Sie können in der Administrationsoberfläche (Web, Datei, Datenspeicher) Crawling-Ziele in den Crawler-Konfigurationsseiten registrieren und den Crawler manuell auf der [Scheduler-Seite](https://fess.codelibs.org/15.3/admin/scheduler-guide.html) starten.

## Migration von einem anderen Suchanbieter

Bitte lesen Sie [MIGRATION.md](MIGRATION.md).

## Datenspeicher

    OkHttpClient client = new OkHttpClient.Builder()
        .cache(cache)
        .callTimeout(5, TimeUnit.SECONDS)
        .build();

    Crawler crawler = new Crawler(client, queueLimit, hostLimit);
    crawler.queue.add(HttpUrl.get(args[1]));
    crawler.parallelDrainQueue(threadCount);
  }

<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 ---

            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = getComponent(Crawler.class);
            crawler2.setBackground(true);
            ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
            crawler2.addUrl(url2);
            crawler2.getCrawlerContext().setMaxAccessCount(maxCount);

│   ├── config/                # Config index (crawl configs, schedules)
│   ├── log/                   # Log index (search logs, click logs)
│   └── user/                  # User index (users, groups, roles)
├── helper/                    # Cross-cutting utilities (~40+ helpers)
├── crawler/                   # Crawling engine (processor, transformer, service)

        // Verify that multiple components can be retrieved
        final Crawler crawler1 = crawlerContainer.getComponent("crawler");
        final Crawler crawler2 = crawlerContainer.getComponent("crawler");

        // They should be different instances (prototype scope)
        assertNotNull(crawler1);
        assertNotNull(crawler2);
    }

    @Test
    public void test_isLastaCrawlerContainer() {

 */
package org.codelibs.fess.crawler.processor;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;

 */
package org.codelibs.fess.crawler.service;

import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlQueueService;
import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;

     */
    @Min(value = 0)
    @Max(value = 9223372036854775807L)
    @ValidateTypeFailure
    public Long maxAccessCount;

    /**
     * The user agent string to use during crawling.
     */
    @Required
    @Size(max = 200)
    public String userAgent;

    /**
     * The number of crawler threads to use.
     */
    @Required
    @Min(value = 1)