root@slave0:~# cat /root/stest.py
#
# Spark job to bin data in WebMercator Spatial Reference
# The bin is a hexagon with a width of 100 meters
#
from pyspark import SparkContext
import datetime
from pyspark.sql import SQLContext
year = datetime.date.today().strftime("%Y")
moy = datetime.date.today().strftime("%B")
dom = datetime.date.today().strftime("%d")
hour = str(datetime.datetime.now().hour)
minute = str(datetime.datetime.now().minute)
opstring = "hdfs:///tmp/" + year + "/" + moy + "/" + dom + "/" + hour + "/" + minute
sc = SparkContext()
sqlContext = SQLContext(sc)
#query = "(select * from NE.INTER_APP_EVENT where objectid = (Select MAX(Objectid) from  NE.INTER_APP_EVENT))"
df = sqlContext.read.format("jdbc").option("driver", "oracle.jdbc.OracleDriver").option("url","jdbc:oracle:thin:NE/Network_147@10.77.1.147:1521/ELLDEV").option("dbtable","NE.INTER_APP_EVENT").load()
rdd = df.rdd
output = rdd.saveAsTextFile(opstring)