Kafka作为源数据进行数据流计算

#!/user/bin/env python3

from __future__ import print_function
import sys
from pyspark import SparkContext
from pyspark.streaming import StreamingContext
from pyspark.streaming.kafka import KafkaUtils

if __name__ == "__main__":
	if len(sys.argv)!=3:
		print("Usage:KafkaWordCount.py<zk><topic>", file = sys.stderr)
		exit(-1)
	sc = SparkContext(aapname = "PythonStreamingKafkaWordCount")
	ssc = StreamingContext(sc,1)
	zkQuorum,topic = sys.argv[1:]
	kvs = KafkaUtils.createStream(ssc,zkQuorum,"spark-streaming-consummer",{topic:1})
	lines = kvs.map(lambda x:x[1])
	counts = lines.fatMap(lambda line:lines.split(" ")).map(lambda word:(word,1)).reduceByKey(lambda a,b:a+b)
counts.pprint()
ssc.start()
ssc.awaitTermination()