1.代码
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.SparkConf
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
/**
* @author xxx_xx
* @date 2018/4/17
*/
object KaflaWordCount {
def main(args: Array[String]): Unit = {
//在yarn上运行
val conf = new SparkConf().setAppName("kafka_wordcount").setMaster("yarn");
val ssc = new StreamingContext(conf, Seconds(5));
val kafkaParams = Map[String, Object](
"bootstrap.servers" -> "centos-1:9092",
"key.deserializer" -> classOf[StringDeserializer],
"value.deserializer" -> classOf[StringDeserializer],
"group.id" -> "test",
"auto.offset.reset" -> "latest",
"enable.auto.commit" -> (false: java.lang.Boolean)
)
val topics = Array("data-syn")
val stream = KafkaUtils.createDirectStream[String, String](
ssc,
PreferConsistent,
Subscribe[String, String](topics, kafkaParams)
)
stream.map(record => (record.key, record.value)).print()
ssc.start();
ssc.awaitTermination();
}
}
2.pom.xml这里为了避免服务器上类找不到,直接把依赖打上,不推荐
<?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>
<groupId>com.tech.data</groupId>
<artifactId>spark-test</artifactId>
<version>1.0-SNAPSHOT</version>
<properties>
<spark.version>2.3.0</spark.version>
<scala.version>2.11</scala.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.version}</artifactId>
<version>${spark.version}</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming_${scala.version}</artifactId>
<version>2.3.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
<version>2.3.0</version>
</dependency>
</dependencies>
<build>
<plugins>
<plugin>
<groupId>org.scala-tools</groupId>
<artifactId>maven-scala-plugin</artifactId>
<version>2.15.2</version>
<executions>
<execution>
<goals>
<goal>compile</goal>
<goal>testCompile</goal>
</goals>
</execution>
</executions>
</plugin>
<plugin>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.6.0</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-surefire-plugin</artifactId>
<version>2.19</version>
<configuration>
<skip>true</skip>
</configuration>
</plugin>
<plugin>
<artifactId>maven-assembly-plugin</artifactId>
<configuration>
<appendAssemblyId>false</appendAssemblyId>
<descriptorRefs>
<descriptorRef>jar-with-dependencies</descriptorRef>
</descriptorRefs>
<archive>
<manifest>
<!-- 此处指定main方法入口的class -->
<mainClass>KaflaWordCount</mainClass>
</manifest>
</archive>
</configuration>
<executions>
<execution>
<id>make-assembly</id>
<phase>package</phase>
<goals>
<goal>assembly</goal>
</goals>
</execution>
</executions>
</plugin>
</plugins>
</build>
</project>
3.提交命令
spark-submit --master yarn --class KaflaWordCount spark-test-1.0-SNAPSHOT.jar
4.测试输入
bin/kafka-console-producer.sh --broker-list centos-3:9092 --topic data-syn