python与hive通信交互

一、python与hive1通信

#!/usr/bin/python2.7
#hive --service hiveserver >/dev/null 2>/dev/null&
#/usr/lib/hive/lib/py
import sys
from hive_service import ThriftHive
from hive_service.ttypes import HiveServerException
from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol

def hiveExe(sql):
    try:
        transport = TSocket.TSocket('*.*.*.*', 10000)
        transport = TTransport.TBufferedTransport(transport)
        protocol = TBinaryProtocol.TBinaryProtocol(transport)
        client = ThriftHive.Client(protocol)
        transport.open()

        client.execute(sql)

        print "The return value is : "
        print client.fetchAll()
        print "............"
        transport.close()
    except Thrift.TException, tx:
        print '%s' % (tx.message)

if __name__ == '__main__':
    hiveExe("select * from project.table")

 python和hive1通讯是一件非常容易的事情，因为python所需要的依赖包从/usr/lib/hive/lib/py获取即可，导入到hive的扩张中就可以应用了。

二、python与hive2的通信

#!/usr/bin/python2.7
#hive --service hiveserver2 >/dev/null 2>/dev/null&
#install pyhs2,first install cyrus-sasl-devel,gcc,libxml2-devel,libxslt-devel
#hiveserver2 is different from hiveserver on authority

import pyhs2

conn = pyhs2.connect(host='*.*.*.*',port=10000,authMechanism="PLAIN", user='hive', password='', database='project')
cur = conn.cursor()
cur.execute("select * from table limit 10")
for i in cur.fetch():
        print i
cur.close()
conn.close()

  python与hive2通信比较费劲，需要安装的依赖比较多（install pyhs2,first install cyrus-sasl-devel,gcc,libxml2-devel,libxslt-devel）。但是安装完成后编程还是很容易的。

  两种通讯有一个共同点，就是必须启动hive服务器。