import com.google.common.base.Charsets;

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

/**
 * Extract a text by using external http server.
 */
public class ApiExtractor extends AbstractExtractor {

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

    /** The URL of the API endpoint. */
    protected String url;

    /** The access timeout in seconds. */

import org.codelibs.fess.crawler.util.IgnoreCloseInputStream;

import jakarta.annotation.Resource;

/**
 * Extracts text content from TAR archives.
 */
public class TarExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(TarExtractor.class);

    /**
     * The archive stream factory.
     */
    @Resource
    protected ArchiveStreamFactory archiveStreamFactory;

 * The extractor first tries to match against the URL, then falls back to the resource name if available.
 *
 * @author shinsuke
 */
public abstract class PasswordBasedExtractor extends AbstractExtractor {

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(PasswordBasedExtractor.class);

    /** Map of regex patterns to passwords for static password configuration. */

import jakarta.mail.internet.MimeMessage;
import jakarta.mail.internet.MimeUtility;

/**
 * Gets a text from .eml file.
 *
 * @author shinsuke
 *
 */
public class EmlExtractor extends AbstractExtractor {
    /** Array of day of week abbreviations used for parsing received dates */
    private static final String[] DAY_OF_WEEK = { "Mon", "Tue", "Wed", "Thu", "Fri", "Sat", "Sun" };

    /** Logger instance for this class */

 * It handles encoding detection, HTML entity unescaping, and tag-based content extraction.
 *
 */
public abstract class AbstractXmlExtractor extends AbstractExtractor {

    /**
     * Logger for this class.
     */
    protected static final Logger logger = LogManager.getLogger(AbstractXmlExtractor.class);

    /**
     * UTF-7 Byte Order Mark definition.
     */

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

/**
 * Extracts text content from various document formats using JODConverter.
 */
public class JodExtractor extends AbstractExtractor {
    /** Logger for this class. */
    private static final Logger logger = LogManager.getLogger(JodExtractor.class);

    /** Office manager for document conversion. */
    protected OfficeManager officeManager;

import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content by executing an external command.
 */
public class CommandExtractor extends AbstractExtractor {
    private static final Logger logger = LogManager.getLogger(CommandExtractor.class);

    /** The encoding for the output. */
    protected String outputEncoding = Constants.UTF_8;

}

// Wait for completion
crawler.awaitTermination();
System.out.println("Crawling completed");
```

### Custom Content Extractor

```java
public class CustomExtractor extends AbstractExtractor {
    @Override
    public ExtractData getText(final InputStream inputStream, final Map<String, String> params) {
        // Custom extraction logic
        ExtractData extractData = new ExtractData();