WordPress Yoast exclude posts from XML sitemap – SEO

I know the question has been answered already but I needed a more dynamical approach of what @clodclod91 explained and since I received the question more than once, I wrote some code about how to do this best in a ‘more fluid way’ than hardcoding any values.

I hope it helps some people.

I also wrote a post with a bit more explanation. Read it here.

/**
 * Set all excluded items for sitemap in a transient
 *
 * @return mixed
 */
function beee_get_sitemap_excludes_transient() {

    // get transient
    $output = get_transient( 'beee_exclude_sitemap' );

    // if transient returns false, create it
    if ( false == $output ) {

        $exclude_args = array(
            'post_type'      => [ 'page' ], // change this to the post types you want excluded
            'posts_per_page' => -1, // all items of course
            'meta_query'     => array(
                array(
                    'key'     => 'beee_exclude_sitemap',
                    'value'   => '1',
                    'compare' => '=',
                ),
            ),
            'orderby'        => 'ID',  // recommend to set to ID so 'the order is easier to compare later on', otherwise it can create issues
            'order'          => 'ASC', // same, just sort ASC to avoid issues
        );
        $excluded_items = get_posts( $exclude_args );
        if ( count( $excluded_items ) > 0 ) {
            // if there are items and create an empty array
            $exclude = [];
            foreach( $excluded_items as $item ) {
                // add post id to array
                $exclude[] = $item->ID;
            }
            // create a string from an array since Yoast stores a string, not an array
            $output = implode( ',', $exclude );

            // set transient with a 24-hour expiration
            set_transient( 'beee_exclude_sitemap', $output, 24 * HOUR_IN_SECONDS );
        }
    }

    return $output;
}

/**
 * Set Yoast settings from transient
 */
function beee_exclude_pages_sitemap( $post_id ) {

    // get our excluded items from transient
    $our_excluded_posts = beee_get_sitemap_excludes_transient();

    // check if 'exclude' field has been set (in the post)
    if ( 1 == get_field( 'beee_exclude_sitemap', $post_id ) ) {
        // if yes, check if it exists in transient
        if ( in_array( $post_id, explode( ',', $our_excluded_posts ) ) ) {
            // yes, it's already included so we don't have to do anything
        } else {
            // no, it's not included so it needs to be added
            // so we delete the transient (existing values)
            delete_transient( 'beee_exclude_sitemap' );
        }
    } else {
        // it has not been set in the post
        if ( in_array( $post_id, explode( ',', $our_excluded_posts ) ) ) {
            // if does exists in our stored transient, which it shouldn't be in there
            // so we delete the transient (existing values)
            delete_transient( 'beee_exclude_sitemap' );
        }
    }

    // get our excluded ids from transient
    // since we just cleared it, the transient doesn't exist and is retrieved from scratch
    $our_excluded_posts = beee_get_sitemap_excludes_transient();

    // get post ids from Yoast settings
    $wpseo_xml = get_option( 'wpseo_xml' );

    // compare Yoast's value with our items
    if ( $wpseo_xml[ 'excluded-posts' ] == $our_excluded_posts ) {
        // they are the same so we don't need to do anything
    } else {
        // they are not the same so we need to update the database with our new ids
        update_option( 'wpseo_xml', $wpseo_xml );
    }
}
add_action( 'save_post', 'beee_exclude_pages_sitemap' );