suabo/oxid_clean_articlelongdesc.php

## oxid_clean_articlelongdesc.php
<?php
/**
 * Clean article long descriptions
 * Author: Marcel Grolms - suabo
 */

echo "<html><head><meta charset='utf-8' /></head><body>";

include('bootstrap.php');

$oList = oxNew('oxlist');
$oList->init('oxarticle', 'oxarticles');
$oList->selectString('SELECT oxid FROM oxarticles WHERE 1 = 1;');

foreach($oList as $oArticle) {
    echo $oArticle->oxarticles__oxid->value . " - ok";
    echo "<br />";

    $sLongDesc = strip_html_tags($oArticle->getLongDesc());

    //echo $sLongDesc;
    //echo "<br />";

    $oArticle->setArticleLongDesc($sLongDesc);
    $oArticle->save();
}


function strip_html_tags($sString) {
    $sString = preg_replace(
        array(
            '@class="[^"]*?"@iu',
            '@style="[^"]*?"@iu',
            '@<head[^>]*?>.*?</head>@siu',
            '@<style[^>]*?>.*?</style>@siu',
            '@<script[^>]*?.*?</script>@siu',
            '@<object[^>]*?.*?</object>@siu',
            '@<embed[^>]*?.*?</embed>@siu',
            '@<applet[^>]*?.*?</applet>@siu',
            '@<noframes[^>]*?.*?</noframes>@siu',
            '@<noscript[^>]*?.*?</noscript>@siu',
            '@<noembed[^>]*?.*?</noembed>@siu',
            '@</?((address)|(blockquote)|(center)|(del))@iu',
            '@</?((div)|(h[1-9])|(ins)|(isindex)|(p)|(pre))@iu',
            '@</?((dir)|(dl)|(dt)|(dd)|(li)|(menu)|(ol)|(ul))@iu',
            '@</?((table)|(th)|(td)|(caption))@iu',
            '@</?((form)|(button)|(fieldset)|(legend)|(input))@iu',
            '@</?((label)|(select)|(optgroup)|(option)|(textarea))@iu',
            '@</?((frameset)|(frame)|(iframe))@iu',
            '@  @ ',
        ),
        array(
            '',
            '',
            '',
            '',
            '',
            '',
            '',
            '',
            '',
            '',
            '',
            "\n\$0",
            "\n\$0",
            "\n\$0",
            "\n\$0",
            "\n\$0",
            "\n\$0",
            "\n\$0",
            "\n\$0",
        ),
        $sString);

    $sString = preg_replace('/\s+/', ' ', $sString);
    $sString = preg_replace('/\s\s+/', ' ', $sString);
    $sString=preg_replace("~( +)~"," ",$sString);
    $sString=preg_replace("~( +)~"," ",$sString);
    return trim(strip_tags($sString, '<p><a><br><h1><h2><h3><h4><h5><h6><b><u><strong>'));
}

echo "</body></html>";
	<?php
	/**
	* Clean article long descriptions
	* Author: Marcel Grolms - suabo
	*/

	echo "<html><head><meta charset='utf-8' /></head><body>";

	include('bootstrap.php');

	$oList = oxNew('oxlist');
	$oList->init('oxarticle', 'oxarticles');
	$oList->selectString('SELECT oxid FROM oxarticles WHERE 1 = 1;');

	foreach($oList as $oArticle) {
	echo $oArticle->oxarticles__oxid->value . " - ok";
	echo "<br />";

	$sLongDesc = strip_html_tags($oArticle->getLongDesc());

	//echo $sLongDesc;
	//echo "<br />";

	$oArticle->setArticleLongDesc($sLongDesc);
	$oArticle->save();
	}



	function strip_html_tags($sString) {
	$sString = preg_replace(
	array(
	'@class="[^"]*?"@iu',
	'@style="[^"]*?"@iu',
	'@<head[^>]?>.?</head>@siu',
	'@<style[^>]?>.?</style>@siu',
	'@<script[^>]?.?</script>@siu',
	'@<object[^>]?.?</object>@siu',
	'@<embed[^>]?.?</embed>@siu',
	'@<applet[^>]?.?</applet>@siu',
	'@<noframes[^>]?.?</noframes>@siu',
	'@<noscript[^>]?.?</noscript>@siu',
	'@<noembed[^>]?.?</noembed>@siu',
	'@</?((address)\|(blockquote)\|(center)\|(del))@iu',
	'@</?((div)\|(h[1-9])\|(ins)\|(isindex)\|(p)\|(pre))@iu',
	'@</?((dir)\|(dl)\|(dt)\|(dd)\|(li)\|(menu)\|(ol)\|(ul))@iu',
	'@</?((table)\|(th)\|(td)\|(caption))@iu',
	'@</?((form)\|(button)\|(fieldset)\|(legend)\|(input))@iu',
	'@</?((label)\|(select)\|(optgroup)\|(option)\|(textarea))@iu',
	'@</?((frameset)\|(frame)\|(iframe))@iu',
	'@ @ ',
	),
	array(
	'',
	'',
	'',
	'',
	'',
	'',
	'',
	'',
	'',
	'',
	'',
	"\n\$0",
	"\n\$0",
	"\n\$0",
	"\n\$0",
	"\n\$0",
	"\n\$0",
	"\n\$0",
	"\n\$0",
	),
	$sString);

	$sString = preg_replace('/\s+/', ' ', $sString);
	$sString = preg_replace('/\s\s+/', ' ', $sString);
	$sString=preg_replace("~( +)~"," ",$sString);
	$sString=preg_replace("~( +)~"," ",$sString);
	return trim(strip_tags($sString, '<p><a><br><h1><h2><h3><h4><h5><h6><b><u><strong>'));
	}

	echo "</body></html>";