You can download crawler4j-4.3.jar in this page.
The Apache Software License, Version 2.0
crawler4j-4.3.jar file has the following types.
META-INF/MANIFEST.MF META-INF/maven/edu.uci.ics/crawler4j/pom.properties META-INF/maven/edu.uci.ics/crawler4j/pom.xml edu.uci.ics.crawler4j.crawler.Configurable.class edu.uci.ics.crawler4j.crawler.CrawlConfig.class edu.uci.ics.crawler4j.crawler.CrawlController.class edu.uci.ics.crawler4j.crawler.Page.class edu.uci.ics.crawler4j.crawler.WebCrawler.class edu.uci.ics.crawler4j.crawler.authentication.AuthInfo.class edu.uci.ics.crawler4j.crawler.authentication.BasicAuthInfo.class edu.uci.ics.crawler4j.crawler.authentication.FormAuthInfo.class edu.uci.ics.crawler4j.crawler.authentication.NtAuthInfo.class edu.uci.ics.crawler4j.crawler.exceptions.ContentFetchException.class edu.uci.ics.crawler4j.crawler.exceptions.PageBiggerThanMaxSizeException.class edu.uci.ics.crawler4j.crawler.exceptions.ParseException.class edu.uci.ics.crawler4j.fetcher.IdleConnectionMonitorThread.class edu.uci.ics.crawler4j.fetcher.PageFetchResult.class edu.uci.ics.crawler4j.fetcher.PageFetcher.class edu.uci.ics.crawler4j.fetcher.SniPoolingHttpClientConnectionManager.class edu.uci.ics.crawler4j.fetcher.SniSSLConnectionSocketFactory.class edu.uci.ics.crawler4j.frontier.Counters.class edu.uci.ics.crawler4j.frontier.DocIDServer.class edu.uci.ics.crawler4j.frontier.Frontier.class edu.uci.ics.crawler4j.frontier.InProcessPagesDB.class edu.uci.ics.crawler4j.frontier.WebURLTupleBinding.class edu.uci.ics.crawler4j.frontier.WorkQueues.class edu.uci.ics.crawler4j.parser.AllTagMapper.class edu.uci.ics.crawler4j.parser.BinaryParseData.class edu.uci.ics.crawler4j.parser.ExtractedUrlAnchorPair.class edu.uci.ics.crawler4j.parser.HtmlContentHandler.class edu.uci.ics.crawler4j.parser.HtmlParseData.class edu.uci.ics.crawler4j.parser.NotAllowedContentException.class edu.uci.ics.crawler4j.parser.ParseData.class edu.uci.ics.crawler4j.parser.Parser.class edu.uci.ics.crawler4j.parser.TextParseData.class edu.uci.ics.crawler4j.robotstxt.HostDirectives.class edu.uci.ics.crawler4j.robotstxt.PathRule.class edu.uci.ics.crawler4j.robotstxt.RobotstxtConfig.class edu.uci.ics.crawler4j.robotstxt.RobotstxtParser.class edu.uci.ics.crawler4j.robotstxt.RobotstxtServer.class edu.uci.ics.crawler4j.robotstxt.UserAgentDirectives.class edu.uci.ics.crawler4j.url.TLDList.class edu.uci.ics.crawler4j.url.URLCanonicalizer.class edu.uci.ics.crawler4j.url.UrlResolver.class edu.uci.ics.crawler4j.url.WebURL.class edu.uci.ics.crawler4j.util.IO.class edu.uci.ics.crawler4j.util.Net.class edu.uci.ics.crawler4j.util.Util.class tld-names.txt
crawler4j-4.3.pom file content.
<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>
<groupId>edu.uci.ics</groupId>
<artifactId>crawler4j</artifactId>
<packaging>jar</packaging>
<name>crawler4j</name>
<version>4.3</version>
<description>Open Source Web Crawler for Java</description>
<url>https://github.com/yasserg/crawler4j</url>
<licenses>
<license>
<name>The Apache Software License, Version 2.0</name>
<url>http://www.apache.org/licenses/LICENSE-2.0.txt</url>
<distribution>repo</distribution>
</license>
</licenses>
<scm>
<url>https://github.com/yasserg/crawler4j</url>
<connection>scm:git:git@github.com:yasserg/crawler4j.git</connection>
<developerConnection>scm:git:git@github.com:yasserg/crawler4j.git</developerConnection>
<tag>crawler4j-4.3</tag>
</scm>
<distributionManagement>
<snapshotRepository>
<id>ossrh</id>
<url>https://oss.sonatype.org/content/repositories/snapshots</url>
</snapshotRepository>
<repository>
<id>ossrh</id>
<url>https://oss.sonatype.org/service/local/staging/deploy/maven2/</url>
</repository>
</distributionManagement>
<properties>
<slf4j.version>1.7.22</slf4j.version>
<logback.version>1.1.7</logback.version>
<guava.version>21.0</guava.version>
<apache.http.components.version>4.5.3</apache.http.components.version>
<je.version>5.0.84</je.version>
<apache.tika.version>1.14</apache.tika.version>
<!--test dependency versions -->
<junit.version>4.12</junit.version>
<wiremock.version>2.4.1</wiremock.version>
<spock.version>1.0-groovy-2.4</spock.version>
<groovy.version>2.4.7</groovy.version>
</properties>
<parent>
<groupId>org.sonatype.oss</groupId>
<artifactId>oss-parent</artifactId>
<version>7</version>
</parent>
<profiles>
<profile>
<id>release</id>
<build>
<plugins>
<!-- generate a source jar -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<version>2.4</version>
<executions>
<execution>
<id>attach-sources</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
<!-- generate a javadoc jar -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-javadoc-plugin</artifactId>
<version>2.10.1</version>
<configuration>
<additionalparam>-Xdoclint:none</additionalparam>
</configuration>
<executions>
<execution>
<id>attach-javadocs</id>
<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>
<groupId>org.sonatype.plugins</groupId>
<artifactId>nexus-staging-maven-plugin</artifactId>
<version>1.6.7</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-release-plugin</artifactId>
<version>2.5.3</version>
<configuration>
<autoVersionSubmodules>true</autoVersionSubmodules>
<useReleaseProfile>false</useReleaseProfile>
<releaseProfiles>release</releaseProfiles>
<goals>deploy</goals>
</configuration>
</plugin>
</plugins>
</build>
</profile>
<profile>
<id>fatjar</id>
<build>
<plugins>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<version>2.5.3</version>
<configuration>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
</configuration>
<executions>
<execution>
<id>make-fat-jar</id>
<phase>package</phase>
<goals>
<goal>single</goal>
</goals>
<configuration>
<finalName>crawler4j-${project.version}</finalName>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
</profile>
</profiles>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.2</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.5</version>
<configuration>
<excludes>
<exclude>**/*.properties</exclude>
</excludes>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-checkstyle-plugin</artifactId>
<version>2.17</version>
<executions>
<execution>
<id>compile</id>
<phase>compile</phase>
<configuration>
<configLocation>checkstyle.xml</configLocation>
<encoding>UTF-8</encoding>
<consoleOutput>true</consoleOutput>
<failsOnError>true</failsOnError>
<includeTestSourceDirectory>true</includeTestSourceDirectory>
</configuration>
<goals>
<goal>check</goal>
</goals>
</execution>
</executions>
<dependencies>
<dependency>
<groupId>com.puppycrawl.tools</groupId>
<artifactId>checkstyle</artifactId>
<version>7.1</version>
</dependency>
</dependencies>
</plugin>
<plugin>
<groupId>org.jacoco</groupId>
<artifactId>jacoco-maven-plugin</artifactId>
<version>0.7.9</version>
<executions>
<execution>
<id>pre-unit-test</id>
<goals>
<goal>prepare-agent</goal>
</goals>
</execution>
<execution>
<id>post-unit-test</id>
<phase>test</phase>
<goals>
<goal>report</goal>
</goals>
<configuration>
<excludes>
<exclude>**/exceptions/**</exclude>
</excludes>
</configuration>
</execution>
</executions>
</plugin>
<!-- Groovy compiler stuff -->
<plugin>
<groupId>org.codehaus.gmavenplus</groupId>
<artifactId>gmavenplus-plugin</artifactId>
<version>1.5</version>
<executions>
<execution>
<goals>
<goal>addSources</goal>
<goal>addTestSources</goal>
<goal>generateStubs</goal>
<goal>compile</goal>
<goal>testGenerateStubs</goal>
<goal>testCompile</goal>
<goal>removeStubs</goal>
<goal>removeTestStubs</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<groupId>org.codehaus.mojo</groupId>
<artifactId>build-helper-maven-plugin</artifactId>
<version>1.9.1</version>
<executions>
<execution>
<id>add-source</id>
<phase>generate-sources</phase>
<goals>
<goal>add-source</goal>
</goals>
<configuration>
<sources>
<source>src/main/groovy</source>
</sources>
</configuration>
</execution>
<execution>
<id>add-test-source</id>
<phase>generate-test-sources</phase>
<goals>
<goal>add-test-source</goal>
</goals>
<configuration>
<sources>
<source>src/test/groovy</source>
</sources>
</configuration>
</execution>
</executions>
</plugin>
</plugins>
</build>
<dependencies>
<!-- Compile time Dependencies -->
<dependency>
<!-- Logging framework -->
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>${slf4j.version}</version>
</dependency>
<dependency>
<!-- Implementation of slf4j -->
<groupId>ch.qos.logback</groupId>
<artifactId>logback-classic</artifactId>
<version>${logback.version}</version>
<scope>runtime</scope>
</dependency>
<dependency>
<!-- Google's core Java libraries -->
<groupId>com.google.guava</groupId>
<artifactId>guava</artifactId>
<version>${guava.version}</version>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>${apache.http.components.version}</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>com.sleepycat</groupId>
<artifactId>je</artifactId>
<version>${je.version}</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>${apache.tika.version}</version>
</dependency>
<!-- Test Dependencies -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>${junit.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>com.github.tomakehurst</groupId>
<artifactId>wiremock</artifactId>
<version>${wiremock.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.codehaus.groovy</groupId>
<artifactId>groovy-all</artifactId>
<version>${groovy.version}</version>
<scope>test</scope>
</dependency>
<dependency>
<groupId>org.spockframework</groupId>
<artifactId>spock-core</artifactId>
<version>${spock.version}</version>
<scope>test</scope>
</dependency>
</dependencies>
<repositories>
<repository>
<id>oracleReleases</id>
<name>Oracle Released Java Packages</name>
<url>http://download.oracle.com/maven</url>
<layout>default</layout>
</repository>
</repositories>
</project>
<dependency> <groupId>edu.uci.ics</groupId> <artifactId>crawler4j</artifactId> <version>4.3</version> </dependency>
If you think the following crawler4j-4.3.jar downloaded from Maven central repository is inappropriate, such as containing malicious code/tools or violating the copyright, please email , thanks.
Download crawler4j-4.3.jar file