Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 17 for crawl (0.04 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/RobotsTxtHelper.java

    import org.codelibs.fess.crawler.exception.RobotsTxtException;
    
    /**
     * Robots.txt Specifications:
     * <ul>
     * <li><a href=
     * "https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt"
     * >https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
     * </a></li>
     * </ul>
     *
     * @author bowez
     * @author shinsuke
     *
     */
    public class RobotsTxtHelper {
    
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Sat Oct 12 01:40:57 UTC 2024
    - 6.1K bytes
    - Viewed (0)
  2. src/main/java/org/codelibs/fess/exec/Crawler.java

                    webFsCrawlerThread = new Thread((Runnable) () -> {
                        // crawl web
                        writeTimeToSessionInfo(crawlingInfoHelper, Constants.WEB_FS_CRAWLER_START_TIME);
                        webFsIndexHelper.crawl(options.sessionId, webConfigIdList, fileConfigIdList);
                        writeTimeToSessionInfo(crawlingInfoHelper, Constants.WEB_FS_CRAWLER_END_TIME);
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:20:39 UTC 2024
    - 24K bytes
    - Viewed (0)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/entity/SitemapUrl.java

         * command. Even though search engine crawlers may consider this information
         * when making decisions, they may crawl pages marked "hourly" less
         * frequently than that, and they may crawl pages marked "yearly" more
         * frequently than that. Crawlers may periodically crawl pages marked
         * "never" so that they can handle unexpected changes to those pages.
         */
        private String changefreq;
    
        /**
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 4.9K bytes
    - Viewed (0)
  4. src/main/resources/fess_label_de.properties

    labels.crawling_info_CrawlerExecTime=Crawler Ausführungsdauer
    labels.crawling_info_CrawlerStatus=Crawler-Status
    labels.crawling_info_WebFsCrawlExecTime=Crawl Ausführungsdauer (Web/Dateisystem)
    labels.crawling_info_WebFsCrawlStartTime=Crawl Startzeit (Web/Dateisystem)
    labels.crawling_info_WebFsCrawlEndTime=Crawl Endzeit (Web/Dateisystem)
    labels.crawling_info_WebFsIndexExecTime=Indizierung Ausführungsdauer (Web/Dateisystem)
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Mar 22 11:58:34 UTC 2024
    - 42.8K bytes
    - Viewed (0)
  5. src/main/java/org/codelibs/fess/helper/DataIndexHelper.java

        protected int crawlerPriority = Thread.NORM_PRIORITY;
    
        protected final List<DataCrawlingThread> dataCrawlingThreadList = Collections.synchronizedList(new ArrayList<>());
    
        public void crawl(final String sessionId) {
            final List<DataConfig> configList = ComponentUtil.getCrawlingConfigHelper().getAllDataConfigList();
    
            if (configList.isEmpty()) {
                // nothing
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:37:57 UTC 2024
    - 12K bytes
    - Viewed (0)
  6. src/main/resources/fess_label_en.properties

    labels.crawling_info_WebFsCrawlExecTime=Crawl exec time (Web/File system)
    labels.crawling_info_WebFsCrawlStartTime=Crawl start time (Web/File system)
    labels.crawling_info_WebFsCrawlEndTime=Crawl end time (Web/File system)
    labels.crawling_info_WebFsIndexExecTime=Indexing exec time (Web/File system)
    labels.crawling_info_WebFsIndexSize=Index size (Web/File system)
    labels.crawling_info_DataCrawlExecTime=Crawl exec time (Data store)
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Mar 22 11:58:34 UTC 2024
    - 40.7K bytes
    - Viewed (0)
  7. src/main/java/org/codelibs/fess/helper/WebFsIndexHelper.java

        protected int crawlerPriority = Thread.NORM_PRIORITY;
    
        protected final List<Crawler> crawlerList = Collections.synchronizedList(new ArrayList<>());
    
        public void crawl(final String sessionId, final List<String> webConfigIdList, final List<String> fileConfigIdList) {
            final boolean runAll = webConfigIdList == null && fileConfigIdList == null;
            final List<WebConfig> webConfigList;
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:11:58 UTC 2024
    - 22.6K bytes
    - Viewed (0)
  8. src/main/resources/fess_label.properties

    labels.crawling_info_WebFsCrawlExecTime=Crawl exec time (Web/File system)
    labels.crawling_info_WebFsCrawlStartTime=Crawl start time (Web/File system)
    labels.crawling_info_WebFsCrawlEndTime=Crawl end time (Web/File system)
    labels.crawling_info_WebFsIndexExecTime=Indexing exec time (Web/File system)
    labels.crawling_info_WebFsIndexSize=Index size (Web/File system)
    labels.crawling_info_DataCrawlExecTime=Crawl exec time (Data store)
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Mar 22 11:58:34 UTC 2024
    - 40.7K bytes
    - Viewed (0)
  9. src/main/resources/fess_label_ru.properties

    labels.crawling_info_WebFsCrawlExecTime=Crawl exec time (Web/File system)
    labels.crawling_info_WebFsCrawlStartTime=Crawl start time (Web/File system)
    labels.crawling_info_WebFsCrawlEndTime=Crawl end time (Web/File system)
    labels.crawling_info_WebFsIndexExecTime=Indexing exec time (Web/File system)
    labels.crawling_info_WebFsIndexSize=Index size (Web/File system)
    labels.crawling_info_DataCrawlExecTime=Crawl exec time (Data store)
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Mar 22 11:58:34 UTC 2024
    - 45.6K bytes
    - Viewed (0)
  10. build-logic-commons/code-quality-rules/src/main/resources/checkstyle/suppressions.xml

    <?xml version="1.0"?>
    
    <!DOCTYPE suppressions PUBLIC
        "-//Puppy Crawl//DTD Suppressions 1.1//EN"
        "http://www.puppycrawl.com/dtds/suppressions_1_1.dtd">
    
    <suppressions>
        <!-- These packages are duplicated in core-api, don't require a package-info.java in each place -->
        <suppress checks="JavadocPackage"
                  files=".*[/\\]stdlib-java-extensions[/\\]src[/\\]main[/\\]java[/\\]org[/\\]gradle[/\\]api[/\\][^/\\]+"/>
    Registered: Wed Nov 06 11:36:14 UTC 2024
    - Last Modified: Mon Jun 10 14:28:48 UTC 2024
    - 10.5K bytes
    - Viewed (0)
Back to top