* Please note that the value of this tag is considered a hint and not a
     * 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.
     */

     * 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
     * discovery of new URLs on very large sites.

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute") : Framework Web
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job") : Planificateur de tâches
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler") : Crawler Web

            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 {

            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);

 */
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;

            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);

      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]));

<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"/>

/*
 [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 ---