}

        return parser;
    }

    /**
     * Gets the base href from the document's BASE tag.
     *
     * @param document the document to extract base href from
     * @return the base href URL, or null if not found
     */
    protected String getBaseHref(final Document document) {
        try {

        final Map<String, String> childUrlRuleMap = newHashMap();
        childUrlRuleMap.put("//A", "href");
        childUrlRuleMap.put("//AREA", "href");
        childUrlRuleMap.put("//FRAME", "src");
        childUrlRuleMap.put("//IFRAME", "src");
        childUrlRuleMap.put("//IMG", "src");
        childUrlRuleMap.put("//LINK", "href");
        childUrlRuleMap.put("//SCRIPT", "src");

        container = new StandardCrawlerContainer();

import org.codelibs.fess.crawler.entity.RobotsTxt.Directive;
import org.codelibs.fess.crawler.exception.RobotsTxtException;

/**
 * Robots.txt Specifications:
 * <ul>
 * <li><a href=
 * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
 * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
 * </a></li>
 * </ul>
 *
 * @author bowez