`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

                .singleton("zipExtractor", ZipExtractor.class)
                .singleton("tarExtractor", TarExtractor.class)
                .<ExtractorFactory> singleton("extractorFactory", ExtractorFactory.class, factory -> {
                    final TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");

    filter.addExclude(".*\\.(css|js|png|jpg|gif)$");
});

// Configure content extraction
container.singleton("tikaExtractor", TikaExtractor.class);
container.singleton("extractorFactory", ExtractorFactory.class, factory -> {
    factory.addExtractor("text/html", container.getComponent("tikaExtractor"));
    factory.addExtractor("application/pdf", container.getComponent("tikaExtractor"));
});

import org.codelibs.fess.crawler.client.CrawlerClientCreator;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.OpenSearchAccessResult;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.dict.DictionaryManager;
import org.codelibs.fess.ds.DataStoreFactory;
import org.codelibs.fess.exception.ContainerNotAvailableException;

		<property name="officeManager">
			@org.jodconverter.local.office.LocalOfficeManager@.builder().portNumbers(12002).build()
		</property>
	</component>
	-->

	<component name="extractorFactory"
		class="org.codelibs.fess.crawler.extractor.ExtractorFactory">
		<postConstruct name="addExtractor">
			<arg>[
				"application/xml",
				"application/xhtml+xml",
				"application/rdf+xml",
				"application/x-freemind",
				"text/xml"