import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.CrawlerClient;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

 */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.IOException;
import java.io.InputStream;
import java.util.Map;

import org.apache.poi.hpbf.extractor.PublisherTextExtractor;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Gets a text from . file.

import org.codelibs.core.lang.SystemUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;

  -F "file=@documents.bulk"
```

### 4. Direct Crawler Configuration

Instead of importing documents, configure Fess to crawl your data sources:

**Web Crawling**:
- **Admin Path**: Crawler > Web
- **Supports**: HTTP/HTTPS websites
- **Features**: JavaScript rendering, authentication, custom headers

**File Crawling**:
- **Admin Path**: Crawler > File
- **Supports**: SMB, FTP, local file systems

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.interval;

/**
 * The {@code IntervalController} interface defines methods for controlling
 * the delay intervals in a web crawler. It includes constants representing
 * different types of processing states and a method to introduce a delay
 * based on the type of processing.
 * <p>

 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.container;

import org.codelibs.core.lang.StringUtil;

/**
 * The CrawlerContainer interface provides methods for managing components
 * within a crawler container. It includes methods to retrieve components,
 * check availability, and destroy the container. Additionally, it provides

        return id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#setId(IDTYPE)
     */
    @Override
    public void setId(final IDTYPE id) {
        this.id = id;
    }

    /*
     * (non-Javadoc)
     *
     * @see org.codelibs.fess.crawler.entity.UrlQueue#getSessionId()
     */
    @Override
    public String getSessionId() {

import org.codelibs.fess.crawler.filter.UrlFilter;
import org.codelibs.fess.crawler.helper.LogHelper;
import org.codelibs.fess.crawler.interval.IntervalController;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.exception;

/**
 * The crawler login failure exception.
 * This exception is thrown when the crawler fails to login to a website.
 *
 */
public class CrawlerLoginFailureException extends CrawlerSystemException {
    private static final long serialVersionUID = 1L;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.entity.UrlQueueImpl;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;