CRAWLER - Code Search

src/main/resources/mail/crawler.dfmail

/*
 [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 ---

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Wed Jan 15 22:05:20 UTC 2020

- 1K bytes

- Viewed (0)

github.com/codelibs/fess

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>
		<postConstruct name="addRule">

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Thu Jun 04 08:42:49 UTC 2020

- 4.6K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/resources/fess_indices/fess_config.scheduled_job/scheduled_job.bulk

{"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"}}

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Thu Dec 02 13:14:56 UTC 2021

- 4.2K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/crawler/processor/FessResponseProcessor.java

 */
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;

Registered: Mon Oct 28 08:04:08 UTC 2024

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

- 2.3K bytes

- Viewed (0)

github.com/codelibs/fess

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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.client.CrawlerClientFactory;
import org.codelibs.fess.crawler.client.ftp.FtpClient;
import org.codelibs.fess.crawler.client.http.HcHttpClient;
import org.codelibs.fess.crawler.client.smb.SmbClient;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Thu Oct 24 13:01:38 UTC 2024

- 5.5K bytes

- Viewed (0)

github.com/codelibs/fess

README.md

* [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web Framework
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Job Scheduler
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web Crawler

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Sat Oct 12 07:19:47 UTC 2024

- 7.3K bytes

- Viewed (0)

github.com/codelibs/fess

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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.AccessResult;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.util.CrawlingParameterUtil;
import org.codelibs.fess.crawler.util.FieldConfigs;
import org.codelibs.fess.mylasta.direction.FessConfig;

Registered: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Fri Oct 11 21:11:58 UTC 2024

- 9.5K bytes

- Viewed (0)

github.com/codelibs/fess

src/test/resources/plugin/repo1/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: Mon Oct 28 08:04:08 UTC 2024

- Last Modified: Tue Aug 13 07:34:14 UTC 2019

- 3.3K 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: Mon Oct 28 08:04:08 UTC 2024

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

- 6.2K 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: Mon Oct 28 08:04:08 UTC 2024

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

- 381 bytes

- Viewed (0)

Search Options