네트워크 데이터를 크롤링하는 PHP의 고전적인 방법 index.php forum.php phpno

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

        $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;

$url = 'http://blog.csdn.net/guugle2010';
$handle = fopen($url, r);
$html = '';
while(!feof($handle)){
    $html .= fgets($handle);
}
echo $html;
fclose($handle);

$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;

$url = 'http://blog.csdn.net/guugle2010';
function get_url($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);

$url = 'http://blog.csdn.net/guugle2010';
function HTTP_Post($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="<span style="font-family: Arial, Helvetica, sans-serif;">blog.csdn.net</span><span style="font-family: Arial, Helvetica, sans-serif;">";</span>

	// 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'=>'<span style="font-family: Arial, Helvetica, sans-serif;">blog.csdn.net/guugle2010</span><span style="font-family: Arial, Helvetica, sans-serif;">', </span>
	'name'=>'guugle'); 
	
$cookie = '';
$referer = 'http://blog.csdn.net/';
	
echo HTTP_Post($url, $data, $cookie, $referer);