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");
crawler.crawlerContext.setMaxAccessCount(500);

 * It provides methods to get and set the name and value of the header,
 * as well as a method to validate the header.
 *
 * <p>Example usage:</p>
 * <pre>
 *     RequestHeader header = new RequestHeader("Content-Type", "application/json");
 *     String name = header.getName();
 *     String value = header.getValue();
 *     boolean isValid = header.isValid();
 * </pre>
 *

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

    /** The MIME type for application/octet-stream. */
    protected static final String APPLICATION_OCTET_STREAM = "application/octet-stream";

    /** The property name for access timeout. */
    public static final String ACCESS_TIMEOUT_PROPERTY = "accessTimeout";

 */
package org.codelibs.fess.suggest.constants;

/**
 * This class contains constants for field names used in the Fess Suggest system.
 * These constants represent various field names that are used throughout the application
 * to ensure consistency and avoid hardcoding strings.
 *
 * <ul>
 * <li>{@link #ID} - The unique identifier field.</li>
 * <li>{@link #TEXT} - The text content field.</li>

                    factory.addExtractor("text/plain", tikaExtractor);
                    factory.addExtractor("text/html", tikaExtractor);
                    factory.addExtractor("application/pdf", pdfExtractor);
                });
        pdfExtractor = container.getComponent("pdfExtractor");
        pdfExtractorForPdfPassword = container.getComponent("pdfExtractorForPdfPassword");

"+f}}}return{state:"success",data:b}}n.extend({active:0,lastModified:{},etag:{},ajaxSettings:{url:fc,type:"GET",isLocal:jc.test(ec[1]),global:!0,processData:!0,async:!0,contentType:"application/x-www-form-urlencoded; charset=UTF-8",accepts:{"*":pc,text:"text/plain",html:"text/html",xml:"application/xml, text/xml",json:"application/json, text/javascript"},contents:{xml:/xml/,html:/html/,json:/json/},responseFields:{xml:"responseXML",text:"responseText",json:"responseJSON"},converters:{"* text":String,"text...

 * </p>
 *
 * <pre>
 * {@code
 * try (InputStream in = new FileInputStream("example.pdf")) {
 *     ExtractData extractData = new ExtractorBuilder(crawlerContainer, in, new HashMap<>())
 *         .mimeType("application/pdf")
 *         .filename("example.pdf")
 *         .maxContentLength(1024 * 1024)
 *         .extract();
 *
 *     String content = extractData.getContent();
 *     // Process the extracted content

        // MIME type doesn't match
        ResponseData responseData3 = new ResponseData();
        responseData3.setUrl("https://www.example.com/page");
        responseData3.setMimeType("application/json");
        responseData3.setHttpStatusCode(200);
        assertFalse(rule.match(responseData3));

        // Status code doesn't match
        ResponseData responseData4 = new ResponseData();

import jakarta.annotation.PreDestroy;
import jakarta.annotation.Resource;

/**
 * A container implementation that manages the lifecycle and dependency injection of components
 * in a crawler application. This container supports both singleton and prototype component
 * instantiation patterns.
 *
 * <p>The container provides mechanisms for:
 * <ul>
 *   <li>Registering and retrieving components by name</li>

     */
    protected boolean isHtml(final ResponseData responseData) {
        final String mimeType = responseData.getMimeType();
        if ("text/html".equals(mimeType) || "application/xhtml+xml".equals(mimeType)) {
            return true;
        }
        return false;
    }

    /**
     * Adds a rule for extracting child URLs from HTML tags.
     *