有时候需要登入网站，然后去抓取一些有用的信息，人工做的话，太累了。有的人可以很快的做到登入，但是需要在登入后再去访问其他页面始终都访问不了，因为他们没有带Cookie进去而被当做是两次会话。下面看看代码
<?php //test.php
function getWebContent($host,$page="/",$paramstr="",$cookies='',$medth="POST",$port=80){
$fp = fsockopen($host,$port);
if(!$fp){
return false;
}
$medth = strtoupper($medth);
$medth = $medth=="POST" ? "POST":"GET";
$length = strlen($paramstr);
if($medth == "GET" && $paramstr){
$page .= "?".$paramstr;
}
$out = "$medth $page HTTP/1.1 ";
$out .= "Accept: */* ";
$out .= "Host: www.exaple.com ";
$out .= "Content-Length: ".$length." ";
$out .= "Content-Type: application/x-www-form-urlencoded ";
if($cookies){
$out .= "Cookie: ".$cookies." ";
}
$out .= "Connection: Keep-Alive ";
if($medth=='POST' && $paramstr){
$out .= $paramstr." ";
}
fwrite($fp, $out);
$cookie = "";
$content = "";
while (!feof($fp)) {
$str = fgets($fp);
if(preg_match("/Set-Cookie:([^ ]*)/",$str,$matchs)){
if($cookie){
$cookie .= ";".$matchs[1];
}else{
$cookie = $matchs[1];
}
}
$content .= $str;
echo $str;
}
fclose($fp);
return array('content'=>$content,'cookie'=>$cookie);
}
$params = "name=admin&pwd=admin";
$rs = getWebContent("127.0.0.1","/test/login.php",$params,"","POST",8080);
echo $rs['content'];
$rs = getWebContent("127.0.0.1","/test/index.php","",$rs['cookie'],"POST",8080);
//这里传入上次cookie是关键,否则会被当成两次会话
echo $rs['content'];
?>
<?php //login.php
$name = $_REQUEST['name'];
$pwd = $_REQUEST['pwd'];
if($name == "admin" && $pwd == "admin"){
setcookie("cname",$name);
echo "success";
}else{
echo "failed";
}
?>
<?php //index.php
if(isset($_COOKIE['cname']) && $_COOKIE['cname']){
echo "<ul><li>1</li><li>2</li><li>3</li><li>4</li><li>5</li><li>6</li></ul>";
}else{
echo "please login first!";
}
?>
将上面三个文件分别保存，login.php和index.php放在root目录下的test目录下。然后test.php放在任意目录，然后去命令行运行php test.php，结果就能出来。
还有一种更简单的方式，就是用curl,代码如下，可以用下面的代码替换test.php
<?php
$post_data = array (
"name" => "admin",
"pwd" => "admin",
);
$cookie_jar = tempnam('./', 'cookie');//新建cookie文件
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, "http://localhost:8080/test/login.php");
//设定返回的数据是否自动显示
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
// 我们在POST数据哦！
curl_setopt($ch, CURLOPT_POST, 1);
// 把post的变量加上
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
//把返回来的cookie信息保存在$cookie_jar文件中
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_jar);
echo curl_exec($ch);
curl_close($ch);
$ch2 = curl_init();
curl_setopt($ch2, CURLOPT_URL, "http://localhost:8080/test/index.php");
curl_setopt($ch2, CURLOPT_HEADER, false);
curl_setopt($ch2, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch2, CURLOPT_COOKIEFILE, $cookie_jar);
echo curl_exec($ch2);
unlink($cookie_jar);
curl_close($ch2);
?>
