* This job launches a separate crawler process that can crawl web sites, file systems,
 * and data sources based on the configured crawling settings.
 *
 * <p>The job supports selective crawling by specifying configuration IDs for different
 * types of crawlers (web, file, data). It manages the crawler process lifecycle,
 * handles timeout scenarios, and ensures proper cleanup of resources.</p>
 *

 *
 * <p>Example usage:
 * <pre>
 *   Crawler crawler = new Crawler();
 *   crawler.addUrl("http://example.com/");
 *   crawler.execute();
 *   crawler.close();
 * </pre>
 */
public class Crawler implements Runnable, AutoCloseable {

    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /**
     * Service for managing URL queues during crawling.
     */

    /**
     * Add an url pattern as a target.
     *
     * @param urlPattern Regular expression that is crawled
     */
    void addInclude(String urlPattern);

    /**
     * Add an url pattern as a non-target.
     *
     * @param urlPattern Regular expression that is not crawled
     */
    void addExclude(String urlPattern);

    /**
     * Process an url when it's added as a seed url.
     *

 */
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;

```java
// Create multiple crawler instances
Crawler crawler1 = container.getComponent("crawler");
crawler1.setSessionId("session1");
crawler1.addUrl("https://site1.com");

Crawler crawler2 = container.getComponent("crawler");  
crawler2.setSessionId("session2");
crawler2.addUrl("https://site2.com");

// Execute concurrently
crawler1.setBackground(true);
crawler2.setBackground(true);

        mimeType = contentType;
    }

    /**
     * Gets the URL of the crawled resource.
     *
     * @return the URL
     */
    public String getUrl() {
        return url;
    }

    /**
     * Sets the URL of the crawled resource.
     *
     * @param url the URL to set
     */
    public void setUrl(final String url) {
        this.url = url;

import org.codelibs.fess.crawler.entity.Sitemap;
import org.codelibs.fess.crawler.entity.SitemapSet;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.codelibs.fess.crawler.processor.ResponseProcessor;

import jakarta.annotation.Resource;

/**
 * A response processor implementation that handles sitemaps.

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;

import org.codelibs.core.io.CopyUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>
 * FileTransformer stores the content of a crawled resource as a file on the file system.

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;