pyspark 操作mysql_pyspark 连接mysql

1：载mysql-connector 放入 jars下

2：在spark-env.sh中 配置EXTRA_SPARK_CLASSPATH环境变量

3:export SPARK_CLASSPATH=/opt/spark/spark-2.4.0-bin-hadoop2.7/jars

from pyspark.sql import SparkSession

from pyspark.sql import SQLContext

sc = SparkSession.builder.appName("Python Spark SQL basic example")\

.config('spark.some.config,option0','some-value')\

.getOrCreate()

ctx = SQLContext(sc)

jdbcDf=ctx.read.format("jdbc").options(url="jdbc:mysql://localhost:3306/stock",

driver="com.mysql.jdbc.Driver",

dbtable="(SELECT * FROM stock) tmp",user="root",

password="0845").load()

print(jdbcDf.printSchema())

print(jdbcDf.show())

root

|-- open: double (nullable = true)

|-- high: double (nullable = true)