You can download crawler4j-4.0.jar in this page.
The Apache Software License, Version 2.0
crawler4j-4.0.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.fetcher.CustomFetchStatus.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.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.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.RobotstxtConfig.class edu.uci.ics.crawler4j.robotstxt.RobotstxtParser.class edu.uci.ics.crawler4j.robotstxt.RobotstxtServer.class edu.uci.ics.crawler4j.robotstxt.RuleSet.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 logback.xml tld-names.zip
crawler4j-4.0.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>4.0</version>
<description>Open Source Web Crawler for Java</description>
<url>http://code.google.com/p/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>
<connection>scm:git:https://crawler4j.googlecode.com/git/</connection>
<developerConnection>scm:git:https://crawler4j.googlecode.com/git/</developerConnection>
<url>https://crawler4j.googlecode.com/git/</url>
</scm>
<developers>
<developer>
<name>Yasser Ganjisaffar</name>
<email>{lastname}@gmail.com</email>
</developer>
<developer>
<name>Avi Hayun</name>
<email>avraham2@gmail.com</email>
</developer>
</developers>
<parent>
<groupId>org.sonatype.oss</groupId>
<artifactId>oss-parent</artifactId>
<version>7</version>
</parent>
<build>
<plugins>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<configuration>
<source>1.7</source>
<target>1.7</target>
</configuration>
<version>2.3.2</version>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-jar-plugin</artifactId>
<version>2.3</version>
<configuration>
<excludes>
<exclude>**/*.properties</exclude>
</excludes>
</configuration>
</plugin>
<!-- generate a source jar -->
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-source-plugin</artifactId>
<version>2.2.1</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>2.9</version>
<executions>
<execution>
<id>attach-javadocs</id>
<goals>
<goal>jar</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
<dependencies>
<!-- Compile time Dependencies -->
<dependency>
<groupId>org.slf4j</groupId>
<artifactId>slf4j-api</artifactId>
<version>1.7.7</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>ch.qos.logback</groupId>
<artifactId>logback-classic</artifactId>
<version>1.1.2</version>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.3.5</version>
<scope>compile</scope>
</dependency>
<dependency>
<groupId>com.sleepycat</groupId>
<artifactId>je</artifactId>
<version>5.0.73</version>
</dependency>
<dependency>
<groupId>org.apache.tika</groupId>
<artifactId>tika-parsers</artifactId>
<version>1.5</version>
</dependency>
<!-- Test Dependencies -->
<dependency>
<groupId>junit</groupId>
<artifactId>junit</artifactId>
<version>4.11</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>4.0</version> </dependency>
If you think the following crawler4j-4.0.jar downloaded from Maven central repository is inappropriate, such as containing malicious code/tools or violating the copyright, please email , thanks.
Download crawler4j-4.0.jar file