PHP uses regular expressions to extract links in content

function get_all_url($code){ 
    preg_match_all('/"' ]+)["|']?s*[^>]*>([^>]+)/i',$code,$arr); 
    return array('name'=>$arr[2],'url'=>$arr[1]); 
}

/**
 * date 2015-07-24
 **/
 
$site=substr($url,0,strpos($url,"/",8));//站点 
$base=substr($url,0,strrpos($url,"/")+1);//文件所在目录 
$fp = fopen($url, "r" );//打开url 
while(!feof($fp))$contents.=fread($fp,1024);// 
$pattern="|href=['"]?([^ '"]+)['" ]|u"; 
preg_match_all($pattern,$contents, $regarr, preg_set_order);//匹配所有href= 
for($i=0;$i";//根目录 
else
  echo "link".($i+1).":".$base.$regarr[$i][1]."
";//当前目录 
else
echo "link".($i+1).":".$regarr[$i][1]."
";//相对路径 
}
fclose($fp);