CURL技术说白了就是模拟浏览器的动作实现页面抓取或表单提交,通过此技术可以实现许多有去的功能。 <div class="codetitle"><a style="CURSOR: pointer" data="25558" class="copybut" id="copybut25558" onclick="doCopy('code25558')"> 代码如下:<div class="codebody" id="code25558"> <?php error_reporting(0); //邮箱用户名(不带@163.com后缀的) $user = 'papatata_test'; //邮箱密码 $pass = '000000'; //目标邮箱 //$mail_addr = uenucom@163.com'; //登陆 $url = 'http://reg.163.com/logins.jsp?type=1&url=http://entry.mail.163.com/coremail/fcg/ntesdoor2?lightweight%3D1%26verifycookie%3D1%26language%3D-1%26style%3D-1'; $ch = curl_init($url); //创建一个用于存放cookie信息的临时文件 $cookie = tempnam('.','~'); $referer_login = 'http://mail.163.com'; //返回结果存放在变量中,而不是默认的直接输出 curl_setopt($ch,CURLOPT_RETURNTRANSFER,true); curl_setopt($ch,CURLOPT_HEADER,CURLOPT_CONNECTTIMEOUT,120); curl_setopt($ch,CURLOPT_POST,CURLOPT_REFERER,$referer_login); $fields_post = array( 'username'=> $user, 'password'=> $pass, 'verifycookie'=>1, 'style'=>-1, 'product'=> 'mail163', 'selType'=>-1, 'secure'=>'on' ); $headers_login = array( 'User-Agent' => 'Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/2008052906 Firefox/3.0', 'Referer' => 'http://www.163.com' ); $fields_string = ''; foreach($fields_post as $key => $value) { $fields_string .= $key . '=' . $value . '&'; } $fields_string = rtrim($fields_string,'&'); curl_setopt($ch,CURLOPT_COOKIESESSION,true); //关闭连接时,将服务器端返回的cookie保存在以下文件中 curl_setopt($ch,CURLOPT_COOKIEJAR,$cookie); curl_setopt($ch,CURLOPT_HTTPHEADER,$headers_login); curl_setopt($ch,count($fields)); curl_setopt($ch,CURLOPT_POSTFIELDS,$fields_string); $result= curl_exec($ch); curl_close($ch); //跳转 $url='http://entry.mail.163.com/coremail/fcg/ntesdoor2?lightweight=1&verifycookie=1&language=-1&style=-1&username=loki_wuxi'; $ch = curl_init($url); $headers = array( 'User-Agent' => 'Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/2008052906 Firefox/3.0' ); curl_setopt($ch,$headers); //将之前保存的cookie信息,一起发送到服务器端 curl_setopt($ch,CURLOPT_COOKIEFILE,$cookie); $result = curl_exec($ch); curl_close($ch); //取得sid preg_match('/sid=[^"]./',$result,$location); $sid = substr($location[0],4,-1); //file_put_contents('./result.txt',$sid); //通讯录地址 $url='http://g4a30.mail.163.com/jy3/address/addrlist.jsp?sid='.$sid.'&gid=all'; $ch = curl_init($url); $headers = array( 'User-Agent' => 'Mozilla/5.0 (Windows; U; Windows NT 5.1; zh-CN; rv:1.9) Gecko/2008052906 Firefox/3.0' ); curl_setopt($ch,$headers); curl_setopt($ch,$cookie); $result = curl_exec($ch); curl_close($ch); //file_put_contents('./result.txt',$result); unlink($cookie); //开始抓取内容 preg_match_all('/<td class="Ibx_Td_addrName"><a[^>]>(.?)</a></td><td class="Ibx_Td_addrEmail"><a[^>]>(.*?)</a></td>/i',$infos,PREG_SET_ORDER); //1:姓名2:邮箱 print_r($infos); ?>
(编辑:李大同)
【声明】本站内容均来自网络,其相关言论仅代表作者个人观点,不代表本站立场。若无意侵犯到您的权利,请及时与联系站长删除相关内容!
|