import org.codelibs.fess.app.service.FailureUrlService;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.log.LogType;
import org.codelibs.fess.exception.ContainerNotAvailableException;

### Key File Locations

**Core**: `fess-crawler/src/main/java/org/codelibs/fess/crawler/`
- `Crawler.java`, `CrawlerContext.java`, `CrawlerThread.java`

**Clients**: `fess-crawler/src/main/java/org/codelibs/fess/crawler/client/`
- `http/HcHttpClient.java`, `fs/FileSystemClient.java`, `storage/StorageClient.java`

**DI Config**: `fess-crawler-lasta/src/main/resources/crawler.xml`

### Exception Hierarchy

```

 */
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)

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.OpenSearchAccessException;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;

labels.crawling_info_CrawlerStartTime=Crawler-Startzeit
labels.crawling_info_CrawlerEndTime=Crawler-Endzeit
labels.crawling_info_CrawlerExecTime=Crawler-Ausführungszeit
labels.crawling_info_CrawlerStatus=Crawler-Status
labels.crawling_info_WebFsCrawlExecTime=Crawl-Ausführungszeit (Web/Datei)
labels.crawling_info_WebFsCrawlStartTime=Crawl-Startzeit (Web/Datei)
labels.crawling_info_WebFsCrawlEndTime=Crawl-Endzeit (Web/Datei)

     * 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.

        return redirectWith(getClass(), moreUrl("crawlingConfigForm"));
    }

    /**
     * Creates a crawling configuration and proceeds to the start crawling form.
     *
     * @param form the form containing crawling configuration data
     * @return HTML response redirecting to the start crawling form
     */
    @Execute
    @Secured({ ROLE })

    /** 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)

import java.util.Map;
import java.util.Set;

import org.codelibs.core.exception.IORuntimeException;
import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.Constants;

/**
 * Represents the response data obtained from a crawled resource.
 * This class encapsulates various details of an HTTP response, including
 * status code, content type, content length, and the response body.