# coding=utf-8
# Author: ruin
"""
discrible: """
from thrift.transport import TSocket
from thrift.protocol import TBinaryProtocol
from thrift.transport import TTransport
from hbase import Hbase import struct # Method for encoding ints with Thrift's string encoding
def encode(n):
return struct.pack("i", n) # Method for decoding ints with Thrift's string encoding
def decode(s):
return int(s) if s.isdigit() else struct.unpack('i', s)[0]
class HBaseApi(object): def __init__(self,table='fr_test_hbase:test_api',host='10.2.46.240',port=9090):
self.table = table.encode('utf-8')
self.host = host
self.port = port
# Connect to HBase Thrift server
self.transport = TTransport.TBufferedTransport(TSocket.TSocket(host, port))
self.protocol = TBinaryProtocol.TBinaryProtocolAccelerated(self.transport) # Create and open the client connection
self.client = Hbase.Client(self.protocol)
self.transport.open()
# set type and field of column families
self.set_column_families([bytes],['info'])
self._build_column_families() def set_column_families(self,type_list,col_list=['info']):
self.columnFamiliesType = type_list self.columnFamilies = col_list def _build_column_families(self):
"""
give all column families name list,create a table
:return:
"""
tables = self.client.getTableNames()
if self.table not in tables:
self.__create_table(self.table) def __create_table(self,table):
"""
create table in hbase with column families
:param table: fr_test_hbase:fr_test
:return:
""" columnFamilies = []
for columnFamily in self.columnFamilies:
name = Hbase.ColumnDescriptor(name = columnFamily)
columnFamilies.append(name)
table = table.encode('utf-8')
print(type(table),type(columnFamilies)) self.client.createTable(table,columnFamilies) def __del__(self):
self.transport.close() def __del_table(self,table):
"""
delete a table,first need to disable it
"""
self.client.disableTable(table)
self.client.deleteTable(table) def getColumnDescriptors(self):
return self.client.getColumnDescriptors(self.table) def put(self, rowKey, qualifier, value):
"""
put one row
column is column name,value is column value
:param rowKey: rowKey
:param column: column name
:param value: column value
:description: HbaseApi(table).put('rowKey','column','value')
""" rowKey = rowKey.encode('utf-8')
mutations = []
# for j, column in enumerate(column):
if isinstance(value, str):
value = value.encode('utf-8')
m_name = Hbase.Mutation(column=(self.columnFamilies[0]+':'+qualifier).encode('utf-8'), value=value)
elif isinstance(value, int):
m_name = Hbase.Mutation(column=(self.columnFamilies[0]+':'+qualifier).encode('utf-8'), value=encode(value))
mutations.append(m_name)
self.client.mutateRow(self.table, rowKey, mutations, {}) def puts(self,rowKeys,qualifier,values):
""" put sevel rows, `qualifier` is autoincrement :param rowKeys: a single rowKey
:param values: values is a 2-dimension list, one piece element is [name, sex, age]
:param qualifier: column family qualifier Usage:: >>> HBaseTest('table').puts(rowKeys=[1,2,3],qualifier="name",values=[1,2,3]) """ mutationsBatch = []
if not isinstance(rowKeys,list):
rowKeys = [rowKeys] * len(values) for i, value in enumerate(values):
mutations = []
# for j, column in enumerate(value):
if isinstance(value, str):
value = value.encode('utf-8')
m_name = Hbase.Mutation(column=(self.columnFamilies[0]+':'+qualifier).encode('utf-8'), value=value)
elif isinstance(value, int):
m_name = Hbase.Mutation(column=(self.columnFamilies[0]+':'+qualifier).encode('utf-8'), value=encode(value))
mutations.append(m_name)
mutationsBatch.append(Hbase.BatchMutation(row = rowKeys[i].encode('utf-8'),mutations=mutations))
self.client.mutateRows(self.table, mutationsBatch, {}) def getRow(self,row, qualifier='name'):
"""
get one row from hbase table
:param row:
:param qualifier:
:return:
"""
# res = []
row = self.client.getRow(self.table, row.encode('utf-8'),{})
for r in row:
rd = {}
row = r.row.decode('utf-8')
value = (r.columns[b'info:name'].value).decode('utf-8')
rd[row] = value
# res.append(rd)
# print ('the row is ',r.row.decode('utf-8'))
# print ('the value is ',(r.columns[b'info:name'].value).decode('utf-8'))
return rd def getRows(self, rows, qualifier='name'):
"""
get rows from hbase,all the row sqecify the same 'qualifier'
:param rows: a list of row key
:param qualifier: column
:return: None
"""
# grow = True if len(rows) == 1 else False
res = []
for r in rows:
res.append(self.getRow(r,qualifier))
return res def scanner(self, numRows=100, startRow=None, stopRow=None):
""" :param numRows:
:param startRow:
:param stopRow:
:return:
"""
scan = Hbase.TScan(startRow, stopRow)
scannerId = self.client.scannerOpenWithScan(self.table,scan, {}) ret = []
rowList = self.client.scannerGetList(scannerId, numRows) for r in rowList:
rd = {}
row = r.row.decode('utf-8')
value = (r.columns[b'info:name'].value).decode('utf-8')
rd[row] = value
# print ('the row is ',r.row.decode('utf-8'))
# print ('the value is ',(r.columns[b'info:name'].value).decode('utf-8'))
ret.append(rd) return ret def demo():
ha = HBaseApi('fr_test_hbase:test_log1')
# ha.put('0002','age','23')
rowKeys = [str(key) for key in range(10001,10010)]
values = ['fr'+str(val) for val in range(10001,10010)]
ha.puts(rowKeys,'name',values)
print(ha.scanner())
# print(ha.getRow('0001'))
# print(ha.getRows(rowKeys))
if __name__ == "__main__":
demo()

通过Python操作hbase api的更多相关文章

  1. python 操作 hbase

    python 是万能的,当然也可以通过api去操作big database 的hbase了,python是通过thrift去访问操作hbase 以下是在centos7 上安装操作,前提是hbase已经 ...

  2. 【Hbase三】Java,python操作Hbase

    Java,python操作Hbase 操作Hbase python操作Hbase 安装Thrift之前所需准备 安装Thrift 产生针对Python的Hbase的API 启动Thrift服务 执行p ...

  3. 使用IDEA操作Hbase API 报错:org.apache.hadoop.hbase.client.RetriesExhaustedException的解决方法:

     使用IDEA操作Hbase API 报错:org.apache.hadoop.hbase.client.RetriesExhaustedException的解决方法: 1.错误详情: Excepti ...

  4. Hbase理论&&hbase shell&&python操作hbase&&python通过mapreduce操作hbase

    一.Hbase搭建: 二.理论知识介绍: 1Hbase介绍: Hbase是分布式.面向列的开源数据库(其实准确的说是面向列族).HDFS为Hbase提供可靠的底层数据存储服务,MapReduce为Hb ...

  5. Python操作HBase之happybase

    安装Thrift 安装Thrift的具体操作,请点击链接 pip install thrift 安装happybase pip install happybase 连接(happybase.Conne ...

  6. 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 . ...

  7. python 操作Hbase 详解

    博文参考:https://www.cnblogs.com/tashanzhishi/p/10917956.html 如果你们学习过Python,可以用Python来对Hbase进行操作. happyb ...

  8. python操作ansible api示例

    #!/usr/bin/env python # -*- coding:utf-8 -*- import json import shutil from collections import named ...

  9. Python 操作 GA API 指南

    因为需要写一个 Blog Feature 的缘故,所以接触了下 GA 的 Python API,发现 G 家的 API 不是那么直观,比较绕,但是,在使用过程中发现其实 G 家的 API 设计挺有意思 ...

随机推荐

  1. LA 5009 (HDU 3714) Error Curves (三分)

    Error Curves Time Limit:3000MS    Memory Limit:0KB    64bit IO Format:%lld & %llu SubmitStatusPr ...

  2. CentOS7下利用init.d启动脚本实现tomcat开机自启动

    在之前的博文中已经对CentOS7下通过tomcat进行WEB系统的发布进行了介绍,今天将利用init.d启动脚本,将服务脚本加入到开机启动服务队列,实现tomcat服务的开机启动. 1. 环境准备 ...

  3. Atitit.java 虚拟机的构成 与指令分类 与 指令集合 以及字节码查看工具javjap

    Atitit.java 虚拟机的构成 与指令分类 与 指令集合 以及字节码查看工具javjap 1.1. 虚拟机的构成 java虚拟机--处理器.堆栈.寄存器.指令系统. 1 1.2. 虚拟机执行过程 ...

  4. ResultSet详解(转)

      ResultSet用法集锦 结果集(ResultSet)是数据中查询结果返回的一种对象,可以说结果集是一个存储查询结果的对象,但是结果集并不仅仅具有存储的功能,他同时还具有操纵数据的功能,可能完成 ...

  5. ipk CONTROL 目录的作用

    CONTROL文件夹下的文件意义preinst        - shell script,在ipk包开始安装前执行;postinst       - shell script,在ipk包安装后执行; ...

  6. Cap'n Proto, FlatBuffers, and SBE

    转自:utm_source=tuicool">http://kentonv.github.io/capnproto/news/2014-06-17-capnproto-flatbuff ...

  7. centos修改启动顺序,登录后提示,启动级别,主机名,免密登录

    修改启动顺序 # vim  /etc/inittab ....... d:3:initdefault: #找到这一行,d:3:initdefault:最小化启动 d:5:initdefault:图形界 ...

  8. Yarn源码分析之MRAppMaster上MapReduce作业处理总流程(二)

    本文继<Yarn源码分析之MRAppMaster上MapReduce作业处理总流程(一)>,接着讲述MapReduce作业在MRAppMaster上处理总流程,继上篇讲到作业初始化之后的作 ...

  9. constructors and destructors

    A constructor is a method that gets called immediately when an object is allocated (on the stack or ...

  10. Git使用技巧(1)-- 配置【持续更新】

    配置名字和邮箱 git config --global user.name "Your Name" git config --global user.email "ema ...