python操作Hbase

本地操作

• 启动thrift服务：./bin/hbase-daemon.sh start thrift

• hbase模块产生：

  • 下载thrfit源码包：thrift-0.8.0.tar.gz

  • 解压安装

  • ./configure

  • make

  • make install

• 在thrift-0.8.0目录中，lib/py/build/lib.linux-x86_64-2.6/目录下存在thrift的python模块，拷贝出来即可

• 生成hbase模块

  • 下载源码包：hbase-0.98.24-src.tar.gz

  • 解压，进入下面目录：hbase-0.98.24/hbase-thrift/src/main/resources/org/apache/hadoop/hbase/thrift

  • thrift --gen py Hbase.thrift

• 创建表格

  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('master' , 9090)
  transport = TTransport.TBufferedTransport(transport)
  ​
  protocol = TBinaryProtocol.TBinaryProtocol(transport)
   
  client = Hbase.Client(protocol)
  ​
  transport.open()
  ​
  base_info_contents = ColumnDescriptor(name='meta-data',maxVersions=1)
  other_info_contents = ColumnDescriptor(name='flags',maxVersions=1)
  ​
  client.createTable('new_music_table', [base_info_contents, other_info_contents])
  ​
  print client.getTableNames()

• 写数据

  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('master' , 9090)
  transport = TTransport.TBufferedTransport(transport)
  ​
  protocol = TBinaryProtocol.TBinaryProtocol(transport)
   
  client = Hbase.Client(protocol)
  ​
  transport.open()
  ​
  tableName = 'new_music_table'
  rowKey = '1100'
  ​
  mutations = [Mutation(column="meta-data:name" , value="wangqingshui"),
              Mutation(column="meta-data:tag" , value="pop"),
              Mutation(column="meta-data:is_valid" , value="TRUE")]
  client.mutateRow(tableName,rowKey,mutations,None)

• 读数据

  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('master' , 9090)
  transport = TTransport.TBufferedTransport(transport)
  ​
  protocol = TBinaryProtocol.TBinaryProtocol(transport)
   
  client = Hbase.Client(protocol)
  ​
  transport.open()
  ​
  tableName = 'new_music_table'
  rowKey = '1100'
  ​
  result = client.getRow(tableName,rowKey,None)
  for r in result:
      print 'the row is ',r.row
      print 'the name is ',r.columns.get('meta-data:name').value
      print 'the name is ',r.columns.get('meta-data:is_valid').value

  • 读多条数据

  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('master' , 9090)
  transport = TTransport.TBufferedTransport(transport)
  ​
  protocol = TBinaryProtocol.TBinaryProtocol(transport)
   
  client = Hbase.Client(protocol)
  ​
  transport.open()
  ​
  tableName = 'new_music_table'
  ​
  scan = TScan()
  id = client.scannerOpenWithScan(tableName , scan , None)
  result = client.scannerGetList(id,10)
  ​
  for r in result:
      print '==============='
      print 'the row is ' , r.row
      for k,v in r.columns.items():
          print "	".join([k,v.value])
  ​
   # 执行结果
  ===============
  the row is  1100
  meta-data:name  wangqingshui
  meta-data:is_valid      TRUE
  meta-data:tag   pop
  ===============
  the row is  2200
  meta-data:name  langdechuanshuo