5. SparkStreaming消费kafka

1. 新建工程

2. 导入maven依赖

<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/maven-v4_0_0.xsd">
    <parent>
        <artifactId>spark-train</artifactId>
        <groupId>com.hp</groupId>
        <version>1.0</version>
    </parent>
    <modelVersion>4.0.0</modelVersion>
    <artifactId>iqiyi-log</artifactId>
    <inceptionYear>2008</inceptionYear>
    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.1.0</spark.version>
    </properties>


    <pluginRepositories>
        <pluginRepository>
            <id>alimaven</id>
            <name>aliyun maven</name>
            <url>http://maven.aliyun.com/nexus/content/repositories/central/</url>
        </pluginRepository>
    </pluginRepositories>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.kafka</groupId>
            <artifactId>kafka_2.11</artifactId>
            <version>2.1.1</version>
            <exclusions>
                <exclusion>
                    <groupId>com.fasterxml.jackson.core</groupId>
                    <artifactId>*</artifactId>
                </exclusion>
            </exclusions>
        </dependency>

        <dependency>
            <groupId>com.fasterxml.jackson.core</groupId>
            <artifactId>jackson-core</artifactId>
            <version>2.6.6</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0-cdh5.7.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-client</artifactId>
            <version>1.2.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.hbase</groupId>
            <artifactId>hbase-server</artifactId>
            <version>1.2.0</version>
        </dependency>

    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
                <configuration>
                    <scalaVersion>${scala.version}</scalaVersion>
                    <args>
                        <arg>-target:jvm-1.5</arg>
                    </args>
                </configuration>
            </plugin>
            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-eclipse-plugin</artifactId>
                <configuration>
                    <downloadSources>true</downloadSources>
                    <buildcommands>
                        <buildcommand>ch.epfl.lamp.sdt.core.scalabuilder</buildcommand>
                    </buildcommands>
                    <additionalProjectnatures>
                        <projectnature>ch.epfl.lamp.sdt.core.scalanature</projectnature>
                    </additionalProjectnatures>
                    <classpathContainers>
                        <classpathContainer>org.eclipse.jdt.launching.JRE_CONTAINER</classpathContainer>
                        <classpathContainer>ch.epfl.lamp.sdt.launching.SCALA_CONTAINER</classpathContainer>
                    </classpathContainers>
                </configuration>
            </plugin>
        </plugins>
    </build>

</project>

3. 编写代码消费Kafka

package com.hp.kafka
import com.hp.kafka.dao.{CategoryClickCountDAO, CategorySearchClickCountDAO}
import com.hp.kafka.dao.entity.{CategoryClickCount, CategorySearchClickCount}
import com.hp.kafka.utils.DateUtils
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.streaming.kafka010.KafkaUtils
import org.apache.spark.streaming.kafka010.ConsumerStrategies.Subscribe
import org.apache.spark.streaming.kafka010.LocationStrategies.PreferConsistent

import scala.collection.mutable.ListBuffer

object StatStreamingApp {

  def main(args: Array[String]): Unit = {
    val ssc = new StreamingContext("local[1]", "StatStreamingApp", Seconds(5))

    val kafkaParams = Map[String, Object](
      "bootstrap.servers" -> "localhost:9092",
      "key.deserializer" -> classOf[StringDeserializer],
      "value.deserializer" -> classOf[StringDeserializer],
      "group.id" -> "example",
      "auto.offset.reset" -> "latest",
      "enable.auto.commit" -> (false: java.lang.Boolean)
    )

    val topics = List("flumeTopic").toSet
    val logs = KafkaUtils.createDirectStream[String, String](
      ssc,
      PreferConsistent,
      Subscribe[String, String](topics, kafkaParams)
    ).map(_.value)
    # logs中已经获取到kafka中的数据
    ssc.start()
    ssc.awaitTermination()
  }

}