crawler.addExcludeFilter("http://example\\.com/exclude/.*");

        // Initialize the filter
        crawler.urlFilter.init(crawler.getSessionId());

        assertTrue(crawler.urlFilter.match("http://example.com/page"));
        assertFalse(crawler.urlFilter.match("http://example.com/exclude/page"));
    }

    public void test_daemon_mode() throws Exception {

        crawler.crawlerContext.setMaxThreadCheckCount(3);
        crawler.crawlerContext.setMaxAccessCount(maxCount);
        crawler.crawlerContext.setNumOfThread(numOfThread);
        crawler.urlFilter.addInclude(url + ".*");
        crawler.urlFilter.addExclude(url + "/dir1/.*");
        final String sessionId = crawler.execute();
        assertEquals(maxCount, dataService.getCount(sessionId));
        dataService.delete(sessionId);
    }

        String sessionId = "test-session-006";
        urlFilter.init(sessionId);

        urlFilter.addExclude(".*\\.(css|js)$");
        urlFilter.addExclude(".*\\/admin\\/.*");
        urlFilter.addExclude(".*#.*");

        assertTrue(urlFilter.match("https://example.com/page.html"));
        assertFalse(urlFilter.match("https://example.com/style.css"));
        assertFalse(urlFilter.match("https://example.com/script.js"));

    /**
     * Returns the URL filter.
     * @return The UrlFilter instance.
     */
    public UrlFilter getUrlFilter() {
        return urlFilter;
    }

    /**
     * Sets the URL filter.
     * @param urlFilter The UrlFilter instance to set.
     */
    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.

    }

    /**
     * Returns the URL filter.
     * @return The UrlFilter.
     */
    public UrlFilter getUrlFilter() {
        return urlFilter;
    }

    /**
     * Sets the URL filter.
     * @param urlFilter The UrlFilter.
     */
    public void setUrlFilter(final UrlFilter urlFilter) {
        this.urlFilter = urlFilter;
    }

    /**
     * Returns the rule manager.

        crawlerContainer = mock(CrawlerContainer.class);
        logHelper = mock(LogHelper.class);
        clientFactory = mock(CrawlerClientFactory.class);
        urlFilter = mock(UrlFilter.class);
        ruleManager = mock(RuleManager.class);

        crawlerContext.urlFilter = urlFilter;
        crawlerContext.ruleManager = ruleManager;

        crawlerThread.urlQueueService = urlQueueService;
        crawlerThread.dataService = dataService;

import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.service.UrlFilterService;

import jakarta.annotation.Resource;

/**
 * Implementation of the {@link UrlFilter} interface.
 * This class provides functionality to filter URLs based on include and exclude patterns.

                .singleton("urlFilter", UrlFilterImpl.class)//
                .singleton("robotsTxtHelper", RobotsTxtHelper.class)//
                .singleton("httpClient", HcHttpClient.class);
        httpClient = container.getComponent("httpClient");
        urlFilter = container.getComponent("urlFilter");
    }

    public void test_doGet() {

            crawler.addUrl(url);
            crawler.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler.getCrawlerContext().setNumOfThread(numOfThread);
            crawler.urlFilter.addInclude(url + ".*");
            final String sessionId = crawler.execute();
            assertEquals(maxCount, dataService.getCount(sessionId));
            dataService.delete(sessionId);
        } finally {

crawler.crawlerContext.setDefaultIntervalTime(1000); // 1 second
```

### URL Filtering

```java
// Include patterns
crawler.urlFilter.addInclude("https://example.com/.*");
crawler.urlFilter.addInclude(".*\\.pdf$");

// Exclude patterns  
crawler.urlFilter.addExclude(".*\\.js$");
crawler.urlFilter.addExclude(".*login.*");
```

## Supported Protocols and Formats

### Protocols