Example #1
0
def getMysqlConn(url, driver, dbtable, user, password):
    print(" ############ inside getMysqlConn")
    df_dataset = sqlContext.read.format("jdbc").options(
        url=url, driver=driver, dbtable=dbtable, user=user,
        password=password).load()

    return df_dataset


try:
    conf = SparkConf().setAppName("Spark_ETL")
    sc = SparkContext(conf=conf)
    sqlContext = HiveContext(sc)

    conf = ConfigParser.ConfigParser()
    conf.read("param.config")

    url = conf.get("MySQL", "url")
    driver = conf.get("MySQL", "driver")
    dbtable_A = conf.get("MySQL", "dbtable_A")
    dbtable_B = conf.get("MySQL", "dbtable_B")
    user = conf.get("MySQL", "user")
    password = conf.get("MySQL", "password")
    HiveSchema = conf.get("HiveSchema", "schema")

    print(url, driver, dbtable_A, dbtable_B, user, password)

    #check if we have received arguments as inputs to the script
    strWeek = sys.argv[1] if len(sys.argv) == 2 else "all_weeks"

    #logic to derive where clause based on input provided