* supports dependency injection via the {@link Resource} annotation.
 * </p>
 */
public class ExtractorFactory {

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

    /** Container for managing crawler components */
    @Resource
    protected CrawlerContainer crawlerContainer;

    @Override
    protected Extractor getExtractor(final ResponseData responseData) {
        final ExtractorFactory extractorFactory = ComponentUtil.getExtractorFactory();
        if (extractorFactory == null) {
            throw new FessSystemException("Could not find extractorFactory.");
        }
        final Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        if (logger.isDebugEnabled()) {

            throw new CrawlerSystemException("LHA archive input stream is null. Cannot extract text from null input.");
        }

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        final StringBuilder buf = new StringBuilder(1000);

        File tempFile = null;
        LhaFile lhaFile = null;
        try {

    }

    /**
     * Returns the ExtractorFactory instance from the CrawlerContainer.
     * @return The ExtractorFactory instance.
     */
    protected ExtractorFactory getExtractorFactory() {
        final ExtractorFactory extractorFactory = crawlerContainer.getComponent("extractorFactory");
        if (extractorFactory == null) {
            throw new CrawlerSystemException("ExtractorFactory is unavailable.");
        }

        final ExtractorFactory extractorFactory = getExtractorFactory();
        return new ExtractData(getTextInternal(in, mimeTypeHelper, extractorFactory));
    }

    /**
     * Returns a text from the input stream.
     *
     * @param in The input stream.
     * @param mimeTypeHelper The mime type helper.
     * @param extractorFactory The extractor factory.
     * @return A text.
     */

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        final String mimeType = mimeTypeHelper.getContentType(null, filename);
        if (mimeType != null) {
            final Extractor extractor = extractorFactory.getExtractor(mimeType);
            if (extractor != null) {

    @Override
    protected Extractor getExtractor(final ResponseData responseData) {
        final ExtractorFactory extractorFactory = ComponentUtil.getExtractorFactory();
        if (extractorFactory == null) {
            throw new FessSystemException("Could not find extractorFactory.");
        }
        Extractor extractor = extractorFactory.getExtractor(responseData.getMimeType());
        if (extractor == null) {

                    factory.addClient("file:.*", container.getComponent("fsClient"));
                })
                .singleton("tikaExtractor", TikaExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);

    public ExtractData getText(final InputStream in, final Map<String, String> params) {
        validateInputStream(in);

        final MimeTypeHelper mimeTypeHelper = getMimeTypeHelper();
        final ExtractorFactory extractorFactory = getExtractorFactory();
        final StringBuilder buf = new StringBuilder(1000);
        int processedEntries = 0;
        int failedEntries = 0;

        try (final ArchiveInputStream ais =

`TikaExtractor` (1000+ formats), `PdfExtractor`, `MsWordExtractor`, `MsExcelExtractor`, `MsPowerPointExtractor`, `ZipExtractor`, `HtmlExtractor`, etc.

**Registration**:
```java
extractorFactory.addExtractor("text/html", htmlExtractor, 2);  // Weight 2
extractorFactory.addExtractor("text/html", tikaExtractor, 1);  // Fallback
```

### Helpers

**RobotsTxtHelper**: RFC 9309 parsing, user-agent matching, crawl-delay, sitemaps