/**
     * Sets the current {@link CrawlerContext} for the current thread.
     * If the provided {@code crawlerContext} is {@code null}, the context is removed from the thread-local storage.
     * Otherwise, the provided {@code crawlerContext} is set in the thread-local storage.
     *
     * @param crawlerContext the {@link CrawlerContext} to be set for the current thread, or {@code null} to remove the context.
     */

        this.maxAccessCount = maxAccessCount;
    }

    /**
     * Adds sitemaps to the thread-local storage.
     * @param sitemaps An array of sitemap URLs.
     */
    public void addSitemaps(final String[] sitemaps) {
        sitemapsLocal.set(sitemaps);
    }

    /**
     * Removes sitemaps from the thread-local storage and returns them.
     * @return An array of sitemap URLs, or null if none were present.
     */

    }

    /**
     * Gets the local IP address for passive mode FTP.
     *
     * @return The passive local host IP address
     */
    public String getPassiveLocalHost() {
        return passiveLocalHost;
    }

    /**
     * Sets the local IP address for passive mode FTP.
     *
     * @param passiveLocalHost The passive local host IP address
     */

    protected String contentXpath = "//BODY";

    /** Map of metadata field names to their corresponding XPath expressions. */
    protected Map<String, String> metadataXpathMap = new HashMap<>();

    /** Thread-local instance of XPathAPI for thread-safe XPath evaluation. */
    private final ThreadLocal<XPathAPI> xpathAPI = new ThreadLocal<>();

    /**
     * Creates a new HtmlExtractor instance.
     */
    public HtmlExtractor() {

            }
        }
    }

    /**
     * Polls the next URL queue entry for the specified session.
     * This method manages local caches and fetches from OpenSearch when needed.
     *
     * @param sessionId The session ID.
     * @return The next URL queue entry, or null if none available.
     */
    @Override

import org.codelibs.fess.crawler.extractor.Extractor;
import org.jodconverter.core.office.OfficeException;
import org.jodconverter.core.office.OfficeManager;
import org.jodconverter.local.LocalConverter;

import jakarta.annotation.PostConstruct;
import jakarta.annotation.PreDestroy;

/**
 * Extracts text content from various document formats using JODConverter.
 */

crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols
- **HTTP/HTTPS**: Full web crawling support with cookies, authentication, redirects
- **File System**: Local and network file system access
- **FTP**: FTP server crawling with authentication
- **SMB/CIFS**: Windows network shares
- **Storage**: Cloud storage systems (MinIO, S3-compatible)

### Content Formats

        urlFilter.processUrl("https://example.com/");
        urlFilter.processUrl("http://test.com/path/to/page");
        urlFilter.processUrl("ftp://files.server.com/documents/");
        urlFilter.processUrl("file:///local/path/file.txt");

        // Should complete without errors
        assertNotNull(urlFilter);
    }

    /**
     * Test processUrl with null URL
     */
    public void test_processUrl_nullUrl() {

			<groupId>jp.gr.java_conf.dangan</groupId>
			<artifactId>jlha</artifactId>
			<version>${jlha.version}</version>
		</dependency>
		<dependency>
			<groupId>org.jodconverter</groupId>
			<artifactId>jodconverter-local</artifactId>
			<version>${jodconverter.version}</version>
		</dependency>
		<dependency>
			<groupId>com.sun.mail</groupId>
			<artifactId>jakarta.mail</artifactId>
			<version>${jakarta.mail.version}</version>

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;
import org.jodconverter.local.office.LocalOfficeManager;

/**
 * @author shinsuke
 *
 */
public class JodExtractorTest extends PlainTestCase {
    private static final Logger logger = LogManager.getLogger(JodExtractorTest.class);