python通过thrift操作hbase实例

关于thrift的论文：http://pan.baidu.com/share/link?shareid=234128&uk=3238841275

安装thrift：http://thrift.apache.org/docs/install/ubuntu/

安装完成后到hbase的目录下，找到Hbase.thrift，该文件在

hbase-0.94.4/src/main/resources/org/apache/hadoop/hbase/thrift下可以找到

thrift --gen python hbase.thrift 会生成gen-py文件夹，将其修改成hbase

安装python的thrift库

sudo pip install thrift

启动hbase的thrift服务：bin/hbase-daemon.sh start thrift 默认端口是9090

创建hbase表:

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 *
  
transport = TSocket.TSocket(&＃39;localhost&＃39;, 9090);
  
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport);
  
client = Hbase.Client(protocol)
transport.open()
  
  
cOntents= ColumnDescriptor(name=&＃39;cf:&＃39;, maxVersiOns=1)
client.createTable(&＃39;test&＃39;, [contents])
  
print client.getTableNames()

执行代码，成功后，进入hbase的shell，用命令list可以看到刚刚的test表已经创建成功。

插入数据：

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 *
  
transport = TSocket.TSocket(&＃39;localhost&＃39;, 9090)
  
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
  
transport.open()
  
row = &＃39;row-key1&＃39;
  
mutatiOns= [Mutation(column="cf:a", value="1")]
client.mutateRow(&＃39;test&＃39;, row, mutations, None)

获取一行数据：

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 *
  
transport = TSocket.TSocket(&＃39;localhost&＃39;, 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
  
transport.open()
  
tableName = &＃39;test&＃39;
rowKey = &＃39;row-key1&＃39;
  
result = client.getRow(tableName, rowKey, None)
print result
for r in result:
    print &＃39;the row is &＃39; , r.row
    print &＃39;the values is &＃39; , r.columns.get(&＃39;cf:a&＃39;).value

返回多行则需要使用scan：

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 *
  
transport = TSocket.TSocket(&＃39;localhost&＃39;, 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
transport.open()
  
scan = TScan()
tableName = &＃39;test&＃39;
id = client.scannerOpenWithScan(tableName, scan, None)
  
result2 = client.scannerGetList(id, 10)
  
print result2

scannerGet则是每次只取一行数据：

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 *
  
transport = TSocket.TSocket(&＃39;localhost&＃39;, 9090)
transport = TTransport.TBufferedTransport(transport)
  
protocol = TBinaryProtocol.TBinaryProtocol(transport)
  
client = Hbase.Client(protocol)
transport.open()
  
scan = TScan()
tableName = &＃39;test&＃39;
id = client.scannerOpenWithScan(tableName, scan, None)
result = client.scannerGet(id)
while result:
    print result
    result = client.scannerGet(id)