crawlers - Code Search

fess-crawler/src/main/java/org/codelibs/fess/crawler/extractor/impl/HtmlExtractor.java

import javax.xml.xpath.XPathNodes;

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.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.w3c.dom.Document;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 6.9K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Sun Oct 11 02:16:55 UTC 2015

- 394 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/processor/impl/DefaultResponseProcessorTest.java

 * either express or implied. See the License for the specific language
 * governing permissions and limitations under the License.
 */
package org.codelibs.fess.crawler.processor.impl;

import org.codelibs.fess.crawler.entity.ResponseData;
import org.dbflute.utflute.core.PlainTestCase;

/**
 * @author shinsuke
 *
 */
public class DefaultResponseProcessorTest extends PlainTestCase {

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 2.3K bytes

- Viewed (0)

github.com/codelibs/fess

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: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Sun Aug 25 12:46:12 UTC 2019

- 461 bytes

- Viewed (0)

github.com/codelibs/fess-crawler

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;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

/**

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 13.6K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/client/storage/StorageClientTest.java

import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;
import org.codelibs.fess.crawler.helper.impl.MimeTypeHelperImpl;
import org.dbflute.utflute.core.PlainTestCase;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.testcontainers.Testcontainers;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 13.5K bytes

- Viewed (0)

github.com/codelibs/fess

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: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Sun Oct 11 06:51:14 UTC 2015

- 561 bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/es/config/exentity/WebAuthentication.java

import org.codelibs.fess.app.service.WebConfigService;
import org.codelibs.fess.crawler.client.http.Authentication;
import org.codelibs.fess.crawler.client.http.form.FormScheme;
import org.codelibs.fess.crawler.client.http.impl.AuthenticationImpl;
import org.codelibs.fess.crawler.client.http.ntlm.JcifsEngine;
import org.codelibs.fess.crawler.exception.CrawlerSystemException;
import org.codelibs.fess.es.config.bsentity.BsWebAuthentication;

Registered: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Sat Oct 12 01:54:15 UTC 2024

- 5.8K bytes

- Viewed (0)

github.com/codelibs/fess

src/main/java/org/codelibs/fess/job/CrawlJob.java

import org.codelibs.core.timer.TimeoutTask;
import org.codelibs.fess.Constants;
import org.codelibs.fess.es.config.exbhv.ScheduledJobBhv;
import org.codelibs.fess.exception.JobProcessingException;
import org.codelibs.fess.exec.Crawler;
import org.codelibs.fess.helper.ProcessHelper;
import org.codelibs.fess.helper.SystemHelper;
import org.codelibs.fess.mylasta.direction.FessConfig;
import org.codelibs.fess.util.ComponentUtil;

Registered: Thu Oct 31 13:40:30 UTC 2024

- Last Modified: Sun Jun 23 04:13:47 UTC 2024

- 15.1K bytes

- Viewed (0)

github.com/codelibs/fess-crawler

fess-crawler/src/test/java/org/codelibs/fess/crawler/client/ftp/FtpClientTest.java

import org.codelibs.fess.crawler.Constants;
import org.codelibs.fess.crawler.client.ftp.FtpClient.FtpInfo;
import org.codelibs.fess.crawler.container.StandardCrawlerContainer;
import org.codelibs.fess.crawler.entity.RequestData;
import org.codelibs.fess.crawler.entity.ResponseData;
import org.codelibs.fess.crawler.exception.ChildUrlsException;
import org.codelibs.fess.crawler.exception.CrawlingAccessException;

Registered: Sun Nov 10 03:50:12 UTC 2024

- Last Modified: Thu Feb 22 01:36:27 UTC 2024

- 16.3K bytes

- Viewed (0)

Search Options