利用Python調用HBASE

利用Python調用HBASE的 需要安裝thrift hbase-thrift 

啟動hbase的thrift服務：bin/hbase-daemon.sh start thrift 默認端口是9090

mysql 到hbase的數據同步：

1、put 

2、Importtsv

3、編寫MapReduce Job導入

4、sqoop

簡單code:

#!/usr/bin/env python

#coding=utf-8

import sys

sys.path.append('/usr/lib/python2.6/site-packages/hbase')

from thrift import Thrift

from thrift.transport import TSocket

from thrift.transport import TTransport

from thrift.protocol import TBinaryProtocol

from hbase import Hbase

from hbase.ttypes import *

import csv

from hbase.ttypes import ColumnDescriptor, Mutation, BatchMutation, TRegionInfo

from hbase.ttypes import IOError, AlreadyExists

######

def client_conn():

transport=TSocket.TSocket("172.16.10.87",9090)

transport=TTransport.TBufferedTransport(transport)

protocol=TBinaryProtocol.TBinaryProtocol(transport)

client=Hbase.Client(protocol)

transport.open()

return client

def __del__():

transport.close()

if __name__=="__main__":

client=client_conn()

#獲取表名字

print client.getTableNames()

##創建表

#client.createTable('name2',[ColumnDescriptor(name="user_id:",maxVersions=1),ColumnDescriptor(name="user_name"),])

#寫入數據

client.mutateRow('name2','a1',[Mutation(column='user_id:1',value="1")])

client.mutateRow('ca_record','1',[Mutation(column='user_id:0',value='5')])

##獲取數據

aa=client.getRow('name2','a1')

for r in aa:

   print 'row',r.row 

   print '\br'

   print 'value',r.columns.get("user_id:1").value

##刪除表

#client.disableTable("t1")

#client.deleteTable("t1")

print client.getTableNames()

###獲取表的行鍵值

#print client.scannerGet(client.scannerOpen('t2',"cmd",["a"]))

print client.scannerGet(client.scannerOpen('t2',"",["a"])) #當row key為空取第一個

print "------"

print client.getColumnDescriptors('t3')

#在自己開發環境  只要安裝好thrift 及hbase-thrift的包，在import的時候不會出問題