Search Options

Results per page
Sort
Preferred Languages
Advance

Results 131 - 140 of 538 for crawlers (0.17 sec)

  2. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/rule/impl/SitemapsRule.java 

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

import java.io.InputStream;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.SitemapsHelper;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**
 * @author shinsuke
 *
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 1.8K bytes
    - Viewed (0)
  3. github.com/codelibs/fess-crawler

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

    import org.codelibs.core.misc.Pair;
import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.builder.RequestDataBuilder;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Oct 24 12:16:00 UTC 2024
    - 19.4K bytes
    - Viewed (0)
  4. github.com/codelibs/fess-crawler

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

     */
package org.codelibs.fess.crawler.extractor.impl;

import java.io.BufferedInputStream;
import java.io.ByteArrayInputStream;
import java.io.InputStream;

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.ExtractData;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 3.7K bytes
    - Viewed (0)
  5. github.com/codelibs/fess-crawler

    fess-crawler-opensearch/pom.xml 

    	<modelVersion>4.0.0</modelVersion>
	<artifactId>fess-crawler-opensearch</artifactId>
	<packaging>jar</packaging>
	<name>Fess Crawler Elasticsearch</name>
	<parent>
		<groupId>org.codelibs.fess</groupId>
		<artifactId>fess-crawler-parent</artifactId>
		<version>15.0.0-SNAPSHOT</version>
		<relativePath>../pom.xml</relativePath>
	</parent>
	<build>
		<plugins>
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Nov 07 04:44:10 UTC 2024
    - 3.4K bytes
    - Viewed (0)
  6. github.com/codelibs/fess-crawler

    fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/ExtractorFactory.java 

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

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

import org.codelibs.core.lang.StringUtil;
import org.codelibs.fess.crawler.container.CrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Tue Jun 18 05:49:57 UTC 2024
    - 2.9K bytes
    - Viewed (0)
  7. github.com/codelibs/fess-crawler

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

     */
package org.codelibs.fess.crawler.rule.impl;

import java.io.File;

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;
import org.codelibs.fess.crawler.rule.Rule;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 6.2K bytes
    - Viewed (0)
  8. github.com/codelibs/fess

    src/main/java/org/codelibs/fess/crawler/transformer/FessFileTransformer.java 

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

import org.apache.logging.log4j.LogManager;
import org.apache.logging.log4j.Logger;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.extractor.Extractor;
import org.codelibs.fess.crawler.extractor.ExtractorFactory;
import org.codelibs.fess.exception.FessSystemException;
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:53:18 UTC 2024
    - 2.2K bytes
    - Viewed (0)
  9. github.com/codelibs/fess

    src/test/java/org/codelibs/fess/it/CrawlTestBase.java 

                ThreadUtil.sleep(500);
            count++;
            final Map<String, Object> scheduler = getSchedulerItem(namePrefix);
            assertTrue(scheduler.containsKey("running"));
            isRunning = (Boolean) scheduler.get("running");
        }
        if (300 <= count) {
            logger.info("Time out: Failed to start crawler)");
            fail(); // Time Out
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Thu Feb 22 01:37:57 UTC 2024
    - 9.9K bytes
    - Viewed (0)
  10. github.com/codelibs/fess

    src/main/java/org/codelibs/fess/crawler/transformer/AbstractFessFileTransformer.java 

    import org.codelibs.fess.Constants;
import org.codelibs.fess.crawler.entity.AccessResultData;
import org.codelibs.fess.crawler.entity.ExtractData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.entity.ResultData;
import org.codelibs.fess.crawler.entity.UrlQueue;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
    Registered: Thu Oct 31 13:40:30 UTC 2024
    - Last Modified: Fri Oct 11 21:11:58 UTC 2024
    - 23.6K bytes
    - Viewed (0)
  11. github.com/codelibs/fess-crawler

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

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

import java.io.InputStream;

import org.codelibs.core.io.CloseableUtil;
import org.codelibs.core.io.ResourceUtil;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.dbflute.utflute.core.PlainTestCase;
import org.slf4j.Logger;
    Registered: Sun Nov 10 03:50:12 UTC 2024
    - Last Modified: Thu Feb 22 01:36:27 UTC 2024
    - 2K bytes
    - Viewed (0)
Back to top