PHP 컬은 오프사이트 수집을 구현합니다(권장)

// 初始化一个 cURL 对象 
$curl = curl_init(); 
// 设置你需要抓取的URL 
curl_setopt($curl, CURLOPT_URL, 'http://www.cmx8.cn'); 
// 设置header 
curl_setopt($curl, CURLOPT_HEADER, 1); 
// 设置cURL 参数，要求结果保存到字符串中还是输出到屏幕上。 
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); 
// 运行cURL，请求网页 
$data = curl_exec($curl); 
// 关闭URL请求 
curl_close($curl);

//$data是curl_exec返回的的值，即采集的目标内容 
preg_match_all("/<li class=\"item\">(.*?)<\/li>/",$data, $out, PREG_SET_ORDER); 
foreach($out as $key => $value){ 
    //此处$value是数组，同时记录找到带匹配字符的整句和单独匹配的字符 
    echo &#39;匹配到的整句：&#39;.$value[0].&#39;
&#39;; 
    echo &#39;单独匹配到的：&#39;.$value[1].&#39;
&#39;; 
}

curl_setopt($ch, CURLOPT_TIMEOUT, 60);   //只需要设置一个秒的数量就可以 
curl_setopt($ch, CURLOPT_NOSIGNAL, 1);    //注意，毫秒超时一定要设置这个 
curl_setopt($ch, CURLOPT_TIMEOUT_MS, 200);  //超时毫秒，cURL 7.16.2中被加入。从PHP 5.2.3起可使用

//以下摘抄一个例子过来，用于学习借鉴: 
//Curl 模拟登录 discuz 程序,适合DZ7.0 
!extension_loaded('curl') && die('The curl extension is not loaded.');    
$discuz_url = 'http://www.lxvoip.com';//论坛地址    
$login_url = $discuz_url .'/logging.php?action=login';//登录页地址    
$get_url = $discuz_url .'/my.php?item=threads'; //我的帖子    
$post_fields = array();    
//以下两项不需要修改    
$post_fields['loginfield'] = 'username';    
$post_fields['loginsubmit'] = 'true';    
//用户名和密码，必须填写    
$post_fields['username'] = 'lxvoip';    
$post_fields['password'] = '88888888';    
//安全提问    
$post_fields['questionid'] = 0;    
$post_fields['answer'] = '';    
//@todo验证码    
$post_fields['seccodeverify'] = '';    
//获取表单FORMHASH    
$ch = curl_init($login_url);    
curl_setopt($ch, CURLOPT_HEADER, 0);    
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);    
$contents = curl_exec($ch);    
curl_close($ch);    
preg_match(&#39;/<input\s*type="hidden"\s*name="formhash"\s*value="(.*?)"\s*\/>/i&#39;, $contents, $matches);    
if(!empty($matches)) {    
    $formhash = $matches[1];    
} else {    
    die(&#39;Not found the forumhash.&#39;);    
}    
//POST数据，获取COOKIE    
$cookie_file = dirname(__FILE__) . &#39;/cookie.txt&#39;;    
//$cookie_file = tempnam(&#39;/tmp&#39;);    
$ch = curl_init($login_url);    
curl_setopt($ch, CURLOPT_HEADER, 0);    
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);    
curl_setopt($ch, CURLOPT_POST, 1);    
curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);    
curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);    
curl_exec($ch);    
curl_close($ch);    
//带着上面得到的COOKIE获取需要登录后才能查看的页面内容    
$ch = curl_init($get_url);    
curl_setopt($ch, CURLOPT_HEADER, 0);    
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);    
curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);    
$contents = curl_exec($ch);    
curl_close($ch);    
var_dump($contents);