Search Options

Results per page
Sort
Preferred Languages
Advance

Results 231 - 240 of 441 for CRAWLER (5.22 sec)

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

    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;
    import org.codelibs.fess.crawler.exception.CrawlerSystemException;
    import org.codelibs.fess.crawler.exception.ExtractException;
    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
    - 10.4K bytes
    - Viewed (0)
  2. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/TikaExtractor.java

    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.CrawlerSystemException;
    import org.codelibs.fess.crawler.exception.ExtractException;
    import org.codelibs.fess.crawler.extractor.Extractor;
    import org.codelibs.fess.crawler.util.TextUtil;
    import org.xml.sax.ContentHandler;
    import org.xml.sax.SAXException;
    
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 30.8K bytes
    - Viewed (0)
  3. fess-crawler/pom.xml

    	<modelVersion>4.0.0</modelVersion>
    	<artifactId>fess-crawler</artifactId>
    	<packaging>jar</packaging>
    	<name>Fess Crawler</name>
    	<description>Fess Crawler is a crawler framework.</description>
    	<parent>
    		<groupId>org.codelibs.fess</groupId>
    		<artifactId>fess-crawler-parent</artifactId>
    		<version>15.4.1-SNAPSHOT</version>
    		<relativePath>../pom.xml</relativePath>
    	</parent>
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Dec 20 06:34:36 UTC 2025
    - 12.1K bytes
    - Viewed (0)
  4. docs/zh-CN/README.md

    * [LastaFlute](https://github.com/lastaflute/lastaflute "LastaFlute"): Web 框架
    * [Lasta Job](https://github.com/lastaflute/lasta-job "Lasta Job"): 任务调度器
    * [Fess Crawler](https://github.com/codelibs/fess-crawler "Fess Crawler"): Web 爬虫
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Tue Nov 11 22:42:32 UTC 2025
    - 7K bytes
    - Viewed (0)
  5. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/CommandExtractor.java

    import org.codelibs.core.lang.StringUtil;
    import org.codelibs.core.lang.ThreadUtil;
    import org.codelibs.fess.crawler.Constants;
    import org.codelibs.fess.crawler.entity.ExtractData;
    import org.codelibs.fess.crawler.exception.CrawlerSystemException;
    import org.codelibs.fess.crawler.exception.ExecutionTimeoutException;
    import org.codelibs.fess.crawler.exception.ExtractException;
    
    /**
     * Extracts text content by executing an external command.
     */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Nov 23 12:19:14 UTC 2025
    - 16.1K bytes
    - Viewed (0)
  6. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XmlTransformer.java

    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;
    import org.codelibs.fess.crawler.exception.CrawlingAccessException;
    import org.codelibs.fess.crawler.util.XPathAPI;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 23.9K bytes
    - Viewed (0)
  7. fess-crawler/src/main/java/org/codelibs/fess/crawler/transformer/impl/XpathTransformer.java

    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;
    import org.codelibs.fess.crawler.exception.CrawlingAccessException;
    import org.codelibs.fess.crawler.util.XmlUtil;
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sun Jul 06 02:13:03 UTC 2025
    - 13.1K bytes
    - Viewed (0)
  8. fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlExtractor.java

    import org.apache.logging.log4j.Logger;
    import org.codelibs.core.lang.StringUtil;
    import org.codelibs.core.stream.StreamUtil;
    import org.codelibs.fess.crawler.entity.ExtractData;
    import org.codelibs.fess.crawler.exception.CrawlerSystemException;
    import org.codelibs.fess.crawler.util.XPathAPI;
    import org.codelibs.nekohtml.parsers.DOMParser;
    import org.w3c.dom.Document;
    import org.w3c.dom.Node;
    import org.xml.sax.InputSource;
    
    /**
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Oct 04 08:47:19 UTC 2025
    - 9.3K bytes
    - Viewed (0)
  9. src/main/java/org/codelibs/fess/app/web/admin/webconfig/CreateForm.java

         * Document URL patterns to exclude from search index.
         */
        @CustomSize(maxKey = "form.admin.max.input.size")
        public String excludedDocUrls;
    
        /**
         * Additional configuration parameters for the crawler.
         */
        @CustomSize(maxKey = "form.admin.max.input.size")
        public String configParameter;
    
        /**
         * The maximum crawling depth from the starting URLs.
         */
        @Min(value = 0)
    Registered: Sat Dec 20 09:19:18 UTC 2025
    - Last Modified: Thu Jul 17 08:28:31 UTC 2025
    - 5.9K bytes
    - Viewed (0)
  10. fess-crawler/src/main/java/org/codelibs/fess/crawler/util/AccessResultCallback.java

     * either express or implied. See the License for the specific language
     * governing permissions and limitations under the License.
     */
    package org.codelibs.fess.crawler.util;
    
    import org.codelibs.fess.crawler.entity.AccessResult;
    
    /**
     * A callback interface for processing access results.
     *
     * @param <RESULT> the type of access result that extends {@link AccessResult}
     */
    Registered: Sat Dec 20 11:21:39 UTC 2025
    - Last Modified: Sat Nov 22 13:28:22 UTC 2025
    - 1.1K bytes
    - Viewed (0)
Back to top