CRAWLER - Code Search

samples/crawler/src/main/java/okhttp3/sample/Crawler.java

    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);
  }

Created: Fri Apr 03 11:42:14 GMT 2026

- Last Modified: Wed Jul 23 00:58:06 GMT 2025

- 5K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

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

<components namespace="fessCrawler">
	<include path="crawler/container.xml"/>
	<include path="crawler/client.xml"/>
	<include path="crawler/rule.xml"/>
	<include path="crawler/filter.xml"/>
	<include path="crawler/interval.xml"/>
	<include path="crawler/extractor.xml"/>
	<include path="crawler/mimetype.xml"/>
	<include path="crawler/encoding.xml"/>
	<include path="crawler/urlconverter.xml"/>
	<include path="crawler/log.xml"/>

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Tue Nov 28 13:40:25 GMT 2017

- 1.7K bytes

- Click Count (0)

github.com/codelibs/fess

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 ---

Created: Tue Mar 31 13:07:34 GMT 2026

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

- 1K bytes

- Click Count (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"}}

Created: Tue Mar 31 13:07:34 GMT 2026

- Last Modified: Thu Mar 26 02:24:08 GMT 2026

- 5K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

CLAUDE.md

**DI Config**: `fess-crawler-lasta/src/main/resources/`
- `crawler.xml` (root), `crawler/client.xml`, `crawler/extractor.xml`, `crawler/rule.xml`, `crawler/transformer.xml`, `crawler/transformer_basic.xml`
- `crawler/mimetype.xml`, `crawler/encoding.xml`, `crawler/robotstxt.xml`, `crawler/sitemaps.xml`

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Thu Mar 12 03:39:20 GMT 2026

- 8.1K bytes

- Click Count (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>                                              -         -

Created: Tue Mar 31 13:07:34 GMT 2026

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

- 3.3K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler-opensearch/src/main/resources/crawler_opensearch.xml

<components namespace="fessCrawler">
    <include path="crawler/container.xml"/>
    <include path="crawler/client.xml"/>
    <include path="crawler/rule.xml"/>
    <include path="crawler/filter.xml"/>
    <include path="crawler/interval.xml"/>
    <include path="crawler/extractor.xml"/>
    <include path="crawler/mimetype.xml"/>
    <include path="crawler/encoding.xml"/>
    <include path="crawler/urlconverter.xml"/>
    <include path="crawler/log.xml"/>

Created: Sun Apr 12 03:50:13 GMT 2026

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

- 2.2K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/container/LastaCrawlerContainerTest.java

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

import org.codelibs.fess.crawler.Crawler;
import org.codelibs.fess.crawler.helper.MemoryDataHelper;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.dbflute.utflute.lastadi.LastaDiTestCase;
import org.junit.jupiter.api.Test;

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Fri Jan 16 13:52:11 GMT 2026

- 2.7K bytes

- Click Count (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>                                              -         -

Created: Tue Mar 31 13:07:34 GMT 2026

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

- 6.2K bytes

- Click Count (0)

github.com/codelibs/fess-crawler

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

import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
import org.codelibs.fess.crawler.service.DataService;
import org.codelibs.fess.crawler.service.UrlFilterService;
import org.codelibs.fess.crawler.service.UrlQueueService;
import org.codelibs.fess.crawler.transformer.impl.FileTransformer;
import org.codelibs.fess.crawler.util.CrawlerWebServer;
import org.codelibs.opensearch.runner.OpenSearchRunner;
import org.dbflute.utflute.lastadi.LastaDiTestCase;

Created: Sun Apr 12 03:50:13 GMT 2026

- Last Modified: Thu Jan 15 01:11:43 GMT 2026

- 7.8K bytes

- Click Count (0)

Search Options