* 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.

            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);

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;

    protected DynamicProperties systemProperties;

    /** Service for managing web crawler configurations */
    @Resource
    protected WebConfigService webConfigService;

    /** Service for managing file crawler configurations */
    @Resource
    protected FileConfigService fileConfigService;

    /** Helper for managing crawler processes */
    @Resource
    protected ProcessHelper processHelper;

        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";
        options.fileConfigIds = "file1";

        int result = crawler.doCrawl(options);
        assertEquals(Constants.EXIT_OK, result);
    }

    public void test_doCrawl_withDataConfigIds() {
        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";

            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);

* [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

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.CrawlerStatus;
import org.codelibs.fess.crawler.interval.FessIntervalController;
import org.codelibs.fess.crawler.service.impl.OpenSearchDataService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlFilterService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlQueueService;

        return resultBuf.toString();

    }

    /**
     * Gets the count of currently running crawler jobs.
     * This method queries the scheduled jobs to count active crawler processes.
     * Used to enforce maximum concurrent crawler limits.
     *
     * @return the number of currently running crawler jobs
     */
    protected int getRunningJobCount() {
        final AtomicInteger counter = new AtomicInteger(0);