iframe 제거

$STRING=preg_replace("!<iframe(.*?)<\/iframe>!is","",$STRING);

script 제거

$STRING=preg_replace("!<script(.*?)<\/script>!is","",$STRING);

meta 제거

$STRING=preg_replace("!<meta(.*?)>!is","",$STRING);

style 태그 제거

$STRING=preg_replace("!<style(.*?)<\/style>!is","",$STRING);

&nbsp;를 공백으로 변환

$STRING=str_replace("&nbsp;"," ",$STRING);

연속된 공백 1개로

$STRING=preg_replace("/\s{2,}/"," ",$STRING);

태그안에 style= 속성 제거

$STRING=preg_replace("/ style=([^\"\']+) /"," ",$STRING); // style=border:0... 따옴표가 없을때
$STRING=preg_replace("/ style=(\"|\')?([^\"\']+)(\"|\')?/","",$STRING); // style="border:0..." 따옴표 있을때

태그안의 width=, height= 속성 제거

$STRING=preg_replace("/ width=(\"|\')?\d+(\"|\')?/","",$STRING);
$STRING=preg_replace("/ height=(\"|\')?\d+(\"|\')?/","",$STRING);

img 태그 추출 src 추출

preg_match("/<img[^>]*src=[\"']?([^>\"']+)[\"']?[^>]*>/i",$STRING,$RESULT);
preg_match_all("/<img[^>]*src=[\"']?([^>\"']+)[\"']?[^>]*>/i",$STRING,$RESULT);

호스트 추출

<?
preg_match("/^(http:\/\/)?([^\/]+)/i","http://www.kaudo.com/index.html",$matches);
$host = $matches[2];
echo$matches[0]."<br>";
echo$matches[1]."<br>";
echo$matches[2]."<br>";
?>
http://www.kaudo.com
http://
www.kaudo.com

매뉴얼:
http://kr2.php.net/manual/kr/function.preg-replace.php
http://kr2.php.net/manual/kr/function.preg-match.php
http://kr2.php.net/manual/kr/function.str-replace.php