Search Options

Results per page
Sort
Preferred Languages
Advance

Results 71 - 80 of 445 for CRAWLER (0.04 sec)

  1. fess-crawler/src/test/java/org/codelibs/fess/crawler/rule/impl/SitemapsRuleTest.java

     */
    package org.codelibs.fess.crawler.rule.impl;
    
    import java.io.File;
    import java.io.InputStream;
    import java.util.regex.Pattern;
    
    import org.codelibs.core.io.CloseableUtil;
    import org.codelibs.core.io.ResourceUtil;
    import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
    import org.codelibs.fess.crawler.entity.ResponseData;
    import org.codelibs.fess.crawler.helper.SitemapsHelper;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 4.7K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/client/AbstractCrawlerClient.java

     */
    package org.codelibs.fess.crawler.client;
    
    import java.io.File;
    import java.io.IOException;
    import java.util.Map;
    
    import org.apache.logging.log4j.LogManager;
    import org.apache.logging.log4j.Logger;
    import org.codelibs.fess.crawler.container.CrawlerContainer;
    import org.codelibs.fess.crawler.entity.RequestData;
    import org.codelibs.fess.crawler.entity.ResponseData;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Sep 06 04:15:37 UTC 2025
    - 9.7K bytes
    - Viewed (10)
  3. fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/AbstractRule.java

     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.rule.impl;
    
    import org.codelibs.fess.crawler.container.CrawlerContainer;
    import org.codelibs.fess.crawler.processor.ResponseProcessor;
    import org.codelibs.fess.crawler.rule.Rule;
    import org.codelibs.fess.crawler.rule.RuleManager;
    
    import jakarta.annotation.Resource;
    
    /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Wed Sep 03 14:42:53 UTC 2025
    - 2.8K bytes
    - Viewed (0)
  4. fess-crawler/src/main/java/org/codelibs/fess/crawler/processor/impl/SitemapsResponseProcessor.java

    import org.codelibs.fess.crawler.entity.Sitemap;
    import org.codelibs.fess.crawler.entity.SitemapSet;
    import org.codelibs.fess.crawler.exception.ChildUrlsException;
    import org.codelibs.fess.crawler.helper.SitemapsHelper;
    import org.codelibs.fess.crawler.processor.ResponseProcessor;
    
    import jakarta.annotation.Resource;
    
    /**
     * A response processor implementation that handles sitemaps.
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 3.4K bytes
    - Viewed (0)
  5. MIGRATION.md

      -F "file=@documents.bulk"
    ```
    
    ### 4. Direct Crawler Configuration
    
    Instead of importing documents, configure Fess to crawl your data sources:
    
    **Web Crawling**:
    - **Admin Path**: Crawler > Web
    - **Supports**: HTTP/HTTPS websites
    - **Features**: JavaScript rendering, authentication, custom headers
    
    **File Crawling**:
    - **Admin Path**: Crawler > File
    - **Supports**: SMB, FTP, local file systems
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Nov 06 12:40:11 UTC 2025
    - 23.2K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/ApiExtractor.java

    import org.codelibs.core.timer.TimeoutTask;
    import org.codelibs.fess.crawler.Constants;
    import org.codelibs.fess.crawler.client.AccessTimeoutTarget;
    import org.codelibs.fess.crawler.client.http.Authentication;
    import org.codelibs.fess.crawler.client.http.RequestHeader;
    import org.codelibs.fess.crawler.entity.ExtractData;
    import org.codelibs.fess.crawler.exception.ExtractException;
    
    import com.google.common.base.Charsets;
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Mon Nov 24 03:59:47 UTC 2025
    - 12.2K bytes
    - Viewed (0)
  7. fess-crawler/src/test/java/org/codelibs/fess/crawler/transformer/impl/FileTransformerTest.java

     */
    package org.codelibs.fess.crawler.transformer.impl;
    
    import java.io.File;
    import java.io.IOException;
    import java.util.Map;
    
    import org.codelibs.core.io.FileUtil;
    import org.codelibs.fess.crawler.Constants;
    import org.codelibs.fess.crawler.entity.AccessResultDataImpl;
    import org.codelibs.fess.crawler.entity.ResponseData;
    import org.codelibs.fess.crawler.entity.ResultData;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Mar 15 06:52:00 UTC 2025
    - 7.6K bytes
    - Viewed (0)
  8. fess-crawler/src/test/java/org/codelibs/fess/crawler/extractor/impl/EmlExtractorTest.java

     */
    package org.codelibs.fess.crawler.extractor.impl;
    
    import java.io.IOException;
    import java.io.InputStream;
    
    import org.apache.logging.log4j.LogManager;
    import org.apache.logging.log4j.Logger;
    import org.codelibs.core.io.ResourceUtil;
    import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
    import org.codelibs.fess.crawler.entity.ExtractData;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Thu Aug 07 02:55:08 UTC 2025
    - 4.6K bytes
    - Viewed (1)
  9. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/CrawlingParameterUtil.java

     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.util;
    
    import org.codelibs.fess.crawler.CrawlerContext;
    import org.codelibs.fess.crawler.entity.AccessResult;
    import org.codelibs.fess.crawler.entity.UrlQueue;
    import org.codelibs.fess.crawler.service.DataService;
    import org.codelibs.fess.crawler.service.UrlQueueService;
    
    /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Nov 22 13:28:22 UTC 2025
    - 6.4K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/XmlUtil.java

     *   <li>org.codelibs.fess.crawler.Constants</li>
     *   <li>org.codelibs.fess.crawler.exception.CrawlerSystemException</li>
     *   <li>org.codelibs.fess.crawler.entity.AccessResultData</li>
     *   <li>org.codelibs.core.lang.StringUtil</li>
     * </ul>
     *
     * @see org.codelibs.fess.crawler.Constants
     * @see org.codelibs.fess.crawler.exception.CrawlerSystemException
     * @see org.codelibs.fess.crawler.entity.AccessResultData
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Nov 22 13:28:22 UTC 2025
    - 9.5K bytes
    - Viewed (0)
Back to top