/** XPath expression for extracting robots content from meta tags */
    private static final String META_NAME_ROBOTS_CONTENT = "//META[@name=\"robots\" or @name=\"ROBOTS\"]/@content";

    /** Robots tag value indicating no indexing or following */
    private static final String ROBOTS_TAG_NONE = "none";

    /** Robots tag value indicating no indexing */

- **Testing**: JUnit 4, UTFlute, Mockito 5.7.0
- **Storage**: In-memory (default), OpenSearch (optional)

### Protocols

- **HTTP/HTTPS**: Full crawling, cookies, auth, robots.txt
- **File**: Local/network file systems
- **FTP**: With authentication
- **SMB/CIFS**: Windows shares (SMB1/SMB2+)
- **Storage**: MinIO/S3-compatible

### Content Formats

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

    public void testParse() {
        RobotsTxt robotsTxt;
        final InputStream in = RobotsTxtHelperTest.class.getResourceAsStream("robots.txt");
        try {
            robotsTxt = robotsTxtHelper.parse(in);
        } finally {
            CloseableUtil.closeQuietly(in);
        }

import java.util.Map;
import java.util.regex.Pattern;

import org.codelibs.core.lang.StringUtil;

/**
 * Represents a robots.txt file parser and handler.
 * This class manages the rules defined in a robots.txt file, including user agent directives,
 * allowed/disallowed paths, crawl delays, and sitemap URLs.
 *
 * <p>The robots.txt protocol is implemented according to the standard specification,

 * </ul>
 *
 * <p>References:</p>
 * <ul>
 * <li><a href="https://datatracker.ietf.org/doc/html/rfc9309">RFC 9309 - Robots Exclusion Protocol</a></li>
 * <li><a href="https://developers.google.com/search/docs/crawling-indexing/robots/robots_txt">
 * Google's robots.txt Specification</a></li>
 * </ul>
 *
 * @author bowez
 * @author shinsuke
 *
 */
public class RobotsTxtHelper {

            httpClientPropertyMap.put(name, value);
        }
    }

    /**
     * Processes robots.txt for the given URL.
     * This method fetches and parses the robots.txt file to extract disallow/allow rules
     * and sitemap information.
     *
     * @param url The URL to process robots.txt for
     */
    protected void processRobotsTxt(final String url) {
        if (StringUtil.isBlank(url)) {

        }
        if (logger.isDebugEnabled()) {
            logger.debug("Loaded ScriptEngine: {}", name);
        }
        scriptEngineMap.put(name.toLowerCase(Locale.ROOT), scriptEngine);
        scriptEngineMap.put(scriptEngine.getClass().getSimpleName().toLowerCase(Locale.ROOT), scriptEngine);
    }

    /**
     * Gets a script engine.
     * @param name The name of the script engine.
     * @return The script engine.
     */

# Test robots.txt for wildcard (*) and end-of-path ($) support
# Based on RFC 9309 specification

# Test wildcard patterns
User-agent: WildcardBot
Disallow: /*.pdf$
Disallow: /admin/*.php
Disallow: /*/private/
Allow: /public/*.html

# Test end-of-path ($) patterns
User-agent: EndPathBot
Disallow: /fish$
Disallow: /temp$
Allow: /fishing

# Test complex patterns
User-agent: ComplexBot
Disallow: /
Allow: /$

    /** The key of the configuration. e.g. [Test] */
    String MAIL_SUBJECT_TEST_PREFIX = "mail.subject.test.prefix";

    /** The key of the configuration. e.g. root@localhost */
    String MAIL_RETURN_PATH = "mail.return.path";

    /**
     * Get the value of property as {@link String}.
     * @param propertyKey The key of the property. (NotNull)

     * Retrieves the current user's locale from the request manager.
     *
     * @return the user's locale, or Locale.ROOT if not available
     */
    private static Locale getUserLocale() {
        final Locale locale = ComponentUtil.getRequestManager().getUserLocale();
        if (locale == null) {
            return Locale.ROOT;
        }
        return locale;
    }

    /**