数据仓库项目（第二节）采集数据

Flume采集到Kafka

Flume的安装参考hadoop离线阶段（第十六节—1）flume的介绍、安装、使用和自定义拦截器
Kafka的安装参考Kafka（第一节）Kafka的介绍、Kafka集群搭建和常用kafka命令行

自定义Flume拦截器

1、创建maven工程，pom如下：

<repositories>
    <repository>
        <id>cloudera</id>
        <url>https://repository.cloudera.com/artifactory/cloudera-repos/</url>
    </repository>
</repositories>
<dependencies>
    <dependency>
        <groupId>org.apache.flume</groupId>
        <artifactId>flume-ng-core</artifactId>
        <version>1.6.0-cdh5.14.0</version>
        <scope>provided</scope>
    </dependency>
</dependencies>

<build>
    <plugins>
        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-compiler-plugin</artifactId>
            <version>3.0</version>
            <configuration>
                <source>1.8</source>
                <target>1.8</target>
                <encoding>UTF-8</encoding>
                <!--    <verbal>true</verbal>-->
            </configuration>
        </plugin>

        <plugin>
            <groupId>org.apache.maven.plugins</groupId>
            <artifactId>maven-shade-plugin</artifactId>
            <version>2.4.3</version>
            <executions>
                <execution>
                    <phase>package</phase>
                    <goals>
                        <goal>shade</goal>
                    </goals>
                    <configuration>
                        <minimizeJar>true