Search Options

Results per page
Sort
Preferred Languages
Advance

Results 201 - 210 of 441 for CRAWLER (1.7 sec)

  2. github.com/codelibs/fess

    docs/es/README.md 

    * [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Framework Web
* [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): Programador de Tareas
* [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Rastreador Web
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Tue Nov 11 22:42:32 UTC 2025
    - 7.8K bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

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

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

import java.io.InputStream;
import java.util.Map;

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.ExtractException;

/**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Wed Nov 19 08:55:01 UTC 2025
    - 2.7K bytes
    - Viewed (0)
  4. github.com/codelibs/fess-crawler

    fess-crawler-lasta/src/main/resources/crawler/contentlength.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="contentLengthHelper"
		class="org.codelibs.fess.crawler.helper.ContentLengthHelper" instance="singleton">
	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 375 bytes
    - Viewed (0)
  5. github.com/codelibs/fess-crawler

    fess-crawler-lasta/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.impl.DefaultIntervalController"
		instance="prototype">
	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 389 bytes
    - Viewed (0)
  6. github.com/codelibs/fess

    src/main/java/org/codelibs/fess/helper/PluginHelper.java 

            if (artifactType != ArtifactType.CRAWLER) {
            return false;
        }

        if ("fess-crawler".equals(name)//
                || "fess-crawler-db".equals(name)//
                || "fess-crawler-db-h2".equals(name)//
                || "fess-crawler-db-mysql".equals(name)//
                || "fess-crawler-es".equals(name)//
                || "fess-crawler-opensearch".equals(name)//
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Fri Nov 28 16:29:12 UTC 2025
    - 24.9K bytes
    - Viewed (0)
  7. github.com/codelibs/fess-crawler

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

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

import java.io.ByteArrayInputStream;
import java.io.InputStream;
import java.util.Map;

import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;

/**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 8.4K bytes
    - Viewed (0)
  8. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/FileTransformer.java 

    import org.apache.logging.log4j.Logger;
import org.codelibs.core.io.CopyUtil;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;

/**
 * <p>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 11.7K bytes
    - Viewed (0)
  9. github.com/codelibs/fess-crawler

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

    import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
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;

/**
 * Extracts text content and metadata from CSV files.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Dec 11 08:38:29 UTC 2025
    - 12.8K bytes
    - Viewed (0)
  10. github.com/codelibs/fess-crawler

    fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/UrlFilterTest.java 

     */
package org.codelibs.fess.crawler.filter;

import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
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: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 19K bytes
    - Viewed (0)
  11. github.com/codelibs/fess

    src/main/java/org/codelibs/fess/app/web/admin/scheduler/AdminSchedulerAction.java 

        //                                            ----------

    /**
     * Creates a new scheduled job from a crawler configuration.
     *
     * @param type the crawler type (web, file, or data)
     * @param id the crawler configuration ID
     * @param name the name for the new job (base64 encoded)
     * @return HTML response for the job creation form
     */
    @Execute
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Nov 20 13:56:35 UTC 2025
    - 21.8K bytes
    - Viewed (0)
Back to top