Search Options

Results per page
Sort
Preferred Languages
Advance

Results 181 - 190 of 705 for crawler (0.78 sec)

  1. fess-crawler-lasta/src/main/resources/crawler/log.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="logHelper"
    		class="org.codelibs.fess.crawler.helper.impl.LogHelperImpl">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 343 bytes
    - Viewed (0)
  2. fess-crawler-lasta/src/main/resources/crawler/mimetype.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="mimeTypeHelper"
    		class="org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl" instance="singleton">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 374 bytes
    - Viewed (0)
  3. fess-crawler-lasta/src/main/resources/crawler/sitemaps.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="sitemapsHelper" class="org.codelibs.fess.crawler.helper.SitemapsHelper"
    		instance="singleton">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 365 bytes
    - Viewed (0)
  4. fess-crawler-lasta/src/main/resources/crawler/urlconverter.xml

    <!DOCTYPE components PUBLIC "-//DBFLUTE//DTD LastaDi 1.0//EN"
    	"http://dbflute.org/meta/lastadi10.dtd">
    <components namespace="fessCrawler">
    	<include path="crawler/container.xml" />
    
    	<!-- Converts child links to normalize it. -->
    	<component name="urlConvertHelper" class="org.codelibs.fess.crawler.helper.UrlConvertHelper">
    	</component>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Oct 11 02:16:55 UTC 2015
    - 394 bytes
    - Viewed (0)
  5. src/main/resources/crawler/extractor+tikaExtractor.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="tikaExtractor"
    		class="org.codelibs.fess.crawler.extractor.impl.TikaExtractor">
    		<property name="maxCompressionRatio">2</property>
    		<property name="maxUncompressionSize">10000000</property>
    	</component>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Aug 25 12:46:12 UTC 2019
    - 461 bytes
    - Viewed (0)
  6. src/main/java/org/codelibs/fess/crawler/interval/FessIntervalController.java

     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.interval;
    
    import org.apache.logging.log4j.LogManager;
    import org.apache.logging.log4j.Logger;
    import org.codelibs.fess.crawler.interval.impl.DefaultIntervalController;
    import org.codelibs.fess.helper.IntervalControlHelper;
    import org.codelibs.fess.util.ComponentUtil;
    
    /**
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Wed Nov 19 07:09:17 UTC 2025
    - 5.1K bytes
    - Viewed (0)
  7. docs/fr/README.md

    * [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute") : Framework Web
    * [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job") : Planificateur de tâches
    * [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler") : Crawler Web
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Tue Nov 11 22:42:32 UTC 2025
    - 7.9K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/Extractor.java

     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.extractor;
    
    import java.io.InputStream;
    import java.util.Map;
    
    import org.codelibs.fess.crawler.entity.ExtractData;
    
    /**
     * The Extractor interface defines methods for extracting text data from an input stream.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 1.6K bytes
    - Viewed (0)
  9. src/main/java/org/codelibs/fess/app/web/admin/wizard/AdminWizardAction.java

        protected DynamicProperties systemProperties;
    
        /** Service for managing web crawler configurations */
        @Resource
        protected WebConfigService webConfigService;
    
        /** Service for managing file crawler configurations */
        @Resource
        protected FileConfigService fileConfigService;
    
        /** Helper for managing crawler processes */
        @Resource
        protected ProcessHelper processHelper;
    
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Dec 11 09:47:03 UTC 2025
    - 16.3K bytes
    - Viewed (0)
  10. 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">
    		<property name="defaultMaxLength">10485760</property><!-- 10M -->
    		<postConstruct name="addMaxLength">
    			<arg>"text/html"</arg>
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Sun Oct 11 06:51:14 UTC 2015
    - 561 bytes
    - Viewed (0)
Back to top