scala-mysql

package streaming.kafka

import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

object TestFileOutFromKafka {
  def main(args: Array[String]): Unit = {
    // 设定本地测试环境
    System.setProperty("HADOOP_USER_NAME", "root")

    val conf: SparkConf = new SparkConf().setAppName("TestFile").setMaster("local[2]")

    val sc = new SparkContext(conf)

    val scc = new StreamingContext(sc, Seconds(2))

    val kafkaParams = Map(
      ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> "master:9092,worker1:9092,worker2:9092",
      ConsumerConfig.GROUP_ID_CONFIG -> "streamingKafka",
      "key.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer",
      "value.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer"
    )

    val dStream: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream(
      scc,
      LocationStrategies.PreferConsistent, //位置策略
      ConsumerStrategies.Subscribe(Set("test"), kafkaParams) // 消费策略：主题列表与连接kafka的参数信息
    )

    val map = dStream.map(_.value())

    val wordAndOne = map.flatMap(_.split(" "))

    // 将每个单词进行标记
    val value = wordAndOne.map(x => (x, 1))

    // 统计每个单词出现的次数
    val result = value.reduceByKey(_ + _)

//    dStream.saveAsTextFiles("file:///f:/", "txt")
    result.saveAsTextFiles("hdfs://192.168.203.100:9000/streaming", "txt")

    scc.start()

    scc.awaitTermination()
  }

}

package stream.mysql

import java.sql.DriverManager

import org.apache.kafka.clients.consumer.{ConsumerConfig, ConsumerRecord}
import org.apache.spark.streaming.dstream.InputDStream
import org.apache.spark.streaming.kafka010.{ConsumerStrategies, KafkaUtils, LocationStrategies}
import org.apache.spark.streaming.{Seconds, StreamingContext}
import org.apache.spark.{SparkConf, SparkContext}

object InputMysqlWithKafka {

  def main(args: Array[String]): Unit = {
    val conf = new SparkConf().setAppName("ss_kafka_tomysql").setMaster("local[2]")

    val context = new SparkContext(conf)

    context.setLogLevel("WARN")

    val sc = new StreamingContext(context, Seconds(3))

    val kafkaParams = Map(
      ConsumerConfig.BOOTSTRAP_SERVERS_CONFIG -> "master:9092,worker1:9092,worker2:9092",
      ConsumerConfig.GROUP_ID_CONFIG -> "streamingKafka",
      "key.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer",
      "value.deserializer" -> "org.apache.kafka.common.serialization.StringDeserializer"
    )

    val dStream: InputDStream[ConsumerRecord[String, String]] = KafkaUtils.createDirectStream(
      sc,
      LocationStrategies.PreferConsistent, //位置策略
      ConsumerStrategies.Subscribe(Set("test"), kafkaParams) // 消费策略：主题列表与连接kafka的参数信息
    )

    val map = dStream.map(_.value())

    val wordAndOne = map.flatMap(_.split(" "))

    // 将每个单词进行标记
    val value = wordAndOne.map(x => (x, 1))

    // 统计每个单词出现的次数
    val res = value.reduceByKey(_ + _)
    res.print()
    //    将结果输出到mysql中
    // rdd：表示统计之后的数据
    res.foreachRDD(
      rdd => {
        // 使用foreachPartitions将数据写入iteration
        rdd.foreachPartition(
          partition => {
            var url = "jdbc:mysql://localhost:3306/spark_assi"
            var userName = "root"
            var passwd = "baidu123"
            // 加载驱动
            Class.forName("com.mysql.cj.jdbc.Driver")
            val conn = DriverManager.getConnection(url, userName, passwd)
            print("连接成功")
            conn.setAutoCommit(false)
            val statement = conn.createStatement()

            // 遍历获取的数据写入数据库
            partition.foreach(record => {
              statement.addBatch("insert into Count values('" + record._1 + "','" + record._2 + "')")
            })

            // 执行并提交
            statement.executeBatch()
            conn.commit()
            conn.close()
            print("------------- 写入")

          }
        )
      }
    )
    sc.start()
    sc.awaitTermination()

    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>org.example</groupId>
    <artifactId>w13_w12e_sparkStream</artifactId>
    <version>1.0-SNAPSHOT</version>

    <dependencies>
        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming_2.12</artifactId>
            <version>3.2.3</version>
            <scope>compile</scope>
        </dependency>
        <!--         https://mvnrepository.com/artifact/org.scala-lang/scala-library -->
        <dependency>
            <groupId>org.scala-lang</groupId>
            <artifactId>scala-library</artifactId>
            <version>2.12.15</version>
        </dependency>
        <dependency>
            <groupId>junit</groupId>
            <artifactId>junit</artifactId>
            <version>3.8.1</version>
            <scope>test</scope>
        </dependency>
        <!-- https://mvnrepository.com/artifact/org.scalafx/scalafx -->
        <dependency>
            <groupId>org.scalafx</groupId>
            <artifactId>scalafx_2.12</artifactId>
            <version>15.0.1-R21</version>
        </dependency>

        <!-- https://mvnrepository.com/artifact/com.mysql/mysql-connector-j -->
        <dependency>
            <groupId>com.mysql</groupId>
            <artifactId>mysql-connector-j</artifactId>
            <version>8.0.33</version>
        </dependency>


        <dependency>
            <groupId>org.apache.spark</groupId>
            <artifactId>spark-streaming-kafka-0-10_2.12</artifactId>
            <version>3.2.3</version>
        </dependency>
        <!-- https://mvnrepository.com/artifact/net.sf.json-lib/json-lib -->
        <dependency>
            <groupId>net.sf.json-lib</groupId>
            <artifactId>json-lib</artifactId>
            <version>2.4</version>
            <classifier>jdk15</classifier>	<!-- 就是这句 -->
        </dependency>
        <dependency>
            <groupId>org.apache.commons</groupId>
            <artifactId>commons-pool2</artifactId>
            <version>2.11.1</version>
        </dependency>
        <dependency>
            <groupId>redis.clients</groupId>
            <artifactId>jedis</artifactId>
            <version>3.2.0</version>
        </dependency>
        <dependency>
            <groupId>com.alibaba</groupId>
            <artifactId>fastjson</artifactId>
            <version>1.2.47</version>
        </dependency>
        <dependency>
            <groupId>com.typesafe</groupId>
            <artifactId>config</artifactId>
            <version>1.3.1</version>
        </dependency>

    </dependencies>

    <build>
        <sourceDirectory>src/main/scala</sourceDirectory>
        <testSourceDirectory>src/test/scala</testSourceDirectory>
        <plugins>

                        <plugin>
                            <groupId>net.alchim31.maven</groupId>
                            <artifactId>scala-maven-plugin</artifactId>
                            <version>3.2.2</version>
                        </plugin>

            <plugin>
                <groupId>org.apache.maven.plugins</groupId>
                <artifactId>maven-assembly-plugin</artifactId>
                <version>2.4</version>
                <configuration>
                    <descriptorRefs>
                        <descriptorRef>jar-with-dependencies</descriptorRef>
                    </descriptorRefs>
                    <archive>
                        <manifest>
                            <mainClass>com.your-package.MainClass</mainClass>
                        </manifest>
                    </archive>
                </configuration>
                <executions>
                    <execution>
                        <phase>package</phase>
                        <goals>
                            <goal>single</goal>
                        </goals>
                    </execution>
                </executions>
            </plugin>
        </plugins>
    </build>


</project>

mkdir /opt/kafka-3.2.3/kdata

启动kafka

./kafka-server-start.sh -daemon …/config/server.properties

创建主题 stu

./kafka-topics.sh --bootstrap-server master:9092,worker1:9092,worker2:9092 --create --topic stu --partitions 3 --replication-factor 3

查看主题列表

./kafka-topics.sh --bootstrap-server master:9092,worker1:9092,worker2:9092 --list
生产者
./kafka-console-producer.sh --bootstrap-server master:9092,worker1:9092,worker2:9092 --topic stu
错误数据用ctrl+删除
消费者
./kafka-console-consumer.sh --bootstrap-server master:9092 --topic stu --from-beginning