# 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. linux 进入 GNOME X 界面

    CentOS 安装Gnome CentOSVmwareLinuxBlogHTML  刚开始装系统的时候,没有选Gnome或者KDE,现在想装个玩玩. 简单的安装可以参考这个:http://huruxi ...

  2. Linux下(centos6.8)JDK1.8的安装与配置

    今天说下在Linux(centos6.8)系统下的JDK安装与配置. 据我所知的jdk安装方式有三种(rpm.yum方式没用过,暂且不提)今天只说解压安装方式: 一.解压jdk安装包: 附上jdk1. ...

  3. window安装rabbitmq

    Rabbit MQ 是建立在强大的Erlang OTP平台上,因此安装Rabbit MQ的前提是安装Erlang.通过下面两个连接可以下载安装最新的版本: 下载并安装Eralng OTP For Wi ...

  4. 集成学习1-Boosting

    转自http://blog.csdn.net/lvhao92/article/details/51079018 集成学习大致分为两类,一类串行生成.如Boosting.一类为并行化.如Bagging和 ...

  5. poj 3666 河南省第七届程序设计D题(山区修路)

    题目大意: 给定一个序列,以最小代价将其变成单调不增或单调不减序列,求最小的变动价值:需要用到离散化dp 状态转移方程: dp[i][j]=abs(j-w[i])+min(dp[i-1][k]);(k ...

  6. PLSQL快捷键设置

    1.在PL/SQL Developer中编写sql语句时,如果无法自动提示字段那是一件痛苦的事情,工作效率又低,在此演示下如何在PL/SQL Developer工具中自动提示字段,让开发者省时又省心, ...

  7. Using Swift with Cocoa and Objective-C下载

    <Using Swift with Cocoa and Objective-C Building App > 下载地址 http://download.csdn.net/detail/sw ...

  8. linux oracle sqlplus中文乱码解决

    在oracle用户的~/.bash_profile中添加 NLS_LANG="SIMPLIFIED CHINESE"_CHINA.ZHS16GBKexport NLS_LANG 然 ...

  9. src.rpm包安装方法

    有些软件包是以.src.rpm结尾的,这类软件包是包含了源代码的rpm包,在安装时需要进行编译.这类软件包有多种安装方法,以redhat为例说明如下: 注意: 如果没有rpmbuild可以从系统安装光 ...

  10. 一些常用的html css整理--文本长度截取

    div+css设置列表div超出部分显示...(单行文本) width:200px; //指定宽度: overflow:hidden; //将超出内容隐藏 text-overflow:ellipsis ...