Search Options

Results per page
Sort
Preferred Languages
Advance

Results 11 - 20 of 44 for Sitemaps (2.73 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

                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');
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.3K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapSet.java

        }
    
        /**
         * Adds a sitemap to this set.
         * @param sitemap the sitemap to add
         */
        public void addSitemap(final Sitemap sitemap) {
            sitemapList.add(sitemap);
        }
    
        /**
         * Removes a sitemap from this set.
         * @param sitemap the sitemap to remove
         */
        public void removeSitemap(final Sitemap sitemap) {
            sitemapList.remove(sitemap);
        }
    
        /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.9K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerContextTest.java

        }
    
        /**
         * Test sitemaps add and remove operations
         */
        public void test_sitemaps() {
            // Initial state
            assertNull(crawlerContext.removeSitemaps());
    
            // Add sitemaps
            String[] sitemaps = new String[] { "http://example.com/sitemap.xml", "http://test.com/sitemap.xml" };
            crawlerContext.addSitemaps(sitemaps);
    
            // Remove and verify
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 25.6K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapVideo.java

     * </p>
     *
     * @see <a href="https://developers.google.com/search/docs/crawling-indexing/sitemaps/video-sitemaps">Video Sitemaps</a>
     */
    public class SitemapVideo implements Serializable {
    
        private static final long serialVersionUID = 1L;
    
        /**
         * A URL pointing to the video thumbnail image file.
         * Images must be at least 160x90 pixels and at most 1920x1080 pixels.
         */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Nov 13 13:34:36 UTC 2025
    - 8.9K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/SitemapsHelper.java

    /**
     * Helper class for parsing and validating sitemaps.
     * It supports XML sitemaps, XML sitemap indexes, and text sitemaps,
     * and can handle GZIP compressed sitemaps.
     * The class provides methods to check if an input stream is a valid sitemap,
     * and to parse an input stream into a {@link SitemapSet} object.
     * It uses SAX parser for XML sitemaps and XML sitemap indexes,
     * and handles potential exceptions during parsing.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Fri Nov 14 13:19:40 UTC 2025
    - 34.9K bytes
    - Viewed (0)
  6. fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/util/CrawlerWebServer.java

                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');
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 6.3K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapFile.java

     * and processing of Sitemap data.
     * </p>
     *
     * <p>
     * The {@code loc} attribute specifies the URL of the Sitemap, while the {@code lastmod} attribute
     * indicates the last time the Sitemap file was modified.  The {@code lastmod} attribute is used by crawlers
     * to incrementally fetch sitemaps that have been updated since a certain date.
     * </p>
     *
     * <p>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 4.4K bytes
    - Viewed (1)
  8. fess-crawler/src/test/resources/sitemaps/sitemap1.xml

    <?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>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 915 bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/SitemapsRule.java

     * represents a valid sitemap. It uses a SitemapsHelper to validate the response body as an InputStream.
     * The rule checks if the URL matches the defined regex pattern and then validates the content as a sitemap.
     * If any exception occurs during the sitemap validation, it logs the error and returns false.
     *
     */
    public class SitemapsRule extends RegexRule {
        /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.6K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerThread.java

        }
    
        /**
         * Adds sitemaps from robots.txt to the crawling queue.
         * @param urlQueue The URL queue to add sitemaps to.
         */
        protected void addSitemapsFromRobotsTxt(final UrlQueue<?> urlQueue) {
            final String[] sitemaps = crawlerContext.removeSitemaps();
            if (sitemaps != null) {
                for (final String childUrl : sitemaps) {
                    try {
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 20.4K bytes
    - Viewed (0)
Back to top