近需要用到hive,刚开始用py3去连接，白忙活了2天，居然没有搞定，如果你搞定了，请分析笔记给我哈。我用py2搞定了，下面是步骤：
一、安装
### 安装PIP ###curl https://bootstrap.pypa.io/get-pip.py -o get-pip.pypython get-pip.py# 查看 pip 版本 #pip -V#### install 依赖包 ####yum install cyrus-sasl-plain cyrus-sasl-devel cyrus-sasl-gssapi如果 cyrus-sasl-plain 安装失败，则下载rpm包后进行安装：http://download.csdn.net/detail/u012965373/9647909rpm -ivh ./xxxxx.rpm###安装工程依赖包 ###pip install -r requirements.txt
requirements.txt 文件内容如下：
pyhs2 requests
二、代码
#!/usr/bin/python2.7
# -*- coding: UTF-8 -*-
'''
代码运行在python 2.7 环境，需要安装
'''
import pyhs2
import sys
from logger.log import dblog
class HiveModelClass(object):
def __init__(self, **connect_info):
super(HiveModelClass, self).__init__()
domain = connect_info['domain'] # xx.cn
host = connect_info['host']
port = connect_info['port'] if connect_info['port'] else 10000
user = connect_info['user']
password = connect_info['password']
database = connect_info['database'] if connect_info['database'] else 'default'
try:
conn = pyhs2.connect(host=host,
port=port,
authMechanism="LDAP",
user='{0}@{1}'.format(user, domain),
password=password,
database=database)
self.cursor = conn.cursor()
except Exception as e:
dblog.error('Catch exception: [ %s ], file: [ %s ], line: [ %s ].' % (e, __file__, sys._getframe().f_lineno))
self.cursor = None
def _cursorQuery(self, sql):
try:
self.cursor.execute(sql)
return self.cursor.fetchall()
except Exception as e:
dblog.error("[ERROR] Query error, Catch exception:[ %s ], file: [ %s ], line: [ %s ]" % (e, __file__, sys._getframe().f_lineno))
return ''
# 插入接口 ##
def _cursorInsert(self, sql):
try:
self.cursor.execute(sql)
return 1
except Exception as e:
dblog.error("[ERROR] Insert error, Catch exception:[ %s ], file: [ %s ], line: [ %s ]" % (e, __file__, sys._getframe().f_lineno))
return -1
有了hive 连接的基类，就可以针对这个基类新建一类继承他，如下：
#!/usr/bin/python
# -*- coding: UTF-8 -*-
from Model.hiveModelClass import HiveModelClass
from logger.log import dblog
import sys
class DefaultModelClass(HiveModelClass):
def __init__(self):
connect_dic = {
'domain': 'xx.cn',
'host': 'x.x.x.x',
'port': 10000,
'user': 'xxxxxx',
'password': 'xxxxxx',
}
super(DefaultModelClass, self).__init__(**connect_dic)
def getCountData(self):
'''
获取数据的总行数
:return: number
'''
sql = 'select count(*) from test2'
try:
ret = self._cursorQuery(sql)
return ret[0]
except Exception as e:
dblog.error("Catch exception: [ %s ], file: [ %s ], line: [ %s ]" % (e, __file__, sys._getframe().f_lineno))
return []于是在控制器中初始化Default 对象，调用 getCountData 方法即可返回数据。 getCountData只是示列，其他方法等你开发。
dblog 是日志模块，可以用print替代（dblog.error/http://dblog.info 等替换为print）
hive查询起来还是很慢的，优势在于大量数据查询或者处理。
