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

/*
 [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 ---

│   ├── 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)

 */
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;

    /** Additional configuration parameters for the file crawler. */
    @CustomSize(maxKey = "form.admin.max.input.size")
    public String configParameter;

    /** The maximum crawling depth (0 to 2147483647, 0 means unlimited). */
    @Min(value = 0)
    @Max(value = 2147483647)
    @ValidateTypeFailure
    public Integer depth;

    /** The maximum number of documents to access during crawling (0 means unlimited). */
    @Min(value = 0)

     */
    @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)

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

    /** Configuration ID */
    public String id;

    /** Configuration name */
    public String name;

    /** File system paths to crawl */
    public String paths;

    /** Number of threads for crawling */
    public String numOfThread;

    /** Interval time between crawling operations */
    public String intervalTime;

    /** Boost value for search ranking */
    public String boost;

import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.exception.MultipleCrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.LogHelperImpl;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;