spark连接mysql数据库
安装启动检查Mysql服务。
spark 连接mysql驱动程序。
pyspark --jars /usr/local/spark/jars/mysql-connector-java-8.0.25.jar --driver-class-path /usr/local/spark/jars/mysql-connector-java-8.0.25.jar
启动 Mysql shell，新建数据库spark，表student。
create database spark;
use spark;
create table student (id int(4), name char(20), gender char(4), age int(4));
alter table student change id id int auto_increment primary key;
insert into student values(1,‘Xueqian‘,‘F‘,23);
insert into student values(2,‘Weiliang‘,‘M‘,24);
select * from student;
spark读取MySQL数据库中的数据
jdbcDF = spark.read.format("jdbc").option("url", "jdbc:mysql://localhost:3306/spark").option("driver","com.mysql.jdbc.Driver").option("dbtable", "student").option("user", "root").option("password", "123456").load()
jdbcDF.show()
spark向MySQL数据库写入数据
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 Rongcheng M 26","4 Guanhua M 27"]).map(lambda line : line.split(" "))
//下面要设置模式信息
schema = StructType([StructField("name", StringType(), True),StructField("gender", StringType(), True),StructField("age",IntegerType(), True)])
rowRDD = studentRDD.map(lambda p : Row(p[1].strip(), p[2].strip(),int(p[3])))
//建立起Row对象和模式之间的对应关系，也就是把数据和模式对应起来
studentDF = spark.createDataFrame(rowRDD, schema)
prop = {}
prop[‘user‘] = ‘root‘
prop[‘password‘] = ‘hadoop‘
prop[‘driver‘] = "com.mysql.jdbc.Driver"
studentDF.write.jdbc("jdbc:mysql://localhost:3306/spark",‘student‘,‘append‘, prop)
select * from student;