简介:
python连接hbase是需要通过thrift连进行连接的,ambari安装的服务中貌似没有自带安装hbase的thrift,我是看配置hbase的配置名称里面没有thrift,cdh版本的就有,所以我就自己安装了thrift。
一、thrift安装:
1、下载thrift依赖的东西
yum install automake libtool flex bison pkgconfig gcc-c++ boost-devel libevent-devel zlib-devel python-devel ruby-devel openssl-devel
2、安装boost_1_53_0.tar.gz
[root@master ~]# wget http://sourceforge.net/projects/boost/files/boost/1.53.0/boost_1_53_0.tar.gz[root@master ~]# tar xvf boost_1_53_0.tar.gz[root@master ~]# cd boost_1_53_0[root@master boost_1_53_0]# ./bootstrap.sh[root@master boost_1_53_0]# ./b2 install[root@master boost_1_53_0]# cp /usr/local/lib/libboost_unit_test_framework.a /usr/lib64/[root@master boost_1_53_0]# make[root@master boost_1_53_0]# make install
3、下载最新版本thrift,网址:
4、移动到默认安装目录,并解压[root@master ~]# mv thrift-0.11.0.tar.gz /usr/local[root@master ~]# cd /usr/local[root@master local]# tar -zxvf thrift-0.11.0.tar.gz[root@master local]# mv thrift-0.11.0 thrift[root@master local]# cd thrift[root@master local]# ./configure --libdir=/usr/lib --without-java --without-python --without-c_glib[root@master local]# make[root@master local]# make install
二、启动thrift
1、找到hbase的bin执行文件夹,我执行的位置是ambari默认安装的文件夹下面/usr/hdp/2.6.3.0-235/hbase/bin
2、启动thrift,默认端口是9090
[root@master ~]# cd /usr/hdp/2.6.3.0-235/hbase/bin[root@master bin]# bin/hbase-daemon.sh start thrift
三、使用python连接hbase
1、安装python依赖包
pip install thriftpip install hbase-thrift
2、demo程序
from thrift import Thriftfrom thrift.transport import TSocketfrom thrift.transport import TTransportfrom thrift.protocol import TBinaryProtocolfrom hbase import Hbasefrom hbase.ttypes import *transport = TSocket.TSocket('localhost', 9090)transport = TTransport.TBufferedTransport(transport)protocol = TBinaryProtocol.TBinaryProtocol(transport)client = Hbase.Client(protocol)transport.open()contents = ColumnDescriptor(name='cf:', maxVersions=1)# client.deleteTable('test')client.createTable('test', [contents])print client.getTableNames()# insert datatransport.open()row = 'row-key1'mutations = [Mutation(column="cf:a", value="1")]client.mutateRow('test', row, mutations)# get one rowtableName = 'test'rowKey = 'row-key1'result = client.getRow(tableName, rowKey)print resultfor r in result: print 'the row is ', r.row print 'the values is ', r.columns.get('cf:a').valuetransport.close()