public static final String KEEP_ORIGINAL_BODY = "keep.original.body";
            public static final String CLEANUP_ALL = "cleanup.all";
            public static final String CLEANUP_URL_FILTERS = "cleanup.urlFilters";
            public static final String JCIFS_PREFIX = "jcifs.";
            public static final String HTML_CANONICAL_XPATH = "html.canonical.xpath";

        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);
    }

    /**
     * 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.

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

            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 {

                try {
                    urlFilterService.delete(sid);
                } catch (final Exception e) {
                    logger.warn("Failed to delete UrlFilter: sessionId={}", sid);
                }
            }

            final DuplicateHostHelper duplicateHostHelper = ComponentUtil.getDuplicateHostHelper();

            // set urls

<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/container.xml" />

	<component name="urlFilter"
		class="org.codelibs.fess.crawler.filter.impl.UrlFilterImpl" instance="prototype">
	</component>

        final Set<String> urlSet = new HashSet<>();
        final List<UrlQueue<?>> childList = childUrlList.stream()
                .filter(d -> StringUtil.isNotBlank(d.getUrl()) && urlSet.add(d.getUrl()) && crawlerContext.urlFilter.match(d.getUrl()))
                .map(d -> {
                    final UrlQueue<?> uq = crawlerContainer.getComponent("urlQueue");
                    uq.setCreateTime(SystemUtil.currentTimeMillis());

     */
    private void deleteBySessionId(final String sessionId) {
        try {
            urlFilterService.delete(sessionId);
        } catch (final Exception e) {
            logger.warn("Failed to delete UrlFilter: sessionId={}", sessionId, e);
        }
        try {
            urlQueueService.delete(sessionId);
        } catch (final Exception e) {