Maison >développement back-end >tutoriel php >hp 论坛 php 论坛采集程序 模拟登陆,抓取页面 实现代码
复制代码 代码如下:
// 吴燕军
// 2009-06-27
// 采集程序php
set_time_limit(0);
//cookie保存目录
$cookie_jar = '/tmp/cookie.tmp';
/*函数------------------------------------------------------------------------------------------------------------*/
//模拟请求数据
function request($url,$postfields,$cookie_jar,$referer){
$ch = curl_init();
$options = array(CURLOPT_URL => $url,
CURLOPT_HEADER => 0,
CURLOPT_NOBODY => 0,
CURLOPT_PORT => 80,
CURLOPT_POST => 1,
CURLOPT_POSTFIELDS => $postfields,
CURLOPT_RETURNTRANSFER => 1,
CURLOPT_FOLLOWLOCATION => 1,
CURLOPT_COOKIEJAR => $cookie_jar,
CURLOPT_COOKIEFILE => $cookie_jar,
CURLOPT_REFERER => $referer
);
curl_setopt_array($ch, $options);
$code = curl_exec($ch);
curl_close($ch);
return $code;
}
//获取帖子列表
function getThreadsList($code){
preg_match_all('/