crawlers - Code Search

fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/impl/UrlFilterImplTest.java

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

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.impl.DataServiceImpl;
import org.codelibs.fess.crawler.service.impl.UrlFilterServiceImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 6.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/Transformer.java

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

import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;

/**
 * The Transformer interface defines methods for transforming response data

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sat Mar 15 06:52:00 UTC 2025

- 1.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/client/smb1/SmbClient.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 Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Sep 18 09:30:45 UTC 2025

- 23K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/resources/crawler/transformer.xml

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

	<component name="fessXpathTransformer" class="org.codelibs.fess.crawler.transformer.FessXpathTransformer" instance="singleton">
		<property name="name">"fessXpathTransformer"</property>
		<property name="featureMap">defaultFeatureMap</property>

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Fri Dec 20 13:14:54 UTC 2024

- 1.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/main/resources/crawler/transformer_basic.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="binaryTransformer"
		class="org.codelibs.fess.crawler.transformer.impl.BinaryTransformer"
		instance="singleton">
		<property name="name">"binaryTransformer"</property>
	</component>

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Sep 30 21:21:24 UTC 2018

- 3.3K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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

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

import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.processor.ResponseProcessor;
import org.codelibs.fess.crawler.rule.Rule;
import org.codelibs.fess.crawler.rule.RuleManager;

import jakarta.annotation.Resource;

/**

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Wed Sep 03 14:42:53 UTC 2025

- 2.8K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/mylasta/direction/FessConfig.java

    /** The key of the configuration. e.g. UTF-8 */
    String CRAWLER_DOCUMENT_SITE_ENCODING = "crawler.document.site.encoding";

    /** The key of the configuration. e.g. unknown */
    String CRAWLER_DOCUMENT_UNKNOWN_HOSTNAME = "crawler.document.unknown.hostname";

    /** The key of the configuration. e.g. false */

Registered: Thu Sep 04 12:52:25 UTC 2025

- Last Modified: Thu Jul 17 08:28:31 UTC 2025

- 525.6K bytes

- Viewed (2)

github.com/codelibs/fess-crawler

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

import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.MaxLengthExceededException;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;

/**

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Thu Aug 07 02:55:08 UTC 2025

- 3.7K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractor.java

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.ExtractException;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.crawler.helper.MimeTypeHelper;

import jakarta.mail.Address;
import jakarta.mail.BodyPart;

Registered: Sun Sep 21 03:50:09 UTC 2025

- Last Modified: Sun Jul 06 02:13:03 UTC 2025

- 12.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/resources/org/codelibs/fess/crawler/helper/robots.txt

User-agent: *
Disallow: /private/
Disallow: /help        # disallows /help.html, /help/index.html, etc.
Allow: /help/faq.html
Crawl-delay: 3

User-agent: Crawler
Disallow: /aaa

User-agent: Crawler/1.0
Disallow: /bbb

User-agent: Crawler/2.0
Disallow: /ccc

User-agent: Hoge Crawler
Disallow: /ddd

sitemap: http://www.example.com/sitmap.xml

Registered: Sun Sep 21 03:50:09 UTC 2025

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

- 566 bytes

- Viewed (0)

Search Options