Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 44 for sitemaps (0.15 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/SitemapsHelperTest.java

            final InputStream in = ResourceUtil.getResourceAsStream("sitemaps/sitemap1.xml");
            final SitemapSet sitemapSet = sitemapsHelper.parse(in);
            final Sitemap[] sitemaps = sitemapSet.getSitemaps();
            assertEquals(5, sitemaps.length);
            assertTrue(sitemapSet.isUrlSet());
            assertFalse(sitemapSet.isIndex());
    
            assertEquals("2005-01-01", sitemaps[0].getLastmod());
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 9.6K bytes
    - Viewed (0)
  2. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/SitemapsRuleTest.java

            responseData.setResponseBody(file, false);
            return responseData;
        }
    
        private ResponseData getTestData3_OK() {
            final ResponseData responseData = new ResponseData();
            responseData.setUrl("http://example.com/sitemap.txt");
            File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.txt");
            responseData.setResponseBody(file, false);
            return responseData;
        }
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 4.7K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerContext.java

        }
    
        public void addSitemaps(final String[] sitemaps) {
            sitemapsLocal.set(sitemaps);
        }
    
        public String[] removeSitemaps() {
            final String[] sitemaps = sitemapsLocal.get();
            if (sitemaps != null) {
                sitemapsLocal.remove();
            }
            return sitemaps;
        }
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 4.5K bytes
    - Viewed (0)
  4. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/RuleManagerImplTest.java

        }
    
        public void test_getRule_sitemaps1() {
            final ResponseData responseData = new ResponseData();
            responseData.setUrl("http://www.example.com/sitemap1.xml");
            File file = ResourceUtil.getResourceAsFile("sitemaps/sitemap1.xml");
            responseData.setResponseBody(file, false);
            final Rule rule = ruleManager.getRule(responseData);
            assertNotNull(rule);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.2K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/SitemapsHelper.java

            } catch (final Exception e) {
                throw new CrawlingAccessException("Could not parse Sitemaps: " + preloadDate, e);
            }
        }
    
        protected SitemapSet parseTextSitemaps(final InputStream in) {
            final SitemapSet sitemapSet = new SitemapSet();
            sitemapSet.setType(SitemapSet.URLSET);
    
            try {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 11.8K bytes
    - Viewed (0)
  6. 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: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.3K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/helper/RobotsTxtHelperTest.java

            assertFalse(robotsTxt.allows("/ddd", "Hoge Crawler"));
    
            String[] sitemaps = robotsTxt.getSitemaps();
            assertEquals(2, sitemaps.length);
            assertEquals("http://www.example.com/sitmap.xml", sitemaps[0]);
            assertEquals("http://www.example.net/sitmap.xml", sitemaps[1]);
    
        }
    
        public void testParse_disable() {
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 5.9K bytes
    - Viewed (0)
  8. 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: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.3K bytes
    - Viewed (0)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapFile.java

         * 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
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 2.7K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/CrawlerThread.java

        }
    
        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);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:41:37 UTC 2024
    - 15.5K bytes
    - Viewed (0)
Back to top