Python批量删除mysql中千万级大量数据的脚本分享

# -*-coding:utf-8 -*-

import sys

# 这是我们内部封装的Python Module
sys.path.append('/var/lib/hadoop-hdfs/scripts/python_module2')
import keguang.commons as commons
import keguang.timedef as timedef
import keguang.sql.mysqlclient as mysql

def run(starttime, endtime, regx):
 tb_name = 'statistic_ad_image_final_count'
 days = timedef.getDays(starttime,endtime,regx)
 # 遍历删除所有天的数据
 for day in days:
  print '%s 数据删除开始'%(day)
  mclient = getConn()
  sql = '''
  select 1 from %s where date = '%s' limit 1
  '''%(tb_name, day)
  print sql
  result = mclient.query(sql)
  # 如果查询到了这一天的数据，继续删除
  while result is not ():
   sql = 'delete from %s where date = "%s" limit 50000'%(tb_name, day)
   print sql
   mclient.execute(sql)
   sql = '''
   select 1 from %s where date = '%s' limit 1
   '''%(tb_name, day)
   print sql
   result = mclient.query(sql)
  print '%s 数据删除完成'%(day)
  mclient.close()

# 返回mysql 连接
def getConn():
 return mysql.MysqlClient(host = '0.0.0.0', user = 'test', passwd = 'test', db= 'statistic')

if __name__ == '__main__':
 regx = '%Y-%m-%d'
 yesday = timedef.getYes(regx, -1)
 starttime = '2019-08-17'
 endtime ='2019-08-30'
 run(starttime, endtime, regx)