正则提取URL

<?php

function getPageLink($url)
{
set_time_limit(0);
$html = file_get_contents($url);
preg_match_all("/<a(s*[^>]+s*)href=([\"|']?)([^\"'>\s]+)([\"|']?)/ies",$html,$out);
$arrLink = $out[3];
$arrUrl = parse_url($url);

if( isset($arrUrl['path']) && !empty($arrUrl['path']) )
        {
$dir = str_replace('\\','/',$dir = dirname($arrUrl['path']));
if( $dir == '/') $dir = '';
        }

if(is_array($arrLink) && count($arrLink) > 0)
        {
$arrLink = array_unique($arrLink);
foreach($arrLink as $key=>$val)
                {
$val = strtolower($val);
if( preg_match('/^#*$/isU',$val))
                        {
unset($arrLink[$key]);
                        }
else  if(preg_match('/^\//isU',$val))
                        {
$arrLink[$key] = 'http://'.$arrUrl['host'].$val;
                        }
else  if(preg_match('/^javascript/isU',$val))
                        {
unset($arrLink[$key]);
                        }
else  if(preg_match('/^mailto:/isU',$val))
                        {
unset($arrLink[$key]);
                        }
else  if( !preg_match('/^\//isU',$val) && strpos($val,'http://') === FALSE)
                        {
$arrLink[$key] = 'http://'.$arrUrl['host'].$path.'/'.$val;
                        }
                }
        }
sort($arrLink);
return $arrLink;
}

print_r(getPageLink('http://www.hao123.com'));
?>

转载于:https://www.cnblogs.com/chenwenbiao/archive/2012/03/06/2382497.html