<?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>

        }
        return false;
    }

    /**
     * Generates SitemapSet instance.
     *
     * This method does not close the input stream.
     *
     * @param in Input stream for a sitemap
     * @return a sitemap set
     */
    public SitemapSet parse(final InputStream in) {
        return parse(in, true);
    }

    protected SitemapSet parse(final InputStream in, final boolean recursive) {

			<component
				class="org.codelibs.fess.crawler.processor.impl.SitemapsResponseProcessor">
			</component>
		</property>
		<postConstruct name="addRule">
			<arg>"url"</arg>
			<arg>".*sitemap.*"</arg>
		</postConstruct>
	</component>

	<component name="fileRule" class="org.codelibs.fess.crawler.rule.impl.RegexRule">
		<property name="ruleId">"fileRule"</property>
		<property name="defaultRule">true</property>

            robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');
            buf.append("<url>").append('\n');

            } catch (final CrawlingAccessException e) {
                throw e;
            } catch (final Exception e) {
                if (logger.isDebugEnabled()) {
                    logger.debug("Failed a sitemap check: {}", responseData, e);
                }
            }
        }

        return false;
    }

 */
package org.codelibs.fess.crawler.entity;

import org.codelibs.core.lang.StringUtil;

/**
 * @author shinsuke
 *
 */
public class SitemapUrl implements Sitemap {

    private static final long serialVersionUID = 1L;

    /**
     * URL of the page. This URL must begin with the protocol (such as http) and

            robotTxtFile.deleteOnExit();

            // sitemaps.xml
            buf = new StringBuilder();
            buf.append("<?xml version=\"1.0\" encoding=\"UTF-8\"?>").append('\n');
            buf.append("<urlset ").append("xmlns=\"http://www.sitemaps.org/schemas/sitemap/0.9\">").append('\n');
            buf.append("<url>").append('\n');

    protected static final Pattern CRAWL_DELAY_RECORD = Pattern.compile("^crawl-delay:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    protected static final Pattern SITEMAP_RECORD = Pattern.compile("^sitemap:\\s*([^\\s]+)\\s*$", Pattern.CASE_INSENSITIVE);

    protected boolean enabled = true;

    public RobotsTxt parse(final InputStream stream) {
        return parse(stream, Constants.UTF_8);
    }

                    rule.setResponseProcessor(container.getComponent("sitemapsResponseProcessor"));
                    rule.setRuleId("sitemapsRule");
                    rule.addRule("url", ".*sitemap.*");
                })//
                .<DefaultResponseProcessor> singleton("defaultResponseProcessor", DefaultResponseProcessor.class, processor -> {

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...