PHP读取指定URL网页地址中的所有链接

<?

$html = file_get_contents('http://www.baidu.com');

$dom = new DOMDocument();

@$dom->loadHTML($html);

$xpath = new DOMXPath($dom);

$hrefs = $xpath->evaluate('/html/body//a');

for ($i = 0; $i < $hrefs->length; $i++) {

$href = $hrefs->item($i);

$url = $href->getAttribute('href');

// 保留以http开头的链接

if(substr($url, 0, 4) == 'http'){

echo $url.'<br />';

}

}

?>