<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">
   <url>
      <loc>http://www.example.com/</loc>
      <lastmod>2005-01-01</lastmod>
      <changefreq>monthly</changefreq>
      <priority>0.8</priority>
   </url>
   <url>
      <loc>http://www.example.com/catalog?item=12&amp;desc=vacation_hawaii</loc>
      <changefreq>weekly</changefreq>
   </url>
   <url>

     * Sitemap were changed. The value for the lastmod tag should be in W3C
     * Datetime format.
     *
     * By providing the last modification timestamp, you enable search engine
     * crawlers to retrieve only a subset of the Sitemaps in the index i.e. a
     * crawler may only retrieve Sitemaps that were modified since a certain
     * date. This incremental Sitemap fetching mechanism allows for the rapid

    }

    protected void addSitemapsFromRobotsTxt(final UrlQueue<?> urlQueue) {
        final String[] sitemaps = crawlerContext.removeSitemaps();
        if (sitemaps != null) {
            for (final String childUrl : sitemaps) {
                try {
                    storeChildUrl(childUrl, urlQueue.getUrl(), null, urlQueue.getDepth() == null ? 1 : urlQueue.getDepth() + 1);

    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>
    <include path="crawler/sitemaps.xml"/>

    <include path="crawler/opensearch.xml"/>

	<!-- Crawler -->
	<component name="crawler" class="org.codelibs.fess.crawler.Crawler" instance="prototype" >
	</component>

	<!-- Crawler Thread -->

	<include path="crawler/extractor.xml"/>
	<include path="crawler/mimetype.xml"/>
	<include path="crawler/encoding.xml"/>
	<include path="crawler/urlconverter.xml"/>
	<include path="crawler/log.xml"/>
	<include path="crawler/sitemaps.xml"/>

	<!-- Crawler -->
	<component name="crawler" class="org.codelibs.fess.crawler.Crawler" instance="prototype" >
	</component>

	<!-- Crawler Thread -->

            file.delete();
            file.mkdirs();
            file.deleteOnExit();
            fileTransformer.setPath(file.getAbsolutePath());
            crawler.addUrl(url + "sitemaps.xml");
            crawler.crawlerContext.setMaxAccessCount(maxCount);
            crawler.crawlerContext.setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");

            file.delete();
            file.mkdirs();
            file.deleteOnExit();
            fileTransformer.setPath(file.getAbsolutePath());
            crawler.addUrl(url + "sitemaps.xml");
            crawler.crawlerContext.setMaxAccessCount(maxCount);
            crawler.crawlerContext.setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");

                    if (robotsTxt != null) {
                        final String[] sitemaps = robotsTxt.getSitemaps();
                        if (sitemaps.length > 0) {
                            crawlerContext.addSitemaps(sitemaps);
                        }

                        final RobotsTxt.Directive directive = robotsTxt.getMatchedDirective(userAgent);

sitemap2.xml http://www.example.com/sitemap1.xml.gz 2004-10-01T18:23:17+00:00 http://www.example.com/sitemap2.xml.gz 2005-01-01...

    public void removeSitemap(final Sitemap sitemap) {
        sitemapList.remove(sitemap);
    }

    public Sitemap[] getSitemaps() {
        return sitemapList.toArray(new Sitemap[sitemapList.size()]);
    }

    public void setType(final String type) {
        this.type = type;
    }

    public boolean isUrlSet() {
        return URLSET.equals(type);
    }

    public boolean isIndex() {