/**
     * 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.
     *

});

Crawler crawler = container.getComponent("crawler");
crawler.addUrl("https://example.com");
crawler.crawlerContext.setMaxAccessCount(500);
String sessionId = crawler.execute();
```

### Background Crawling

```java
// Configure for background execution
crawler.setBackground(true);
String sessionId = crawler.execute();

// Check crawling status

 *
 * <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.
     */

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.

        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;

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * Exception thrown during the extraction process in the crawler.
 * This exception indicates a failure or error that occurred while extracting content from a crawled resource.
 * It extends {@link org.codelibs.fess.crawler.exception.CrawlerSystemException} and provides constructors

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.apache.tika.metadata.Message;
import org.apache.tika.metadata.TIFF;
import org.apache.tika.metadata.TikaCoreProperties;
import org.apache.tika.metadata.TikaMimeKeys;

/**
 * Represents extracted data from a crawled resource, including content and metadata.
 */
public class ExtractData
        implements TikaCoreProperties, CreativeCommons, Geographic, HttpHeaders, Message, ClimateForcast, TIFF, TikaMimeKeys, Serializable {

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.entity;

/**
 * Implementation of the {@link UrlQueue} interface.
 * This class represents a URL to be crawled, storing its ID, session ID,
 * HTTP method, URL, metadata, encoding, parent URL, depth, last modified time,
 * creation time, and weight.
 *

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;