Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 10 of 954 for crawled (0.09 sec)

  1. misc/linkcheck/linkcheck.go

    func crawl(url string, sourceURL string) {
    	if strings.Contains(url, "/devel/release") {
    		return
    	}
    	mu.Lock()
    	defer mu.Unlock()
    	if u, frag, ok := strings.Cut(url, "#"); ok {
    		url = u
    		if frag != "" {
    			uf := urlFrag{url, frag}
    			neededFrags[uf] = append(neededFrags[uf], sourceURL)
    		}
    	}
    	if crawled[url] {
    		return
    	}
    	crawled[url] = true
    
    	wg.Add(1)
    	go func() {
    Registered: Tue Nov 05 11:13:11 UTC 2024
    - Last Modified: Wed Oct 06 15:53:04 UTC 2021
    - 3.9K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/filter/UrlFilter.java

        /**
         * Add an url pattern as a target.
         *
         * @param urlPattern Regular expression that is crawled
         */
        void addInclude(String urlPattern);
    
        /**
         * Add an url pattern as a non-target.
         *
         * @param urlPattern Regular expression that is not crawled
         */
        void addExclude(String urlPattern);
    
        /**
         * Process an url when it's added as a seed url.
         *
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.6K bytes
    - Viewed (0)
  3. src/main/java/org/codelibs/fess/exec/Crawler.java

                if (logger.isDebugEnabled()) {
                    logger.debug("Crawler is stopped.", e);
                } else if (logger.isInfoEnabled()) {
                    logger.info("Crawler is stopped.");
                }
                exitCode = Constants.EXIT_FAIL;
            } catch (final Throwable t) {
                logger.error("Crawler does not work correctly.", t);
                exitCode = Constants.EXIT_FAIL;
            } finally {
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:20:39 UTC 2024
    - 24K bytes
    - Viewed (0)
  4. samples/crawler/src/main/java/okhttp3/sample/Crawler.java

          System.out.println("Usage: Crawler <cache dir> <root>");
          return;
        }
    
        int threadCount = 20;
        long cacheByteCount = 1024L * 1024L * 100L;
    
        Cache cache = new Cache(new File(args[0]), cacheByteCount);
        OkHttpClient client = new OkHttpClient.Builder()
            .cache(cache)
            .build();
    
        Crawler crawler = new Crawler(client);
        crawler.queue.add(HttpUrl.get(args[1]));
    Registered: Fri Nov 01 11:42:11 UTC 2024
    - Last Modified: Thu Aug 12 07:26:27 UTC 2021
    - 4.6K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

     */
    package org.codelibs.fess.crawler;
    
    import java.text.SimpleDateFormat;
    import java.util.Date;
    import java.util.Locale;
    
    import org.codelibs.core.lang.StringUtil;
    import org.codelibs.fess.crawler.client.CrawlerClientFactory;
    import org.codelibs.fess.crawler.container.CrawlerContainer;
    import org.codelibs.fess.crawler.entity.AccessResult;
    import org.codelibs.fess.crawler.entity.UrlQueue;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 7.9K bytes
    - Viewed (0)
  6. fess-crawler-lasta/src/main/resources/crawler.xml

    <components namespace="fessCrawler">
    	<include path="crawler/container.xml"/>
    	<include path="crawler/client.xml"/>
    	<include path="crawler/rule.xml"/>
    	<include path="crawler/filter.xml"/>
    	<include path="crawler/interval.xml"/>
    	<include path="crawler/extractor.xml"/>
    	<include path="crawler/mimetype.xml"/>
    	<include path="crawler/encoding.xml"/>
    	<include path="crawler/urlconverter.xml"/>
    	<include path="crawler/log.xml"/>
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Tue Nov 28 13:40:25 UTC 2017
    - 1.7K bytes
    - Viewed (0)
  7. src/main/resources/mail/crawler.dfmail

    /*
     [Crawler Notification]
     Crawler notification mail.
    */
    subject: [FESS] Crawler completed: /*pmb.hostname*/
    >>>
    --- Server Info ---
    Host Name: /*pmb.hostname:orElse('Unknown')*/
    Job Name: /*pmb.jobname:orElse('Unknown')*/
    
    --- Web/FileSystem Crawler ---
    Start Time: /*pmb.webFsCrawlStartTime:orElse('-')*/
    End Time:   /*pmb.webFsCrawlEndTime:orElse('-')*/
    Exec Time:  /*pmb.webFsCrawlExecTime:orElse('-')*/ ms
    
    --- Web/FileSystem Indexer ---
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Wed Jan 15 22:05:20 UTC 2020
    - 1K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                crawler1.addUrl(url1);
                crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
                crawler1.getCrawlerContext().setNumOfThread(numOfThread);
    
                final Crawler crawler2 = container.getComponent("crawler");
                crawler2.setSessionId(crawler2.getSessionId() + "2");
                crawler2.setBackground(true);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 18K bytes
    - Viewed (0)
  9. fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                crawler1.addUrl(url1);
                crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
                crawler1.getCrawlerContext().setNumOfThread(numOfThread);
    
                final Crawler crawler2 = crawlerContainer.getComponent("crawler");
                crawler2.setSessionId(crawler2.getSessionId() + "2");
                crawler2.setBackground(true);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:47:32 UTC 2024
    - 11.9K bytes
    - Viewed (0)
  10. fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

                crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
                crawler1.getCrawlerContext().setNumOfThread(numOfThread);
    
                Thread.sleep(100);
    
                final Crawler crawler2 = getComponent(Crawler.class);
                crawler2.setBackground(true);
                ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
                crawler2.addUrl(url2);
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Nov 07 04:44:10 UTC 2024
    - 7.7K bytes
    - Viewed (0)
Back to top