sparkStreaming与Kafka整合

./bin/zookeeper-server-start.sh config/zookeeper.properties &

bin/kafka-server-start.sh config/server.properties &

./kafka-topics.sh  --create --zookeeper 192.168.77.133:2181 \ --replication-factor 1\ --partitions 1\ --topic yangsy

./kafka-console-producer.sh --broker-list 192.168.77.133:9092 --topic yangsy

import org.apache.spark.SparkConf
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.kafka.KafkaUtils
import org.apache.spark.streaming.{Seconds, StreamingContext}



/**
 * Created by root on 11/28/15.
 */
object SparkStreaming {
  def main(args: Array[String]) {
/*    val sparkConf = new SparkConf().setMaster("local").setAppName("cocapp")
      .set("spark.executor.memory", "1g")
    val sc = new StreamingContext(sparkConf, Seconds(20))
    val lines = sc.textFileStream("/usr/local/spark-1.4.0-bin-2.5.0-cdh5.2.1/streaming")
    val words = lines.flatMap(_.split(" "))
    val wordCounts = words.map(x => (x, 1)).reduceByKey(_ + _)
    wordCounts.print()
    sc.start()
    sc.awaitTermination()*/
　　//zookeeper的地址
    val zkQuorum = "192.168.77.133:2181"
   //group_id可以通过kafka的conf下的consumer.properties中查找
    val group ="test-consumer-group"
　　//创建的topic 可以是一个或多个
    val topics = "yangsy"
    val sparkConf = new SparkConf().setMaster("local").setAppName("cocapp").set("spark.executor.memory", "1g")
    val sc = new StreamingContext(sparkConf, Seconds(2))
    val numThreads = 2
    val topicpMap = topics.split(",").map((_, numThreads.toInt)).toMap
    //StorageLevel.MEMORY_AND_DISK_SER为存储的级别
    val lines  = KafkaUtils.createStream(sc, zkQuorum, group, topicpMap, StorageLevel.MEMORY_AND_DISK_SER).map(_._2)
    //对于收到的消息进行wordcount
    val words = lines.flatMap(_.split(" "))
    val pairs = words.map(word => (word, 1))
    val wordCounts = pairs.reduceByKey(_ + _)
    wordCounts.print()
    sc.start()
    sc.awaitTermination()

  }
}