cURL

1. 简单的爬虫

　　1. xampp开启php的cURL -> xampp/php/php.ini 搜索curl去掉分号便可

　　2. cmd D: -> cd xampp -> cd php

　 　　php -f ../htdocs/mirror/curl/curl.php > ../htdocs/mirror/curl/haha.html  (将爬下来的数据保存在haha.html中)

//  ../htdocs/mirror/curl/curl.php
<?php
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, "http://www.baidu.com");
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);

    $output = curl_exec($ch);
        //将输出文件中百度替换成屌丝
    echo str_replace("百度", "屌丝", $output);
?>

 

2. 访问WebService

　　http://www.webxml.com.cn/WebServices/WeatherWebService.asmx?op=getWeatherbyCityName

<?php
    $data = 'theCityName=武汉';
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, "http://www.webxml.com.cn/WebServices/WeatherWebService.asmx/getWeatherbyCityName");
    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_USERAGENT, 1); 
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
    curl_setopt($ch, CURLOPT_HTTPHEADER, array("application/x-www-form-urlencoded;
        charset=utf-8", 
        "Content-length:".strlen($data)
        ));

    $rtn = curl_exec($ch);
    if(!curl_errno($ch))
        echo $rtn;
    else
        echo "Curl error ".curl_error($ch);

    curl_close($ch);

?>

　　

 

3. 模拟登录后下载登录以后的信息

<?php
    $data = "username=252973202@qq.com&password=这个密码就不写出来啦&remember=1";
    $ch = curl_init();
    curl_setopt($ch, CURLOPT_URL, "http://www.imooc.com/user/login");
    curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);  //执行以后不直接打印出来
    
    //模拟登录开始
    date_default_timezone_set('PRC'); //设置Cookie时区(有过时时间)
    //模板 大多数都是如此 
    curl_setopt($ch, CURLOPT_COOKIESESSION, true);
    curl_setopt($ch, CURLOPT_COOKIEFILE, "cookiefile");
    curl_setopt($ch, CURLOPT_COOKIEJAR, "cookiefile");
    curl_setopt($ch, CURLOPT_COOKIE, "session_name()"."=".session_id());

    curl_setopt($ch, CURLOPT_HEADER, 0);
    curl_setopt($ch, CURLOPT_USERAGENT, 1);
    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1); //cURL支持页面连接跳转
    curl_setopt($ch, CURLOPT_POST, 1);
    curl_setopt($ch, CURLOPT_POSTFIELDS, $data);
    curl_setopt($ch, CURLOPT_HTTPHEADER, array("application/x-www-form-urlencoded;
        charset=utf-8", 
        "Content-length:".strlen($data)
        ));

    $rtn = curl_exec($ch);
    //模拟登录结束

    //登录成功后获取登录以后的信息
    curl_setopt($ch, CURLOPT_URL, "http://www.imooc.com/space/index");
    curl_setopt($ch, CURLOPT_POST, 0);
    curl_setopt($ch, CURLOPT_HTTPHEADER, array("Content-type:text/xml"));

    $output = curl_exec($ch);

    curl_close($ch);

    echo $output;

?>