crawlers - Code Search

fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java

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

import java.io.IOException;
import java.io.InputStream;

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;

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

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

- 4.5K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/helper/impl/LogHelperImpl.java

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

import java.util.Set;

import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.LogHelper;
import org.codelibs.fess.crawler.log.LogType;
import org.slf4j.Logger;

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

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

- 10.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/FileTransformerTest.java

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

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

import org.codelibs.core.io.FileUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

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

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

- 7.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/rule.xml

<!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>

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

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 1.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/es/config/cbean/cq/bs/BsScheduledJobCQ.java

    }

    public void setCrawler_Equal(Boolean crawler) {
        setCrawler_Term(crawler, null);
    }

    public void setCrawler_Equal(Boolean crawler, ConditionOptionCall<TermQueryBuilder> opLambda) {
        setCrawler_Term(crawler, opLambda);
    }

    public void setCrawler_Term(Boolean crawler) {
        setCrawler_Term(crawler, null);
    }

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

- Last Modified: Thu Feb 22 01:37:57 UTC 2024

- 98.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

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

import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
import java.util.Set;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.regex.Pattern;
import java.util.stream.Collectors;

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

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

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

- 6.3K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/resources/crawler/interval.xml

<!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="intervalController"
		class="org.codelibs.fess.crawler.interval.FessIntervalController"
		instance="prototype">
	</component>

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

- Last Modified: Sun Oct 11 06:51:14 UTC 2015

- 381 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/filter.xml

<!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>

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

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 364 bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/transformer/FessStandardTransformer.java

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.exception.FessSystemException;

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

- Last Modified: Thu Feb 22 01:53:18 UTC 2024

- 2.4K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/es/config/exentity/DataConfig.java

import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.ftp.FtpAuthentication;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.http.Authentication;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.client.http.form.FormScheme;
import org.codelibs.fess.crawler.client.http.impl.AuthenticationImpl;

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

- Last Modified: Sat Oct 12 01:54:15 UTC 2024

- 18.5K bytes

- Viewed (0)

Search Options