1. 安装启动检查Mysql服务。
##netstat -tunlp (3306)
cd /usr/local/hive/lib
ls mysql*
cp mysql-connector-java-5.1.40-bin.jar /usr/local/spark/jars/
cd /usr/local/spark/jars/
ls mysql*
netstat -tunpl
2. spark 连接mysql驱动程序。
##–cp /usr/local/hive/lib/mysql-connector-java-5.1.40-bin.jar /usr/local/spark/jars
3. 启动 Mysql shell，新建数据库spark，表student。
create database spark;#创建数据库
use spark;#使用数据库
create table student(id int(4),name char(20),gender char(4),age int (4));#创建表
insert into student values(1,‘Xueqian‘,‘F‘,23);
insert into student values(2,‘Weiliang‘,‘M‘,24);#插入两条数据
select * from student;#查询数据
4. spark读取MySQL数据库中的数据
##spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/spark?useSSL=false") ... .load()
jdbcDF=spark.read.format("jdbc")\
... .option("driver","com.mysql.jdbc.Driver")\
... .option("url","jdbc:mysql://localhost:3306/spark?useSSL=false")\
... .option("dbtable","student")\
... .option("user","root")\
... .option("password","hadoop")\
... .load()
jdbcDF.show()
5. spark向MySQL数据库写入数据
##studentDF.write.format(‘jdbc’).option(…).mode(‘append’).save()
>>> from pyspark.sql.types import Row
>>> from pyspark.sql.types import StructType
>>> from pyspark.sql.types import StructField
>>> from pyspark.sql.types import StringType
>>> from pyspark.sql.types import IntegerType
>>> studentRDD = spark.sparkContext.parallelize(["3 zhao M 26","4 wang M 27"]).map(lambda line:line.split(" "))
>>> rowRDD = studentRDD.map(lambda p:Row(p[1].strip(),p[2].strip(),int(p[3])))
>>> schema = StructType([StructField("name",StringType(),True),StructField("gender",StringType(),True),StructField("age",IntegerType(),True)])
>>> studentDF=spark.createDataFrame(rowRDD,schema)
>>> prop={}
>>> prop[‘user‘]=‘root‘
>>> prop[‘password‘]=‘123456‘
>>> prop[‘driver‘]=‘com.mysql.jdbc.Driver‘
>>> studentDF.write.jdbc("jdbc:mysql://localhost:3306/spark?useSSL=false",‘student‘,‘append‘,prop)