欢迎您访问程序员文章站本站旨在为大家提供分享程序员计算机编程知识!
您现在的位置是: 首页  >  后端开发

PHP经典抓取网络数据方法 index.php forum.php phpno

程序员文章站 2022-04-10 18:16:10
...
1、file_get_contents

以get的方式获取数据

$url = 'blog.csdn.net/guugle2010';
$html = file_get_contents($url);
echo $html;

以post方式获取数据

        $data = array(
                'name' => 'guugle',
                'blog' => 'blog.csdn.net/guugle2010'
        );      
        $data = http_build_query($data);
        $options = array(
                'http' => array(
                        'method' => 'POST',
                        'header' => 'Content-type:application/x-www-form-urlencode',
                        'content' => $data
                )
        );
        $url = "http://localhost/test.php";
        $context = stream_context_create($options);
        $result = file_get_contents($url, false, $context);
        echo $result;
2、fopen方式
$url = 'http://blog.csdn.net/guugle2010';
$handle = fopen($url, r);
$html = '';
while(!feof($handle)){
    $html .= fgets($handle);
}
echo $html;
fclose($handle);
3、curl库,需要打开curl扩展
$url = 'http://blog.csdn.net/guugle2010';
$ch = curl_init();
$timeout = 5;
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
$file_contents = curl_exec($ch);
curl_close($ch);
 
echo $file_contents;

4、用fsocketopen打开链接

以get的方式获取完整的数据(包括header和body)

$url = 'http://blog.csdn.net/guugle2010';
function get_url($url,$cookie=false)
{
    $url = parse_url($url);
    $query = $url['path']."?".$url['query'];
    echo "Query:".$query;
    $fp = fsockopen( $url['host'], $url['port']?$url['port']:80 , $errno, $errstr, 30);
    if (!$fp)
    {
        return false;
    }
    else {
        $request = "GET $query HTTP/1.1\r\n";
        $request .= "Host: $url[host]\r\n";
        $request .= "Connection: Close\r\n";
        if($cookie) $request.="Cookie:   $cookie\n";
        $request.="\r\n";
        fwrite($fp,$request);
		$result = '';
        while(!feof($fp))
        {
            $result .= @fgets($fp, 1024);
        }
        fclose($fp);
        return $result;
    }
}
//获取url的html部分,去掉header
function GetUrlHTML($url,$cookie=false)
{
    $rowdata = get_url($url,$cookie);
    if($rowdata)
    {
        $body= stristr($rowdata,"\r\n\r\n");
        $body=substr($body,4,strlen($body));
        return $body;
    }

    return false;
}

echo get_url($url);

echo GetUrlHTML($url);

以post方式获取完整数据(包括header和body)
$url = 'http://blog.csdn.net/guugle2010';
function HTTP_Post($URL,$data,$cookie, $referer="")
{

	// parsing the given URL
    $URL_Info=parse_url($URL);

	// Building referrer
    if($referer=="") // if not given use this script as referrer
        $referer="blog.csdn.net";

	// making string from $data
    foreach($data as $key=> $value)
    $values[]="$key=".urlencode($value);
    $data_string=implode("&",$values);

	// Find out which port is needed - if not given use standard (=80)
    if(!isset($URL_Info["port"]))
        $URL_Info["port"]=80;
	
	$request = '';
	// building POST-request:
    $request.="POST ".$URL_Info["path"]." HTTP/1.1\n";
    $request.="Host: ".$URL_Info["host"]."\n";
    $request.="Referer: $referer\n";
    $request.="Content-type: application/x-www-form-urlencoded\n";
    $request.="Content-length: ".strlen($data_string)."\n";
    $request.="Connection: close\n";

    $request.="Cookie:   $cookie\n";

    $request.="\n";
    $request.=$data_string."\n";

    $fp = fsockopen($URL_Info["host"],$URL_Info["port"]);
    fputs($fp, $request);
	$result = '';
    while(!feof($fp))
    {
        $result .= fgets($fp, 1024);
    }
    fclose($fp);

    return $result;
}

$data = array(
	'site'=>'blog.csdn.net/guugle2010', 
	'name'=>'guugle'); 
	
$cookie = '';
$referer = 'http://blog.csdn.net/';
	
echo HTTP_Post($url, $data, $cookie, $referer);

以上就介绍了PHP经典抓取网络数据方法,包括了php,网络方面的内容,希望对PHP教程有兴趣的朋友有所帮助。

相关标签: php 网络