该数据集都为:“http://bigdata.edu360.cn/laozhou” 这个样子,要求的就是最受欢迎的老师
分组TOPN算法:

object FavTeacher {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("FavTeacher").setMaster("local")
    val sc = new SparkContext(conf)
    //指定以后从哪里读取数据
    val lines = sc.textFile(args(0))
    //整理数据
    val teacherAndOne = lines.map(line => {
      //val line = "http://bigdata.edu360.cn/laozhou"
      val conSubject = line.split("/")(2)
      val subject =conSubject.split("[.]")(0)
      val teacher = line.split("/")(3)
      (teacher, 1)
    })
    //聚合
    val reduced = teacherAndOne.reduceByKey(_+_)
    //排序
    val sorted = reduced.sortBy(_._2, false)
    //触发Action执行计算
    val result = sorted.collect()
    //打印
    println(result.toBuffer)
    sc.stop()
  }
}