<?php $data = 'alsdj<img src="http://localdomain.com/donotinclude.jpg">fklasjdf<img src="image.jpg">asdfasdf<img src="http://domain.com/image.jpg">asdfasdfsf<img src="dont_include_me.png">asdfasfasdf'; $images = array(); // Domains to not include images from (for instances where the full URL is specified to image) $localhosts = array( 'localdomain.com' ); // Remove or add any extensions TO be included $allowed_extensions = array( 'jpg', 'jpeg' ); preg_match_all('/(img|src)\=(\"|\')[^\"\'\>]+/i', $data, $media); unset($data); $data=preg_replace('/(img|src)(\"|\'|\=\"|\=\')(.*)/i',"$3",$media[0]); foreach($data as $url) { $url_data = parse_url( $url ); $info = pathinfo($url); // Goto next, we're only looking for remote hosts if( ! array_key_exists( 'host', $url_data ) ) continue; // Check if this is an extension we want to include if( array_key_exists( 'extension', $info ) && in_array( $info['extension'], $allowed_extensions) ){ // Verify this isn't one of our local hosts (where the full URL is specified) if( ! in_array( $url_data['host'], $localhosts ) ){ array_push($images, $url); } } } echo 'Total Images: ' . count( $images ); // This is just linebreaks for display formatting print "\n\n"; echo 'Image Data:'; var_dump( $images );