package student
import java.net.URL
import org.apache.spark.rdd.RDD
import org.apache.spark.{SparkConf, SparkContext}
object StuObject {
  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("stu").setMaster("local")
    val sc = new SparkContext(conf)
    val data: RDD[String] = sc.textFile("D:\\bigdata\\project\\scala2\\src\\main\\scala\\student\\access.txt")
    val maps = data.map(t=>{
      val url = t.split("\t")
      val host: String = new URL(url(1)).getHost
      val strings: Array[String] = host.split("\\.")
      (strings(0),1)
    })
    val redy = maps.reduceByKey(_+_)
    val sor = redy.sortBy(_._2,false)
    val tak = sor.take(2)
    tak.toBuffer.foreach(println)
  }
}
数据
20161123101523  http://java.learn.com/java/javaee.shtml
20161123101523 http://java.learn.com/java/javaee.shtml
20161123101523 http://ui.learn.com/ui/video.shtml
20161123101523 http://bigdata.learn.com/bigdata/teacher.shtml
20161123101523 http://android.learn.com/android/video.shtml
20161123101523 http://h5.learn.com/h5/teacher.shtml
20161123101523 http://h5.learn.com/h5/course.shtml
20161123101523 http://bigdata.learn.com/bigdata/teacher.shtml
20161123101523 http://java.learn.com/java/video.shtml
20161123101523 http://bigdata.learn.com/bigdata/teacher.shtml
20161123101523 http://ui.learn.com/ui/course.shtml
20161123101523 http://bigdata.learn.com/bigdata/teacher.shtml
20161123101523 http://h5.learn.com/h5/course.shtml
20161123101523 http://java.learn.com/java/video.shtml
20161123101523 http://ui.learn.com/ui/video.shtml
20161123101523 http://h5.learn.com/h5/course.shtml
20161123101523 http://h5.learn.com/h5/teacher.shtml
20161123101523 http://bigdata.learn.com/bigdata/teacher.shtml
20161123101523 http://bigdata.learn.com/bigdata/video.shtml
pom.xml
<?xml version="1.0" encoding="UTF-8"?>
<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/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>
    <groupId>scala</groupId>
    <artifactId>scala</artifactId>
    <version>1.0-SNAPSHOT</version>
    <!--<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>-->
    <!--</properties>-->
    <!--<dependencies>-->
    <!--<dependency>-->
    <!--<groupId>org.scala-lang</groupId>-->
    <!--<artifactId>scala-library</artifactId>-->
    <!--<version>${scala.version}</version>-->
    <!--</dependency>-->
    <!--<!–<dependency>–>-->
    <!--<!–<groupId>org.scala-lang</groupId>–>-->
    <!--<!–<artifactId>scala-actors</artifactId>–>-->
    <!--<!–<version>2.11.8</version>–>-->
    <!--<!–</dependency>–>-->
    <!--<dependency>-->
    <!--<groupId>com.typesafe.akka</groupId>-->
    <!--<artifactId>akka-actor_2.11</artifactId>-->
    <!--<version>2.3.14</version>-->
    <!--</dependency>-->
    <!--<dependency>-->
    <!--<groupId>com.typesafe.akka</groupId>-->
    <!--<artifactId>akka-remote_2.11</artifactId>-->
    <!--<version>2.3.14</version>-->
    <!--</dependency>-->
    <!--</dependencies>-->
    <properties>
        <maven.compiler.source>1.8</maven.compiler.source>
        <maven.compiler.target>1.8</maven.compiler.target>
        <encoding>UTF-8</encoding>
        <scala.version>2.10.6</scala.version>
        <spark.version>1.6.3</spark.version>
        <hadoop.version>2.6.4</hadoop.version>
    </properties>
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>${scala.version}</version>
        </dependency>
        <dependency>
            <groupId>com.typesafe.akka</groupId>
            <artifactId>akka-actor_2.10</artifactId>
            <version>2.3.14</version>
        </dependency>
        <dependency>
            <groupId>com.typesafe.akka</groupId>
            <artifactId>akka-remote_2.10</artifactId>
            <version>2.3.14</version>
        </dependency>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.10</artifactId>
            <version>${spark.version}</version>
        </dependency>
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>${hadoop.version}</version>
        </dependency>
        <dependency>
            <groupId>mysql</groupId>
            <artifactId>mysql-connector-java</artifactId>
            <version>5.1.38</version>
        </dependency>
    </dependencies>
    <build>
        <sourceDirectory>src/main/spark</sourceDirectory>
        <plugins>
            <plugin>
                <groupId>net.alchim31.maven</groupId>
                <artifactId>scala-maven-plugin</artifactId>
                <version>3.2.2</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>2.4.3</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></project>