php curl 功能简介与抓取163邮件列表

http://hi.baidu.com/sjow001/item/f3fda20e56cbc0c675cd3cef

<?php
error_reporting(0);

//邮箱用户名(不带@163.com后缀的)
user=;//pass       = '*********';
//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);//cookiecookie         = tempnam('.','~');
refererlogin=http://mail.163.com;//curlsetopt(ch, CURLOPT_RETURNTRANSFER, true);
curl_setopt(ch,CURLOPTHEADER,true);curlsetopt(ch, CURLOPT_CONNECTTIMEOUT, 120);
curl_setopt($ch, CURLOPT_POST, true);

curl_setopt(ch,CURLOPTREFERER,referer_login);

fieldspost=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(fieldspostaskey => $value)
{
fieldsstring.=key . '=' . $value . '&';
}

fieldsstring=rtrim(fields_string , '&');

curl_setopt(ch,CURLOPTCOOKIESESSION,true);//cookiecurlsetopt(ch, CURLOPT_COOKIEJAR, cookie);curlsetopt(ch, CURLOPT_HTTPHEADER, headerslogin);curlsetopt(ch, CURLOPT_POST, count(fields));curlsetopt(ch, CURLOPT_POSTFIELDS, $fields_string);

result=curlexec(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=curlinit(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,CURLOPTRETURNTRANSFER,true);curlsetopt(ch, CURLOPT_HEADER, true);
curl_setopt(ch,CURLOPTCONNECTTIMEOUT,120);curlsetopt(ch, CURLOPT_POST, true);
curl_setopt(ch,CURLOPTHTTPHEADER,headers);
//将之前保存的cookie信息,一起发送到服务器端
curl_setopt(ch,CURLOPTCOOKIEFILE,cookie);
curl_setopt(ch,CURLOPTCOOKIEJAR,cookie);
result=curlexec(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=curlinit(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,CURLOPTRETURNTRANSFER,true);curlsetopt(ch, CURLOPT_HEADER, true);
curl_setopt(ch,CURLOPTCONNECTTIMEOUT,120);curlsetopt(ch, CURLOPT_POST, true);
curl_setopt(ch,CURLOPTHTTPHEADER,headers);
curl_setopt(ch,CURLOPTCOOKIEFILE,cookie);
curl_setopt(ch,CURLOPTCOOKIEJAR,cookie);
result=curlexec(ch);
curl_close(ch);//fileputcontents(./result.txt,result);
unlink($cookie);

//开始抓取内容
preg_match_all('/

]*>(.*?)<\/a><\/td>]*>(.*?)<\/a><\/td>/i', result,infos,PREG_SET_ORDER);
//1:姓名2:邮箱
print_r($infos);

/*
* 下面就可以为所欲为了- -
*/
?>


posted @   张同光  阅读(125)  评论(0编辑  收藏  举报
编辑推荐:
· 基于Microsoft.Extensions.AI核心库实现RAG应用
· Linux系列:如何用heaptrack跟踪.NET程序的非托管内存泄露
· 开发者必知的日志记录最佳实践
· SQL Server 2025 AI相关能力初探
· Linux系列:如何用 C#调用 C方法造成内存泄露
阅读排行:
· 无需6万激活码!GitHub神秘组织3小时极速复刻Manus,手把手教你使用OpenManus搭建本
· Manus爆火,是硬核还是营销?
· 终于写完轮子一部分:tcp代理 了,记录一下
· 别再用vector<bool>了!Google高级工程师:这可能是STL最大的设计失误
· 单元测试从入门到精通
点击右上角即可分享
微信分享提示