1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
import os
import sys
from datetime import datetime
sys.path.append(os.path.dirname(sys.path[0]))
from utils.db_util import DBUtil
from utils.ssh_util import SSHUtil
from utils.common_util import CommonUtil,DateTypes
if __name__ == '__main__':
site_name = CommonUtil.get_sys_arg(1, None)
date_type = CommonUtil.get_sys_arg(2, None)
date_info = CommonUtil.get_sys_arg(3, None)
# 获取最后一个参数
test_flag = CommonUtil.get_sys_arg(len(sys.argv) - 1, None)
print(f"执行参数为{sys.argv}")
if test_flag == 'test':
db_type = 'postgresql_test'
print("导出到测试库中")
else:
db_type = "postgresql_cluster"
print("导出到PG集群库库中")
year_str = CommonUtil.safeIndex(date_info.split("-"), 0, None)
suffix = str(date_info).replace("-", "_")
base_tb = f"{site_name}_st_theme_detail"
# 获取数据库连接
engine = DBUtil.get_db_engine(db_type, site_name)
if date_type in (DateTypes.last30day.name, DateTypes.month_week.name):
export_tb_target = f"{base_tb}_last30day"
export_tb_copy = f"{export_tb_target}_copy"
export_tb = export_tb_copy
# 如果copy表不存在则创建copy表
sql = f"""
create table if not exists {export_tb_copy}
(
like {export_tb_target} including indexes including comments
);
truncate table {export_tb_copy};
"""
DBUtil.engine_exec_sql(engine, sql)
else:
export_master_tb = f"{base_tb}_{year_str}"
export_tb = f"{base_tb}_{suffix}"
next_month = CommonUtil.get_next_val(date_type, date_info)
# 保证幂等性，先删除原始表同周期的数据
sql = f"""
drop table if exists {export_tb};
create table if not exists {export_tb}
(
like {export_master_tb} including comments
);
"""
DBUtil.engine_exec_sql(engine, sql)
if test_flag == "month_append":
partition_dict = {
"site_name": site_name,
"date_type": "month",
"date_info": date_info
}
else:
partition_dict = {
"site_name": site_name,
"date_type": date_type,
"date_info": date_info
}
# 导出agg表
sh_report = CommonUtil.build_export_sh(
site_name=site_name,
db_type=db_type,
hive_tb="dws_st_theme",
export_tb=export_tb,
col=[
"st_key",
"search_term",
"theme_ch",
"theme_en",
"theme_label_ch",
"theme_label_en",
"date_info",
"created_time",
"updated_time"
],
partition_dict=partition_dict
)
client = SSHUtil.get_ssh_client()
SSHUtil.exec_command_async(client, sh_report, ignore_err=False)
client.close()
if date_type in (DateTypes.last30day.name, DateTypes.month_week.name):
# 构建索引并交换表名
DBUtil.exchange_tb(engine,
source_tb_name=export_tb_copy,
target_tb_name=export_tb_target,
cp_index_flag=False)
update_workflow_sql = f"""
replace INTO selection.workflow_everyday
(site_name, report_date, status, status_val, table_name, date_type, page, is_end, remark,export_db_type)
VALUES('{site_name}', '{datetime.now().date()}', '导出PG数据库完成', 14, 'us_aba_last_30_day', '30_day', 'ABA搜索词', '是', 'ABA搜索词最近30天表','{db_type}');
"""
else:
# 创建索引并交换分区
DBUtil.add_pg_part(
engine,
source_tb_name=export_tb,
part_master_tb=export_master_tb,
part_val={
"from": [date_info],
"to": [next_month]
},
cp_index_flag=False,
)
update_workflow_sql = f"""
UPDATE selection.workflow_everyday SET status='导出PG数据库完成', status_val=14,is_end ='是',export_db_type = '{db_type}'
WHERE site_name= '{site_name}' and date_type='{date_type}' and report_date= '{date_info}' and page ='ABA搜索词'
"""
# 往导出流程表插入导出完成数据，方便监听导出脚本是否全部完成
CommonUtil.modify_export_workflow_status(update_workflow_sql, site_name, date_type, date_info)
# 关闭链接
engine.dispose()
print("success")