* </pre>
 */
public class Crawler {

    /**
     * Creates a new instance of Crawler.
     */
    public Crawler() {
        // Default constructor
    }

    /** Logger instance for this class. */
    private static final Logger logger = LogManager.getLogger(Crawler.class);

    /** Thread name for web and file system crawling process. */

    OkHttpClient client = new OkHttpClient.Builder()
        .cache(cache)
        .callTimeout(5, TimeUnit.SECONDS)
        .build();

    Crawler crawler = new Crawler(client, queueLimit, hostLimit);
    crawler.queue.add(HttpUrl.get(args[1]));
    crawler.parallelDrainQueue(threadCount);
  }

/*
 [Crawler Notification]
 Crawler notification mail.
*/
subject: [FESS] Crawler completed: /*pmb.hostname*/
>>>
--- Server Info ---
Host Name: /*pmb.hostname:orElse('Unknown')*/
Job Name: /*pmb.jobname:orElse('Unknown')*/

--- Web/FileSystem Crawler ---
Start Time: /*pmb.webFsCrawlStartTime:orElse('-')*/
End Time:   /*pmb.webFsCrawlEndTime:orElse('-')*/
Exec Time:  /*pmb.webFsCrawlExecTime:orElse('-')*/ ms

--- Web/FileSystem Indexer ---

        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";
        options.fileConfigIds = "file1";

        int result = crawler.doCrawl(options);
        assertEquals(Constants.EXIT_OK, result);
    }

    public void test_doCrawl_withDataConfigIds() {
        Crawler.Options options = new Crawler.Options();
        options.sessionId = "test-session";

 */
package org.codelibs.fess.crawler.processor;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.processor.impl.DefaultResponseProcessor;

 */
package org.codelibs.fess.crawler.service;

import java.util.List;
import java.util.Map;

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.OpenSearchUrlQueue;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlQueueService;
import org.codelibs.fess.crawler.util.OpenSearchCrawlerConfig;

import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.CrawlerContext;
import org.codelibs.fess.crawler.CrawlerStatus;
import org.codelibs.fess.crawler.interval.FessIntervalController;
import org.codelibs.fess.crawler.service.impl.OpenSearchDataService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlFilterService;
import org.codelibs.fess.crawler.service.impl.OpenSearchUrlQueueService;

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

	<component name="ruleManager" class="org.codelibs.fess.crawler.rule.impl.RuleManagerImpl" instance="prototype">
		<postConstruct name="addRule">
			<arg>sitemapsRule</arg>
		</postConstruct>
		<postConstruct name="addRule">

{"index":{"_index":"fess_config.scheduled_job","_id":"default_crawler"}}
{"name":"Default Crawler","target":"all","cronExpression":"0 0 * * *","scriptType":"groovy","scriptData":"return container.getComponent(\"crawlJob\").logLevel(\"info\").gcLogging().execute(executor);","jobLogging":true,"crawler":true,"available":true,"sortOrder":1,"createdBy":"system","createdTime":0,"updatedBy":"system","updatedTime":0}
{"index":{"_index":"fess_config.scheduled_job","_id":"suggest_indexer"}}

            <td>Fri Jan 13 13:53:34 UTC 2017</td>
            <td align="right">
                              &nbsp;
                          </td>
            <td></td>
          </tr>
                  <tr>
            <td><a href="https://oss.sonatype.org/content/repositories/snapshots/org/codelibs/fess/fess-crawler-db-mysql/">fess-crawler-db-mysql/</a></td>