}
        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

        this.tag = tag;
    }

    /**
     * Checks if this pruned tag configuration matches the given DOM node.
     * The matching is based on tag name, and optionally ID, CSS class, or custom attributes.
     *
     * @param node the DOM node to check against this pruned tag configuration
     * @return true if the node matches this pruned tag configuration, false otherwise
     */
    public boolean matches(final Node node) {

     */
    String getCrawlerDocumentHtmlCanonicalXpath();

    /**
     * Get the value for the key 'crawler.document.html.pruned.tags'. <br>
     * The value is, e.g. noscript,script,style,header,footer,aside,nav,a[rel=nofollow] <br>
     * comment: HTML tags to prune (remove) during document processing.
     * @return The value of found property. (NotNull: if not found, exception but basically no way)
     */

            public static final String JCIFS_PREFIX = "jcifs.";
            public static final String HTML_CANONICAL_XPATH = "html.canonical.xpath";
            public static final String HTML_PRUNED_TAGS = "html.pruned.tags";
            public static final String PIPELINE = "pipeline";
            public static final String IGNORE_ROBOTS_TAGS = "ignore.robots.tags";
            public static final String SCRIPT_TYPE = "script.type";

                this.fileLocator.updateType(response.getFileType());
                info = response;
                fileSize = response.getDataSize();

                // this is so damn unreliable, needs another race-prone query if required
                haveAttributes = false;

                // This seems to be the only way to obtain a reliable (with respect to locking) file size here