Search Options

Results per page
Sort
Preferred Languages
Advance

Results 1 - 7 of 7 for UrlFilterImpl (0.07 sec)

  1. fess-crawler/src/main/java/org/codelibs/fess/crawler/filter/impl/UrlFilterImpl.java

     *
     */
    /**
     * This class is an implementation of a URL filter.
     */
    public class UrlFilterImpl implements UrlFilter {
    
        /**
         * Creates a new UrlFilterImpl instance.
         */
        public UrlFilterImpl() {
            // NOP
        }
    
        private static final Logger logger = LogManager.getLogger(UrlFilterImpl.class);
    
        /**
         * The crawler container.
         */
        @Resource
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 9.2K bytes
    - Viewed (0)
  2. fess-crawler-lasta/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

    import java.io.File;
    
    import org.codelibs.core.io.ResourceUtil;
    import org.codelibs.fess.crawler.container.CrawlerContainer;
    import org.codelibs.fess.crawler.entity.UrlQueue;
    import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
    import org.codelibs.fess.crawler.service.DataService;
    import org.codelibs.fess.crawler.service.UrlQueueService;
    import org.codelibs.fess.crawler.transformer.impl.FileTransformer;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 12.8K bytes
    - Viewed (0)
  3. fess-crawler/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

    import org.codelibs.fess.crawler.entity.UrlQueueImpl;
    import org.codelibs.fess.crawler.extractor.ExtractorFactory;
    import org.codelibs.fess.crawler.extractor.impl.TikaExtractor;
    import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
    import org.codelibs.fess.crawler.helper.ContentLengthHelper;
    import org.codelibs.fess.crawler.helper.EncodingHelper;
    import org.codelibs.fess.crawler.helper.MemoryDataHelper;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 19.1K bytes
    - Viewed (0)
  4. fess-crawler-opensearch/src/test/java/org/codelibs/fess/crawler/CrawlerTest.java

    import java.util.logging.Logger;
    import java.util.logging.SimpleFormatter;
    
    import org.codelibs.fess.crawler.client.FesenClient;
    import org.codelibs.fess.crawler.entity.UrlQueue;
    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;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 7.7K bytes
    - Viewed (0)
  5. fess-crawler/src/test/java/org/codelibs/fess/crawler/client/http/HcHttpClientTest.java

    import org.codelibs.fess.crawler.entity.ResponseData;
    import org.codelibs.fess.crawler.exception.CrawlingAccessException;
    import org.codelibs.fess.crawler.filter.UrlFilter;
    import org.codelibs.fess.crawler.filter.impl.UrlFilterImpl;
    import org.codelibs.fess.crawler.helper.MemoryDataHelper;
    import org.codelibs.fess.crawler.helper.RobotsTxtHelper;
    import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 11.7K bytes
    - Viewed (0)
  6. fess-crawler/src/test/java/org/codelibs/fess/crawler/filter/UrlFilterTest.java

     * governing permissions and limitations under the License.
     */
    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;
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 19K bytes
    - Viewed (0)
  7. README.md

        client.setUserAgent("MyBot/1.0");
        client.setConnectionTimeout(30000);
        client.setMaxConnections(100);
    });
    
    // Configure URL filtering
    container.singleton("urlFilter", UrlFilterImpl.class, filter -> {
        filter.addInclude("https://example.com/.*");
        filter.addExclude(".*\\.(css|js|png|jpg|gif)$");
    });
    
    // Configure content extraction
    Registered: Sun Sep 21 03:50:09 UTC 2025
    - Last Modified: Sun Aug 31 05:32:52 UTC 2025
    - 15.3K bytes
    - Viewed (0)
Back to top