Get top 100 words / keywords from a text with PHP

This is useful if you want to create dynamic keywords from content or just sort words by appearing frequency in a text or html by excluding very common words like "the on and to ...". You can give custom limit of words to return and custom words to ignore.

<?php


function top_words($str, $limit=100, $ignore=""){

	if(!$ignore) $ignore = "the of to and a in for is The that on said with be was by";
	
	
	$ignore_arr = explode(" ", $ignore);

	$str = trim($str);
	$str = preg_replace("#[&].{2,7}[;]#sim", " ", $str);
	$str = preg_replace("#[()°^!\"§\$%&/{(\[)\]=}?´`,;.:\-_\#'~+*]#", " ", $str);
	$str = preg_replace("#\s+#sim", " ", $str);
	$arraw = explode(" ", $str);
	
	foreach($arraw as $v){
		$v = trim($v);
		if(strlen($v)<3 || in_array($v, $ignore_arr)) continue;
		$arr[$v]++;
	}
	
	arsort($arr);
	
	return array_keys( array_slice($arr, 0, $limit) );
}

// usage:
// $meta_keywords = implode(", ", top_words( strip_tags( $html_content ) ) );
?>