META data updater for Mageworx SEO Ultimate

metafix.php

<?php
/**
 * Magento META data populator for us with Mageworx SEO Suite Ultimate.
 * Copyright Juicy Media Ltd
 * 
 * Features:
 * -> wipes META description and title
 * -> updates META keywords based on product description 
 * 
 * Usage:
 * 1) place the file in the root folder of the magento installation
 * 2) run from the command line: php ./metafix.php
 * 
 */

ini_set('memory_limit', '512M');
ini_set('max_input_time', 900);
ini_set('max_execution_time',900);

/**
 * Pass a description fields and it will filter common words:
 * http://www.hashbangcode.com/blog/extract-keywords-text-string-php-412.html
 * 
 * @param string $string
 * @param integer $returnno
 * @return array
 */
function extractCommonWords($string,$returnno){
	$stopWords = array('i','a','about','an','and','are','as','at','be','by','com','de','en','for','from','how','in','is','it','la','of','on','or','that','the','this','to','was','what','when','where','who','will','with','und','the','www');
	 
	$string = preg_replace('/\s\s+/i', '', $string); // replace whitespace
	$string = trim($string); // trim the string
	$string = preg_replace('/[^a-zA-Z0-9 -]/', '', $string); // only take alphanumerical characters, but keep the spaces and dashes too…
	$string = strtolower($string); // make it lowercase
	 
	preg_match_all('/\b.*?\b/i', $string, $matchWords);
	$matchWords = $matchWords[0];

	foreach ( $matchWords as $key=>$item ) {
		if ( $item == '' || in_array(strtolower($item), $stopWords) || strlen($item) <= 3 ) {
			unset($matchWords[$key]);
		}
	}
	$wordCountArr = array();
	if ( is_array($matchWords) ) {
		foreach ( $matchWords as $key => $val ) {
			$val = strtolower($val);
			if ( isset($wordCountArr[$val]) ) {
				$wordCountArr[$val]++;
			} else {
				$wordCountArr[$val] = 1;
			}
		}
	}
	arsort($wordCountArr);
	$wordCountArr = array_slice($wordCountArr, 0, $returnno);
	return $wordCountArr;
}
 
require_once ('app/Mage.php');
Mage::app()->setCurrentStore(Mage_Core_Model_App::ADMIN_STORE_ID);
 
// process products by getting a collection
$collection = Mage::getModel('catalog/product')->getCollection()
	->addAttributeToSelect('description')
	->addAttributeToSelect('meta_title')
	->addAttributeToSelect('meta_keywords')
	->addAttributeToSelect('meta_description')
	->load();

// backup existing data
$fp = fopen("prod-data-".date("Ymd-his").".csv", 'w');
foreach ($collection as $oneproduct) {
	// check sku and id exist, only continnue if they do
	$product['id'] = $oneproduct->getId();		
	$product['sku'] = $oneproduct->getSku();
	$product['meta_description'] = $oneproduct->getMetaDescription();
	$product['meta_keywords'] = $oneproduct->getMetaKeyword();
	$product['meta_title'] = $oneproduct->getMetaTitle();
	fputcsv($fp, $product, ";", '"');
}
fclose($fp);

// loop through products
foreach ($collection as $oneproduct) {
	// check sku and id exist, only continnue if they do
	$sku = $oneproduct->getSku();	
	$productId = $oneproduct->getId();
	if ($productId > 0 && !empty($sku)) {
	
		echo "--> ".$sku.", id - ".$productId."\n";
		ob_flush();
		
		// obtain and process description in to keywords
		$description = $oneproduct->getDescription();
		$meta_keywords = implode(',',array_keys(extractCommonWords($description,10)));
		
		// as long as the result is not empty update the product
		if (!empty($meta_keywords)){
			echo "----------> ".$meta_keywords."\n";

			// save the product with the new data
 			$oneproduct->setMetaTitle(null)
				->setMetaDescription(null)
				->setMetaKeyword($meta_keywords)
				->save();
		
			echo "----------> Updated ".$sku."\n";			
			
		} else {
			echo "**********> ERROR on ".$sku."\n";
		}
		ob_flush();
	}		
}