# -*-coding=utf-8 -*-

from pyspark import SparkConf, SparkContext

sc = SparkContext('local')

sc.parallelize([1, 2, 3, 4]).saveAsTextFile("a") #保存

print sc.textFile("a").collect() #读取

# -*-coding=utf-8 -*-

from pyspark import SparkConf, SparkContext

import json

sc = SparkContext('local')

sc.parallelize({(11,2),(103,4),(103,6)}).sortByKey().map(lambda x:json.dumps(x)).saveAsTextFile("b") #保存

print sc.textFile("b").collect() #读取

# -*-coding=utf-8 -*-

from pyspark import SparkConf, SparkContext

sc = SparkContext('local')

sc.parallelize({("",""),("",""),("","")}).saveAsSequenceFile("c") #保存

print sc.sequenceFile("c","org.apache.hadoop.io.Text", "org.apache.hadoop.io.IntWritable").collect() #读取

# -*- coding: utf-8 -*-

from pyspark import SparkConf, SparkContext

from pyspark.sql import HiveContext

conf = SparkConf().setMaster("local").setAppName("My App")

sc = SparkContext(conf=conf)

hiveCtx = HiveContext(sc)

rows = hiveCtx.sql("select * from db.table where pt=20171111 limit 10")

firstRow = rows.first()

print firstRow.userid

'''运行结果：

11308542

'''