大数据spark整合kafka

<!-- spark steaming的依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.2.0</version>
        </dependency>

        <!-- sparkSteaming跟Kafka整合的依赖 -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-8_2.11</artifactId>
            <version>2.2.0</version>
        </dependency>

启动zk

在shell给三个虚拟机发送一下命令启动zk
cd /root/apps/zookeeper
bin/zkServer.sh start

启动zkafka
依次在各节点上启动kafka
cd /export/servers/kafka
bin/kafka-server-start.sh  config/server.properties

创建topic
/export/servers/kafka
bin/kafka-topics.sh --create --zookeeper mini1:2181 --replication-factor 1 --partitions 1 --topic xiaoniuabc

发送消息
bin/kafka-console-producer.sh --broker-list mini1:9092 --topic xiaoniuabc