Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 4 of 4 for getSitemaps (0.06 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapSet.java

            sitemapList.remove(sitemap);
        }
    
        /**
         * Gets all sitemaps in this set as an array.
         * @return an array of sitemaps
         */
        public Sitemap[] getSitemaps() {
            return sitemapList.toArray(new Sitemap[sitemapList.size()]);
        }
    
        /**
         * Sets the type of this sitemap set.
         * @param type the type to set (URLSET or INDEX)
         */
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 2.9K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

                final SitemapSet sitemapSet = sitemapsHelper.parse(responseBody);
                final Set<RequestData> requestDataSet = new LinkedHashSet<>();
                for (final Sitemap sitemap : sitemapSet.getSitemaps()) {
                    if (sitemap != null) {
                        requestDataSet.add(RequestDataBuilder.newRequestData().get().url(sitemap.getLoc()).build()); // TODO priority
                    }
                }
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/RobotsTxt.java

                sitemapList.add(url);
            }
        }
    
        /**
         * Returns an array of sitemap URLs.
         *
         * @return an array of sitemap URLs
         */
        public String[] getSitemaps() {
            return sitemapList.toArray(new String[sitemapList.size()]);
        }
    
        /**
         * Represents a directive in a robots.txt file.
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 10K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/http/HcHttpClient.java

                        final RobotsTxt robotsTxt = robotsTxtHelper.parse(httpEntity.getContent());
                        if (robotsTxt != null) {
                            final String[] sitemaps = robotsTxt.getSitemaps();
                            if (sitemaps.length > 0) {
                                crawlerContext.addSitemaps(sitemaps);
                            }
    
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 52.2K bytes
    - Viewed (0)
Back to top