pyspark读取json文件中的内容

 

代码如下：

#-*- coding:utf- -*-
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
from pyspark import SparkConf,SparkContext
from pyspark.sql import SQLContext
conf=SparkConf().setAppName("spark_json1")
sc=SparkContext(conf=conf)
sqlContext=SQLContext(sc)


jsons=sqlContext.read.json("./testweet.json")
print"type of jsons",type(jsons)
print jsons.collect()#这个是把每个key-value对转化为列表中的一个元素后输出
print"-------------------------"
jsons.printSchema()
print"-------------------------"
pandas_df = jsons.toPandas()  
print"type of pandas_df",type(pandas_df)#类型转化<class 'pyspark.sql.dataframe.DataFrame'> -> <class 'pandas.core.frame.DataFrame'>

{"lovesPandas":"lovesPandas","age":12}
{"lovesPandas":"lili","age":22}
{"lovesPandas":"cc","age":11}
{"lovesPandas":"vv","age":13}
{"lovesPandas":"lee","age":14}
{"lovesPandas":"yuchi","age":14}