(网页抓取)一个用PHP实现的网页抓取的实例

PHP实现的网页抓取的实例

<?
$url = "http://www.lingjuli99.com/new.asp";
$contents = file_get_contents($url);
echo $contents;


$url = "http://www.lingjuli99.com/new.asp";
$ch = curl_init();
$timeout = 5;
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
//在需要用户检测的网页里需要增加下面两行
//curl_setopt($ch, CURLOPT_HTTPAUTH, CURLAUTH_ANY);
//curl_setopt($ch, CURLOPT_USERPWD, US_NAME.":".US_PWD);
$contents = curl_exec($ch);
curl_close($ch);
echo $contents;

$handle = fopen ("http://www.xxx.com/", "rb");
$contents = "";
do {
$data = fread($handle, 8192);
if (strlen($data) == 0) {
break;
}
$contents .= $data;
} while(true);
fclose ($handle);
echo $contents;


if(function_exists('fsockopen'))
     {

        $urlinfo = parse_url($url);
        $host = $urlinfo['host'];
        $str = explode($host, $url);
        $uri = $str[1];
        unset($urlinfo, $str);
        $content = '';
        $fp = fsockopen($host, 80, $errno, $errstr, 30);
        if(!$fp)
        {
            $content = 'Can Not Open Socket...';
        }
        else
        {
            $out = "GET $uri   HTTP/1.1rn";
            $out.= "Host: $host rn";
            $out.= "Accept: */*rn";
            $out.= "User-Agent: $_SERVER[HTTP_USER_AGENT]rn";
            $out.= "Connection: Closernrn";
            fputs($fp, $out);
            while (!feof($fp))
            {
                $content .= fgets($fp, 4069);
            }
            fclose($fp);
        }
    }


$html = file_get_contents($url); 
print_r($http_response_header);

$fp = fopen($url, 'r'); 
print_r(stream_get_meta_data($fp)); 
fclose($fp);


$zd = gzopen($filename, "r"); 
$contents = gzread($zd, filesize ($filename)); 
gzclose($zd);
file_put_contents($filename,$contents);
?>