php curl抓取页面及来路

作者：知乎用户
链接：https://www.zhihu.com/question/38960915/answer/79147687
来源：知乎
著作权归作者所有。商业转载请联系作者获得授权，非商业转载请注明出处。

<?php

    $url = "https://www.zhihu.com/";

    $ch = curl_init();
    // 设置浏览器的特定header
    curl_setopt($ch, CURLOPT_HTTPHEADER, array(
        "Host: www.zhihu.com",
        "Connection: keep-alive",
        "Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8",
        "Upgrade-Insecure-Requests: 1",
        "DNT:1",
        "Accept-Language: zh-CN,zh;q=0.8,en-GB;q=0.6,en;q=0.4,en-US;q=0.2",
        'Cookie:_za=4540d427-eee1-435a-a533-66ecd8676d7d; __utma=51854390.3169871.1440319332.1441339521.1442067491.5; __utmz=51854390.1442067491.5.5.utmcsr=baidu|utmccn=(organic)|utmcmd=organic; __utmv=51854390.100-1|2=registration_date=20140525=1^3=entry_date=20140525=1; q_c1=efa8c4ccdba04f63a0ba88845f485836|1451394239000|1440047640000; _xsrf=20c250b28098f92459cac05a3944d48d; cap_id="ZWQ5OGIzN2JiZWNmNGRlNGE3YTE1MTE0YTA5YjY1NjE=|1451394239|0efd13fc965c43c0fb6a7a2523b5dac4d1dac7e3"; z_c0="QUFCQXRLa3ZBQUFYQUFBQVlRSlZUY29ScWxZN0k3T1BHaFdqb1JNVlVZekNnZ0trU0xXdEdnPT0=|1451394250|02ed77acc81edbf2340fd0ce1b13618862b3674e"; unlock_ticket="QUFCQXRLa3ZBQUFYQUFBQVlRSlZUZEtMZ2xiM21FNDRmdzdsX1NnOVdieUp3M1VtY0RsaUVBPT0=|1451394250|8cf44cefb523b2973eca01f0918ef97fc03a49qa"',
        
        ));
    curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:41.0) Gecko/20100101 Firefox/41.0');
    // 在HTTP请求头中"Referer: "的内容。
    curl_setopt($ch, CURLOPT_REFERER,"https://www.baidu.com/s?word=%E7%9F%A5%E4%B9%8E&tn=sitehao123&ie=utf-8&ssl_sample=normal&f=3&rsp=0");
    curl_setopt($ch, CURLOPT_ENCODING, "gzip, deflate, sdch");
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
    curl_setopt($ch, CURLOPT_URL, $url);
    curl_setopt($ch, CURLOPT_TIMEOUT,120);
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);//302redirect
    // 针对https的设置
    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, FALSE);
    curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 2);
    $html = curl_exec($ch);
    curl_close($ch);
    if($html === false) {
        echo 'Curl error: ' . curl_error($ch) . "<br>\n\r";
    } else {
        echo $html;
    }