pyhon 脚本实现批量日志信息导入外部表分区

最新推荐文章于 2022-10-23 15:35:12 发布

Rascal_Wei

最新推荐文章于 2022-10-23 15:35:12 发布

阅读量577

点赞数

本文链接：https://blog.csdn.net/weishuxiao1/article/details/46428475

版权

#!/usr/bin/python
import os
import time

def cmdmk(dir,year,month,day):
    '''创建根据年月日导入分区的命令'''
    path=dir+'%04d'%year+'/%02d'%month+'/%02d'%day+'/'
    cmd="ALTER TABLE gntable ADD IF NOT EXISTS PARTITION(year="+'"'+'%04d'%year+'"'+",month="+'"'+'%02d'%month+'"'+",day="+'"'+'%02d'%day+'"'+") LOCATION "+'"'+path+'";'
    return cmd

if __name__ == '__main__':
    year=2014;
    days=[31,28,31,30,31,30,31,31,30,31,30,31]
    fo = open("hive_temp.q", "w")
    fo.write(("use gnhive;"+"\n").encode())
    #循环的范式产生批量分区数据导入的命令
    for month in range(1,13):
        for day in range(1,days[month-1]+1):
            hive_cmd=cmdmk("/user/Gn/",year,month,day)
            print(hive_cmd)
            fo.write((hive_cmd+"\n").encode())
    fo.close
    #执行分区导入命令
    print(os.system("hive -f hive_temp.q"))