from pyspark.sql import SQLContext
from pyspark import SparkContext, SparkConf

import os

SUBMIT_ARGS = "--packages mysql:mysql-connector-java:5.1.39 pyspark-shell"
os.environ["PYSPARK_SUBMIT_ARGS"] = SUBMIT_ARGS

conf = SparkConf().setAppName("Flat obs Data flow")\
    .setMaster("local[*]")
sc = SparkContext(conf = conf)

sqlContext = SQLContext(sc)

source_df = sqlContext.read\
    .format('jdbc')\
    .options(
        url = 'jdbc:mysql://localhost/openmrs',
        driver = 'com.mysql.jdbc.Driver',
        dbtable = 'users',
        user = 'root',
        password = 'password')\
    .load()

source_df.printSchema()