spark 操作 JSON数据demo

import org.apache.spark.{SparkConf, SparkContext}

import scala.util.parsing.json.JSON

/**
 * Created with IntelliJ IDEA.
 * User: @别慌
 * Date: 2019-11-24
 * Time: 18:04
 * Description:
 */
object hello {
  def main(args: Array[String]): Unit = {

    // Create spark context
    val conf = new SparkConf()
      .setAppName("WordFreq_Spark")
      .setMaster("local")
   val sc = new SparkContext(conf)
   val do01= sc.textFile("D:\\杂七杂八\\瞎画\\test.json")
    val do02=do01.map(JSON.parseFull)
      println(do02.collect().mkString("\t"))
    do02.foreach (
      {
        case Some(do02) =>println(do02)
        case None => println("unvaild sign")
        case _ =>println("other sign")
      }
    )

    sc.stop()

//   val rdd =  sc.textFile("hdfs://192.168.199.120:9000/words.txt")
//    val wc=rdd.flatMap(_.split(" "))
//      .map(s=>(s,1))
//      .reduceByKey((a,b)=>a+b)
//      .sortBy(_._2,true)
//
//
//    //wc.saveAsTextFile("D:\\")
//
//    for (arg <- wc.collect())
//      print(arg+" ")
//      println()
//    wc.saveAsTextFile("hdfs://192.168.199.120:9000/tai")
//    sc.stop

      }
}

<?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>com.syllabus</groupId>
    <artifactId>chapter-3</artifactId>
    <version>1.0-SNAPSHOT</version>


    <!-- 额外指定可以通过如下链接下载Jar包依赖 -->
    <repositories>
        <repository>
            <id>1</id>
            <name>MAVEN-CENTRE</name>
            <url>http://central.maven.org/maven2/</url>
        </repository>
    </repositories>

    <!-- 添加相关依赖 -->
    <dependencies>
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.11.12</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/org.apache.spark/spark-core -->
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-core_2.11</artifactId>
            <version>2.4.4</version>
            <!-- 排除Spark依赖中关于Hadoop和Scala的依赖，以便于添加自已的版本 -->
            <exclusions>
                <exclusion>
                    <groupId>org.apache.hadoop</groupId>
                    <artifactId>hadoop-client</artifactId>
                </exclusion>

                <exclusion>
                    <groupId>org.scala-lang</groupId>
                    <artifactId>scala-library</artifactId>
                </exclusion>
            </exclusions>
        </dependency>



        <!-- 添加自己的Hadoop版本 -->
        <dependency>
            <groupId>org.apache.hadoop</groupId>
            <artifactId>hadoop-client</artifactId>
            <version>2.9.0</version>
        </dependency>
    </dependencies>

    <!-- 编译Scala代码的插件-->
    <build>
        <plugins>
            <plugin>
                <groupId>org.scala-tools</groupId>
                <artifactId>maven-scala-plugin</artifactId>
                <version>2.15.2</version>
                <executions>
                    <execution>
                        <id>scala-compile-first</id>
                        <goals>
                            <goal>compile</goal>
                        </goals>
                        <configuration>
                            <includes>
                                <include>**/*.scala</include>
                            </includes>
                        </configuration>
                    </execution>
                    <execution>
                        <id>scala-test-compile</id>
                        <goals>
                            <goal>testCompile</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>
</project>

View Code

提交到集群中的时候，shell 代码为
./bin/spark-submit --class hello --master spark://192.168.199.120:7077 --executor-memory 1G --total-executor-cores 3 comspark.jar ;


这里 spark端口为  7070
hdfs端口为 9000