业务场景,写个自动任务定时把mysql的数据同步clickhouse,利用clickhouse的高速查询来做大数据准备
实现原理,查询当前clickhouse的数据id,拉取mysql大于此id的数据,再插入到clickhouse
import pymysql
from clickhouse_driver import Client
click_client = Client("host", "port", "db", "usr", "passwd")
mysql_client =pymysql.connect(host='***',port=***,user='***',passwd='***',db='***',charset='utf8')
def get_id():
click_sql = """SELECT id FROM test order by id desc limit 1"""
try:
list = click_client.execute(click_sql, types_check=True)
for i in list:
id = i[0]
return id
except Exception as e:
print(e)
def get_data():
log_id = get_id()
cursor = mysql_client.cursor()
sql= """SELECT * FROM test WHERE id > "%s" """ % log_id
cursor.execute(sql)
results = cursor.fetchall()
mysql_client.close()
return results
def insert_data(data):
try:
click_client.execute('INSERT INTO test VALUES', [data], types_check=True)
return "成功"
except Exception as e:
return(e)
def main():
print (get_id())
list = get_data()
for data in list:
print(data)
print(insert_data(data))
if __name__ == '__main__':
main()