<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<include path="crawler/transformer_basic.xml"/>

 */
package org.codelibs.fess.crawler;

import java.io.File;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;

<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN" 
	"http://dbflute.org/meta/lastadi10.dtd">
<components namespace="fessCrawler">
	<component name="esClient"
		class="org.codelibs.fess.crawler.client.FesenClient">
	</component>

import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.ThreadUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExecutionTimeoutException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
 * Extracts text content by executing an external command.
 */

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;

});

Crawler crawler = container.getComponent("crawler");
crawler.addUrl("https://example.com");
crawler.crawlerContext.setMaxAccessCount(500);
String sessionId = crawler.execute();
```

### Background Crawling

```java
// Configure for background execution
crawler.setBackground(true);
String sessionId = crawler.execute();

// Check crawling status

/target/
/.settings/
/fess-crawler*/target/
/fess-crawler*/bin/
/fess-crawler*/mydbflute/
/fess-crawler*/.project
/fess-crawler*/.classpath
/fess-crawler*/.settings/
/fess-crawler*/dependency-reduced-pom.xml
/fess-crawler*/dbflute_crawler/log/*.log
/fess-crawler*/dbflute_crawler/schema/project-schema-robot.xml
/fess-crawler/phantomjsdriver.log
.project
.idea
*.iml
/.vscode

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

import java.util.Map;

import org.codelibs.core.lang.ThreadUtil;

/**
 * Default implementation of the IntervalController.
 * This class provides a default way to manage delays between crawler operations.
 * It allows setting delays before processing, after processing, when no URLs are in the queue,

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

import java.util.List;

import org.codelibs.fess.crawler.entity.UrlQueue;

/**
 * Service interface for managing URL queues.
 * Provides methods for adding, retrieving, and managing URLs within a crawling session.
 *

        assertFalse(robotsTxt.allows("/aaa", "Crawler"));
        assertTrue(robotsTxt.allows("/bbb", "Crawler"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler"));
        assertTrue(robotsTxt.allows("/ddd", "Crawler"));
        assertTrue(robotsTxt.allows("/aaa", "Crawler/1.0"));
        assertFalse(robotsTxt.allows("/bbb", "Crawler/1.0"));
        assertTrue(robotsTxt.allows("/ccc", "Crawler/1.0"));