php正则表达式提取网页超链接url与网页中图片

function match_links($document) {
   preg_match_all("'<s*as.*?hrefs*=s*(["'])?(?(1)(.*?)1|([^s>]+))[^>]*>?(.*?)</a>'isx",$document,$links);
   while(list($key,$val) = each($links[2])) {
      if(!empty($val))
         $match['link'][] = $val;
}
while(list($key,$val) = each($links[3])) {
if(!empty($val))
$match['link'][] = $val;
}
while(list($key,$val) = each($links[4])) {
if(!empty($val))
$match['content'][] = $val;
}
while(list($key,$val) = each($links[0])) {
if(!empty($val))
$match['all'][] = $val;
}
return $match;
}

public string GetHref(string HtmlCode)
{
string MatchVale = "";
string Reg = @"(h|H)(r|R)(e|E)(f|F) *= *('|"")?((w||/|.|:|-|_)+)('|""| *|>)?";
foreach (Match m in Regex.Matches(HtmlCode, Reg))
{
MatchVale += (m.Value).ToLower().Replace("href=", "").Trim() + "||";
}
return MatchVale;
}

if (preg_match_all("/http://[^ "']+[.jpg|.gif|.jpeg|.png]+/ui",stripcslashes($content),$aliurl)){
$i=0; //多个文件++
while(list($key ,$v) = each($aliurl[0])){
//echo $v."<br />";
$filetype = pathinfo($v, PATHINFO_EXTENSION); //获取后缀名
$ff = @file_get_contents($v); //获取2进制文件内容
if(!stripos($v,"jb200.com")){//判断是否是自己网站下的图片
if (!empty($ff)){ //获取到文件就执行下面的操作
$dir = "upload/".date("Ymd")."/";//指定新的存储路径
if (!file_exists($dir)){//判断目录是否存在
@mkdir($dir,511,true); //创建多级目录,511转换成十进制是777具有可执行权限
} // www.jb200.com
$nfn = $dir.date("Ymdhis").$i.".".$filetype; //构建文件的新名字
$nf = @fopen($nfn,"w"); //创建文件
fwrite($nf,$ff); //写入文件
fclose($nf); //关闭文件
$i++; //多文件++
echo "<img src="".$nfn."">";
$content = str_replace($v,$nfn, $content);//替换content中的参数
}else{//获取不到图片则替换为默认图片
$content = str_replace($v,"/upload/201204/20120417213810742.gif", $content);//替换content中的参数
}
}
}
}

<?php
/*
shortage: 如果网页中的图片路径不是绝对路径，就无法抓取
*/
set_time_limit(0);//抓取不受时间限制

$URL='http://pp.baidu.com/';//任意网址

get_pic($URL);

function get_pic($pic_url) {
//获取图片二进制流
$data=CurlGet($pic_url);
/*利用正则表达式得到图片链接*/
$pattern_src = '/<[img|IMG].*?src=['|"](.*?(?:[.gif|.jpg]))['|"].*?[/]?>/';
$num = preg_match_all($pattern_src, $data, $match_src);
$arr_src=$match_src[1];//获得图片数组
get_name($arr_src);

echo "<br>finished!!!";
return 0;
}

/*得到图片类型，并将其保存到与该文件同一目录*/
function get_name($pic_arr)
{
//图片类型
$pattern_type = '/(/.(jpg|bmp|jpeg|gif|png))/';

foreach($pic_arr as $pic_item){//循环取出每幅图的地址
$num = preg_match_all($pattern_type, $pic_item, $match_type);
$pic_name = get_unique().$match_type[1][0];//改时微秒时间戳命名
//以流的形式保存图片
$write_fd = @fopen($pic_name,"wb");
@fwrite($write_fd, CurlGet($pic_item));
@fclose($write_fd);
echo "[OK]..!";
}
return 0;
}

//通过微秒时间获得唯一ID
function get_unique(){
list($msec, $sec) = explode(" ",microtime());
return $sec.intval($msec*1000000);
}

//抓取网页内容
function CurlGet($url){
$url=str_replace('&','&',$url);
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HEADER, false);

//curl_setopt($curl, CURLOPT_REFERER,$url);
curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0; SeaPort/1.2; Windows NT 5.1; SV1; InfoPath.2)");
curl_setopt($curl, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($curl, CURLOPT_COOKIEFILE, 'cookie.txt');
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 0);
$values = curl_exec($curl);
curl_close($curl);
return $values;
}
?>