怎么抓取网页实时内容

如何抓取网页实时内容

<br />#网址：http://data.shishicai.cn/cqssc/haoma/<br />#Demo：<br /><?php<br />/* Created on [2013-5-1] Author[Newton] Filename[action.php]*/<br />#编码转换<br />function convToUtf8($str) {<br />	if (mb_detect_encoding($str, "UTF-8, ISO-8859-1, GBK") != "UTF-8") {<br />		return iconv("GBK", "utf-8", $str);<br />	} else {<br />		return $str;<br />	}<br />}<br /><br />header("content-type:te<b>6本文来源gao@dai!ma.com搞$代^码!网7</b><pre>搞gaodaima代码

xt/html;charset:utf-8″);
error_reporting(E_ERROR);
$pages = file_get_contents(‘http://data.shishicai.cn/cqssc/haoma/’);
//$pages = htmlspecialchars($pages);
$pages = convToUtf8($pages);
echo “pages–>>”.print_r($pages);echo PHP_EOL;
$doc = new DOMDocument();
$new_doc = new DOMDocument(‘1.0’, ‘utf-8’);

echo “doc–>>”.print_r($doc);echo PHP_EOL;
$dom = $doc->getElementsByTagName(‘table’);

$newdoc = $new_doc->loadhtml($dom->item(2)->nodeValue);
$table = $new_doc->saveHTML();
echo “table–>>{$table}”.PHP_EOL;

#result：
#……乱码……
#pages–>>1 DOMDocument Object ( ) doc–>>1 table–>>
#table是空的……
?>

PHP DOM