1. 安裝並配置zk
2. 安裝並配置Kafka
3. 啟動zk
4. 啟動Kafka
5. 建立topic

bin/kafka-topics.sh --create --zookeeper node1.itcast.cn:2181,node2.itcast.cn:2181 \

--replication-factor 3 --partitions 3 --topic urlcount

package cn.itcast.spark.streaming

package cn.itcast.spark

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

object UrlCount {
  val updateFunc = (iterator: Iterator[(String, Seq[Int], Option[Int])]) => {
    iterator.flatMap{case(x,y,z)=> Some(y.sum + z.getOrElse(0)).map(n=>(x, n))}
  }

  def main(args: Array[String]) {
    //接收命令列中的引數
    val Array(zkQuorum, groupId, topics, numThreads, hdfs) = args
    //建立SparkConf並設定AppName
    val conf = new SparkConf().setAppName("UrlCount")
    //建立StreamingContext
    val ssc = new StreamingContext(conf, Seconds(2))
    //設定檢查點
    ssc.checkpoint(hdfs)
    //設定topic資訊
    val topicMap = topics.split(",").map((_, numThreads.toInt)).toMap
    //重Kafka中拉取資料建立DStream
    val lines = KafkaUtils.createStream(ssc, zkQuorum ,groupId, topicMap, StorageLevel.MEMORY_AND_DISK).map(_._2)
    //切分資料，擷取使用者點選的url
    val urls = lines.map(x=>(x.split(" ")(6), 1))
    //統計URL點選量
    val result = urls.updateStateByKey(updateFunc, new HashPartitioner(ssc.sparkContext.defaultParallelism), true)
    //將結果列印到控制檯
    result.print()
    ssc.start()
    ssc.awaitTermination()
  }
}