SparkStreaming整合Kafka代碼案例1

代碼

import org.apache.kafka.clients.consumer.ConsumerRecord
import org.apache.kafka.common.serialization.StringDeserializer
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{CanCommitOffsets, ConsumerStrategies, HasOffsetRanges, KafkaUtils, LocationStrategies}
import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object SparkStreamingKafka {

    def main(args: Array[String]): Unit = {
        val ssc = new StreamingContext(new SparkContext(new SparkConf().setAppName("kafka").setMaster("local[6]")), Seconds(5))

        ssc.sparkContext.setLogLevel("warn")

        // 消費kafka數據
        val topic = Array("spark_kafka")

        // kafka參數
        val kafkaParams = Map[String, Object](
            //指明kafka borkerlist
            "bootstrap.servers" -> "node01:9092,node02:9092,node03:9092",
            //kafka message key反序列化器
            "key.deserializer" -> classOf[StringDeserializer],
            //kafka message value反序列化器
            "value.deserializer" -> classOf[StringDeserializer],
            //消費者組
            "group.id" -> "kafka_spark_10",
            //指明從什麼位置開始消費kafka ,latest 從最新的offset開始消費， earliest 從小的offset開始消費
            "auto.offset.reset" -> "latest",
            //是否自動提交offset
            "enable.auto.commit" -> (false: java.lang.Boolean)
        )

        val ids: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream[String, String](ssc, LocationStrategies.PreferConsistent, ConsumerStrategies.Subscribe[String,String](topic, kafkaParams))

        ids.foreachRDD(rdd => {
            // 打印
            rdd.map(_.value()).flatMap(_.split(" ")).map(_ -> 1).reduceByKey(_ + _).foreach(println(_))
            // 獲取offset
            val offset = rdd.asInstanceOf[HasOffsetRanges].offsetRanges
            //提交offset
            ids.asInstanceOf[CanCommitOffsets].commitAsync(offset)
        })

        //4、啓動streaming
        ssc.start()
        //5、阻塞主線程
        ssc.awaitTermination()

    }

}

maven依賴

    <properties>
        <scala.version>2.11.8</scala.version>
        <spark.version>2.2.0</spark.version>
        <slf4j.version>1.7.16</slf4j.version>
        <log4j.version>1.2.17</log4j.version>
    </properties>

    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.6.0</version>
        </dependency>

        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>jcl-over-slf4j</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-api</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>org.slf4j</groupId>
            <artifactId>slf4j-log4j12</artifactId>
            <version>${slf4j.version}</version>
        </dependency>
        <dependency>
            <groupId>log4j</groupId>
            <artifactId>log4j</artifactId>
            <version>${log4j.version}</version>
        </dependency>

        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>4.10</version>
            <scope>provided</scope>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-hive_2.11</artifactId>
            <version>${spark.version}</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-streaming -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.11</artifactId>
            <version>2.2.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-sql-kafka-0-10_2.11</artifactId>
            <version>2.2.0</version>
        </dependency>

        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.11</artifactId>
            <version>2.2.0</version>
        </dependency>
    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>

        <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>
                </configuration>
            </plugin>

            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.0</version>
                <executions>
                    <execution>
                        <goals>
                            <goal>compile</goal>
                            <goal>testCompile</goal>
                        </goals>
                        <configuration>
                            <args>
                                <arg>-dependencyfile</arg>
                                <arg>${project.build.directory}/.scala_dependencies</arg>
                            </args>
                        </configuration>
                    </execution>
                </executions>
            </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-shade-plugin</artifactId>
                <version>3.1.1</version>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>shade</goal>
                        </goals>
                        <configuration>
                            <filters>
                                <filter>
                                    <artifact>*:*</artifact>
                                    <excludes>
                                        <exclude>META-INF/*.SF</exclude>
                                        <exclude>META-INF/*.DSA</exclude>
                                        <exclude>META-INF/*.RSA</exclude>
                                    </excludes>
                                </filter>
                            </filters>
                            <transformers>
                                <transformer implementation="org.apache.maven.plugins.shade.resource.ManifestResourceTransformer">
                                    <mainClass></mainClass>
                                </transformer>
                            </transformers>
                        </configuration>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>