alive",
    "Content-Type:application/x-www-form-urlencoded; charset=UTF-8",
    "Host:******",
    "Origin:******",
    "User-Agent:Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/43.0.2357.134 Safari/537.36",
    "x-insight:activate"
);
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_HTTPHEADER, $header);
    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie); //讀取cookie
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_NOBODY, false);
    curl_setopt($ch, CURLOPT_POSTFIELDS, http_build_query($post));
    $rs = curl_exec($ch); 
    curl_close($ch);
    return $rs;
}

2、登錄系統創建cookie文件

include("D:/reg/function.php");
$loginUrl = "**********";
$cookieFile = tempnam('D:/reg','cookie');
login_post($loginUrl,$cookieFile,$header);
file_put_contents('D:/reg/cookie_path.txt',$cookieFile);

3、抓取頁面數據

$dir = dirname(__FILE__);
$cookieFile = file_get_contents($dir."/cookie_path.txt");
$detail_url = "*******";
$search_arr = array(
            'param'=> 'data'
        );
$search_res = get_content($search_url, $cookieFile, $search_arr);

//剩下的就是數據的正則匹配根據自己想要的獲取數據。


發表評論
所有評論
還沒有人評論,想成為第一個評論的人麼? 請在上方評論欄輸入並且點擊發布.
相關文章