LhaExtractor lhaExtractor = container.getComponent("lhaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/x-lha", lhaExtractor);

                })//
        ;

        lhaExtractor = container.getComponent("lhaExtractor");

    }

                    ZipExtractor zipExtractor = container.getComponent("zipExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);

                })//
        ;

        zipExtractor = container.getComponent("zipExtractor");
    }

        ExtractorFactory extractorFactory = container.getComponent("extractorFactory");
        TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
        extractorFactory.addExtractor("text/plain", tikaExtractor);
        extractorFactory.addExtractor("text/html", tikaExtractor);
    }

    public void test_name() {
        assertEquals("textTransformer", textTransformer.getName());
    }

     */
    public void addExtractor(final List<String> keyList, final Extractor extractor) {
        if (keyList == null || keyList.isEmpty()) {
            throw new CrawlerSystemException("The key list is empty.");
        }
        keyList.stream().distinct().forEach(key -> addExtractor(key, extractor));
    }

    /**
     * Retrieves an extractor for the specified key.

                    TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/tar", tarExtractor);
                })//
        ;

        tarExtractor = container.getComponent("tarExtractor");
    }

                    final TarExtractor tarExtractor = container.getComponent("tarExtractor");
                    factory.addExtractor("text/plain", textExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/zip", zipExtractor);
                    factory.addExtractor("application/x-tar", tarExtractor);
                });

`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

// 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"));
});

Crawler crawler = container.getComponent("crawler");
crawler.addUrl("https://example.com");

		<postConstruct name="addExtractor">
			<arg>[
				"application/pdf"
				]</arg>
			<arg>pdfExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"application/x-lha",
				"application/x-lharc"
				]</arg>
			<arg>lhaExtractor</arg>
		</postConstruct>
		<postConstruct name="addExtractor">
			<arg>[
				"message/rfc822"
				]</arg>
			<arg>emlExtractor</arg>

                    TikaExtractor tikaExtractor = container.getComponent("tikaExtractor");
                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                })//
                .singleton("httpClient", HcHttpClient.class)//