You can download WebCollector-2.32.jar in this page.
GPL2.0
WebCollector-2.32.jar file has the following types.
.netbeans_automatic_build META-INF/MANIFEST.MF META-INF/maven/cn.edu.hfut.dmic.webcollector/WebCollector/pom.properties META-INF/maven/cn.edu.hfut.dmic.webcollector/WebCollector/pom.xml cn.edu.hfut.dmic.contentextractor.ContentExtractor.class cn.edu.hfut.dmic.contentextractor.News.class cn.edu.hfut.dmic.webcollector.crawldb.DBManager.class cn.edu.hfut.dmic.webcollector.crawldb.Generator.class cn.edu.hfut.dmic.webcollector.crawldb.Injector.class cn.edu.hfut.dmic.webcollector.crawldb.SegmentWriter.class cn.edu.hfut.dmic.webcollector.crawler.AutoParseCrawler.class cn.edu.hfut.dmic.webcollector.crawler.Crawler.class cn.edu.hfut.dmic.webcollector.example.DemoBingCrawler.class cn.edu.hfut.dmic.webcollector.example.DemoDepthCrawler.class cn.edu.hfut.dmic.webcollector.example.DemoMetaCrawler.class cn.edu.hfut.dmic.webcollector.example.DemoPostCrawler.class cn.edu.hfut.dmic.webcollector.example.DemoSelenium.class cn.edu.hfut.dmic.webcollector.example.TutorialCrawler.class cn.edu.hfut.dmic.webcollector.fetcher.Executor.class cn.edu.hfut.dmic.webcollector.fetcher.Fetcher.class cn.edu.hfut.dmic.webcollector.fetcher.Visitor.class cn.edu.hfut.dmic.webcollector.model.CrawlDatum.class cn.edu.hfut.dmic.webcollector.model.CrawlDatums.class cn.edu.hfut.dmic.webcollector.model.Links.class cn.edu.hfut.dmic.webcollector.model.Page.class cn.edu.hfut.dmic.webcollector.net.HttpRequest.class cn.edu.hfut.dmic.webcollector.net.HttpResponse.class cn.edu.hfut.dmic.webcollector.net.Proxys.class cn.edu.hfut.dmic.webcollector.net.Requester.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BerkeleyCrawler.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BerkeleyDBManager.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BerkeleyDBReader.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BerkeleyDBUtils.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BerkeleyGenerator.class cn.edu.hfut.dmic.webcollector.plugin.berkeley.BreadthCrawler.class cn.edu.hfut.dmic.webcollector.plugin.ram.RamCrawler.class cn.edu.hfut.dmic.webcollector.plugin.ram.RamDB.class cn.edu.hfut.dmic.webcollector.plugin.ram.RamDBManager.class cn.edu.hfut.dmic.webcollector.plugin.ram.RamGenerator.class cn.edu.hfut.dmic.webcollector.util.CharsetDetector.class cn.edu.hfut.dmic.webcollector.util.Config.class cn.edu.hfut.dmic.webcollector.util.CrawlDatumFormater.class cn.edu.hfut.dmic.webcollector.util.FileSystemOutput.class cn.edu.hfut.dmic.webcollector.util.FileUtils.class cn.edu.hfut.dmic.webcollector.util.JsoupUtils.class cn.edu.hfut.dmic.webcollector.util.RegexRule.class log4j.properties
WebCollector-2.32.pom file content.
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<name>WebCollector</name>
<groupId>cn.edu.hfut.dmic.webcollector</groupId>
<artifactId>WebCollector</artifactId>
<version>2.32</version>
<description>A java crawler for information collection</description>
<url>https://github.com/CrawlScript/WebCollector</url>
<packaging>jar</packaging>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<maven.compiler.source>1.6</maven.compiler.source>
<maven.compiler.target>1.6</maven.compiler.target>
</properties>
<licenses>
<license>
<name>GPL2.0</name>
<url>http://www.gnu.org/licenses/gpl-2.0.html</url>
<distribution>repo</distribution>
</license>
</licenses>
<scm>
<url>https://github.com/CrawlScript/WebCollector</url>
<connection>scm:git:https://github.com/CrawlScript/WebCollector.git</connection>
</scm>
<distributionManagement>
<snapshotRepository>
<id>ossrh</id>
<url>https://oss.sonatype.org/content/repositories/snapshots</url>
</snapshotRepository>
</distributionManagement>
<reporting>
<plugins>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>cobertura-maven-plugin</artifactId>
<version>2.7</version>
<reportSets>
<reportSet>
<reports>
<report>cobertura</report>
</reports>
</reportSet>
</reportSets>
<configuration>
<formats>
<format>html</format>
</formats>
</configuration>
</plugin>
</plugins>
</reporting>
<build>
<plugins>
<plugin>
<groupId>org.sonatype.plugins</groupId>
<artifactId>nexus-staging-maven-plugin</artifactId>
<version>1.6.3</version>
<extensions>true</extensions>
<configuration>
<serverId>ossrh</serverId>
<nexusUrl>https://oss.sonatype.org/</nexusUrl>
<autoReleaseAfterClose>true</autoReleaseAfterClose>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.7.2</version>
<configuration>
<forkMode>once</forkMode>
<argLine>-Dfile.encoding=UTF-8</argLine>
<systemProperties>
<property>
<name>net.sourceforge.cobertura.datafile</name>
<value>target/cobertura/cobertura.ser</value>
</property>
</systemProperties>
<skipTests>false</skipTests>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-dependency-plugin</artifactId>
<version>2.8</version>
<executions>
<execution>
<id>copy-dependencies</id>
<phase>package</phase>
<goals>
<goal>copy-dependencies</goal>
</goals>
<configuration>
<outputDirectory>${project.build.directory}/</outputDirectory>
<overWriteReleases>false</overWriteReleases>
<overWriteSnapshots>true</overWriteSnapshots>
<excludeTransitive>false</excludeTransitive>
<excludeScope>provided</excludeScope>
</configuration>
</execution>
</executions>
</plugin>
<!--
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.5</version>
<configuration>
<archive>
<manifest>
<addClasspath>true</addClasspath>
<mainClass>cn.edu.hfut.dmic.webcollector.ui.BreadthCrawlerUI</mainClass>
</manifest>
</archive>
</configuration>
</plugin>
-->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<version>2.6.1</version>
<configuration>
</configuration>
<executions>
<execution>
<id>attach-javadoc</id>
<phase>verify</phase>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<version>2.1.1</version>
<configuration>
</configuration>
<executions>
<execution>
<id>attach-sources</id>
<phase>verify</phase>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-gpg-plugin</artifactId>
<version>1.5</version>
<executions>
<execution>
<id>sign-artifacts</id>
<phase>verify</phase>
<goals>
<goal>sign</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-antrun-plugin</artifactId>
<executions>
<execution>
<phase>package</phase>
<configuration>
<tasks>
<copy todir="${project.build.directory}/bin">
<fileset dir="${project.build.directory}">
<include name="*.jar"/>
<include name="*.sh"/>
<include name="*.bat"/>
</fileset>
</copy>
<zip basedir="${project.build.directory}/bin"
destfile="../webcollector-${project.version}-bin.zip"/>
</tasks>
</configuration>
<goals>
<goal>run</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
<dependencies>
<!-- https://mvnrepository.com/artifact/org.jsoup/jsoup -->
<dependency>
<groupId>org.jsoup</groupId>
<artifactId>jsoup</artifactId>
<version>1.9.2</version>
</dependency>
<dependency>
<groupId>com.googlecode.juniversalchardet</groupId>
<artifactId>juniversalchardet</artifactId>
<version>1.0.3</version>
</dependency>
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</version>
</dependency>
<dependency>
<groupId>org.json</groupId>
<artifactId>json</artifactId>
<version>20140107</version>
</dependency>
<dependency>
<groupId>com.sleepycat</groupId>
<artifactId>je</artifactId>
<version>5.0.73</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>1.7.21</version>
</dependency>
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-log4j12</artifactId>
<version>1.7.21</version>
</dependency>
<!--
??????dependency??JS????????(selenium)?
????????????? <scope>provided</scope>????????????
?????dependency???????M???????????????maven???,????
??????http://maven.oschina.net/help.html
-->
<!-- https://mvnrepository.com/artifact/org.seleniumhq.selenium/selenium-java -->
<dependency>
<groupId>org.seleniumhq.selenium</groupId>
<artifactId>selenium-java</artifactId>
<version>2.44.0</version>
<scope>provided</scope>
</dependency>
<!--
??????dependency??????????(mysql?spring jdbc)?
??????????????????????????
?????dependency???????M???????????????maven???,????
??????http://maven.oschina.net/help.html
-->
<!--
<dependency>
<groupId>mysql</groupId>
<artifactId>mysql-connector-java</artifactId>
<version>5.1.31</version>
</dependency>
<dependency>
<groupId>org.springframework</groupId>
<artifactId>spring-jdbc</artifactId>
<version>4.0.5.RELEASE</version>
</dependency>
<dependency>
<groupId>commons-dbcp</groupId>
<artifactId>commons-dbcp</artifactId>
<version>1.4</version>
</dependency>
-->
</dependencies>
<developers>
<developer>
<id>hujun</id>
<name>Hu Jun</name>
<email>hujunxianligong@gmail.com</email>
<roles>
<role>Lead Developer</role>
</roles>
<timezone>+8</timezone>
</developer>
</developers>
</project>
<dependency> <groupId>cn.edu.hfut.dmic.webcollector</groupId> <artifactId>WebCollector</artifactId> <version>2.32</version> </dependency>
If you think the following WebCollector-2.32.jar downloaded from Maven central repository is inappropriate, such as containing malicious code/tools or violating the copyright, please email , thanks.
Download WebCollector-2.32.jar file