}
        return pruneNodeByTags(node, prunedTags);
    }

    /**
     * Prunes nodes based on the specified pruned tags.
     *
     * @param node the node to prune
     * @param prunedTags the array of pruned tag configurations
     * @return the pruned node
     */
    protected Node pruneNodeByTags(final Node node, final PrunedTag[] prunedTags) {

# XPath to extract canonical URL from HTML documents.
crawler.document.html.canonical.xpath=//LINK[@rel='canonical'][1]/@href
# HTML tags to prune (remove) during document processing.
crawler.document.html.pruned.tags=noscript,script,style,header,footer,aside,nav,a[rel=nofollow]
# Maximum length of digest extracted from HTML documents.
crawler.document.html.max.digest.length=120