crawler - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/Crawler.java

 */
package org.codelibs.fess.crawler;

import java.text.SimpleDateFormat;
import java.util.Date;
import java.util.Locale;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.UrlQueue;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:47:32 UTC 2024

- 7.9K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/exec/Crawler.java

            if (logger.isDebugEnabled()) {
                logger.debug("Crawler is stopped.", e);
            } else if (logger.isInfoEnabled()) {
                logger.info("Crawler is stopped.");
            }
            exitCode = Constants.EXIT_FAIL;
        } catch (final Throwable t) {
            logger.error("Crawler does not work correctly.", t);
            exitCode = Constants.EXIT_FAIL;
        } finally {

Registered: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Fri Oct 11 21:20:39 UTC 2024

- 24K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            Thread.sleep(100);

            final Crawler crawler2 = getComponent(Crawler.class);
            crawler2.setBackground(true);
            ((UrlFilterImpl) crawler2.urlFilter).setIncludeFilteringPattern("$1$2$3.*");
            crawler2.addUrl(url2);

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Nov 07 04:44:10 UTC 2024

- 7.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

            crawler1.addUrl(url1);
            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = crawlerContainer.getComponent("crawler");
            crawler2.setSessionId(crawler2.getSessionId() + "2");
            crawler2.setBackground(true);

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:47:32 UTC 2024

- 11.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

            crawler1.addUrl(url1);
            crawler1.getCrawlerContext().setMaxAccessCount(maxCount);
            crawler1.getCrawlerContext().setNumOfThread(numOfThread);

            final Crawler crawler2 = container.getComponent("crawler");
            crawler2.setSessionId(crawler2.getSessionId() + "2");
            crawler2.setBackground(true);

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 18K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/client/fs/FileSystemClient.java

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.client.AbstractCrawlerClient;
import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:47:32 UTC 2024

- 11.8K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/service/impl/DataServiceImpl.java

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

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

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.AccessResultImpl;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:47:32 UTC 2024

- 5.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/test/resources/plugin/repo3/index.html

<a href="fess-crawler-es/" title="fess-crawler-es/">fess-crawler-es/</a>                                                 -         -      
<a href="fess-crawler-lasta/" title="fess-crawler-lasta/">fess-crawler-lasta/</a>                                              -         -

Registered: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Mon Jun 17 13:30:41 UTC 2024

- 6.2K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/service/impl/UrlQueueServiceImpl.java

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

import java.util.ArrayList;
import java.util.List;
import java.util.Map;
import java.util.Queue;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.core.lang.SystemUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultImpl;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:47:32 UTC 2024

- 7.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/RuleManagerImpl.java

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

import java.util.ArrayList;
import java.util.List;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

/**
 * @author shinsuke
 *
 */
public class RuleManagerImpl implements RuleManager {

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 2.2K bytes

- Viewed (0)

Search Options