Search Options

Results per page
Sort
Preferred Languages
Advance

Results 21 - 30 of 34 for sitemaps (0.06 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                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 + ".*");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 19.1K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

        }
    
        /**
         * Adds a sitemap URL to the list of sitemaps.
         *
         * @param url The URL of the sitemap to be added
         */
        public void addSitemap(final String url) {
            if (!sitemapList.contains(url)) {
                sitemapList.add(url);
            }
        }
    
        /**
         * Returns an array of sitemap URLs.
         *
         * @return an array of sitemap URLs
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10K bytes
    - Viewed (0)
  3. fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                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 + ".*");
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 12.8K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

                        if (robotsTxt != null) {
                            final String[] sitemaps = robotsTxt.getSitemaps();
                            if (sitemaps.length > 0) {
                                crawlerContext.addSitemaps(sitemaps);
                            }
    
                            final RobotsTxt.Directive directive = robotsTxt.getMatchedDirective(userAgent);
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 52.2K bytes
    - Viewed (0)
  5. fess-crawler/src/test/resources/sitemaps/sitemap2.xml.gz

    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...
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 217 bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/Sitemap.java

    import java.io.Serializable;
    
    /**
     * The Sitemap interface represents a sitemap entity with location and last modification date.
     * It extends the Serializable interface to allow sitemap objects to be serialized.
     */
    public interface Sitemap extends Serializable {
    
        /**
         * Retrieves the location (URL) of the sitemap.
         *
         * @return the location of the sitemap as a String.
         */
        String getLoc();
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 1.2K bytes
    - Viewed (0)
  7. fess-crawler/src/test/resources/sitemaps/sitemap1.xml.gz

    sitemap1.xml http://www.example.com/ 2005-01-01 monthly 0.8 http://www.example.com/catalog?item=12&desc=vacation_hawaii weekly http://www.example.com/catalog?item=73&desc=vacation_new_zealand 2004-12-23 weekly http://www.example.com/catalog?item=74&desc=vacation_newfoundland 2004-12-23T18:00:15+00:00 0.3 http://www.example.com/catalog?item=83&desc=vacation_usa 2004-11-23...
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 332 bytes
    - Viewed (0)
  8. fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots.txt

    User-agent: Crawler
    Disallow: /aaa
    
    User-agent: Crawler/1.0
    Disallow: /bbb
    
    User-agent: Crawler/2.0
    Disallow: /ccc
    
    User-agent: Hoge Crawler
    Disallow: /ddd
    
    sitemap: http://www.example.com/sitmap.xml
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 566 bytes
    - Viewed (0)
  9. fess-crawler/src/test/resources/sitemaps/sitemap1.txt

    Shinsuke Sugaya <******@****.***> 1444529815 +0900
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 273 bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapUrl.java

    import org.codelibs.core.lang.StringUtil;
    
    /**
     * Represents a URL entry within a sitemap.
     *
     * <p>
     * This class encapsulates the properties of a URL as defined in the sitemap XML format,
     * including its location, last modification date, change frequency, and priority.
     * It implements the {@link Sitemap} interface.
     * </p>
     *
     * <p>
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 6.5K bytes
    - Viewed (0)
Back to top