import os import sys from datetime import datetime sys.path.append(os.path.dirname(sys.path[0])) from utils.ssh_util import SSHUtil from utils.common_util import CommonUtil, DateTypes from utils.db_util import DBUtil 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: CommonUtil.judge_is_work_hours(site_name=site_name, date_type=date_type, date_info=date_info, principal='wujicang', priority=2, export_tools_type=1, belonging_to_process=f'新ABA流程_{date_type}') if date_type in (DateTypes.month.name, DateTypes.week.name, DateTypes.month_week.name): db_type = 'postgresql_cluster' print("导出到PG-Cluster库中") else: db_type = "postgresql" print("导出到PG库中") export_master_tb = f"{site_name}_aba_profit_gross" suffix = str(date_info).replace("-", "_") engine = DBUtil.get_db_engine(db_type, site_name) # 30天表进行备份 if date_type == DateTypes.last30day.name or date_type == DateTypes.month_week.name: export_tb_before = f"{site_name}_aba_profit_gross_last30day" export_tb_rel = f"{export_tb_before}_copy" export_tb = export_tb_rel with engine.connect() as connection: sql = f""" drop table if exists {export_tb_rel}; create table if not exists {export_tb_rel} ( like {export_tb_before} including comments ); """ print("================================执行sql================================") print(sql) connection.execute(sql) else: export_tb = f"{site_name}_aba_profit_gross_{date_type}_{suffix}" next_val = CommonUtil.get_next_val(date_type, date_info) with engine.connect() as connection: sql = f""" create table if not exists {export_tb} partition of {export_master_tb} for values from ('{date_type}', '{date_info}') to ('{date_type}', '{next_val}'); truncate table {export_tb}; """ print("================================执行sql================================") print(sql) connection.execute(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 } # 导出表名 sh = CommonUtil.build_export_sh( site_name=site_name, db_type=db_type, hive_tb="dwd_st_volume_fba", export_tb=export_tb, col=[ "search_term_id", "search_term", "fba_fee", "ocean_freight", "air_delivery_fee", "referral_fee", "return_ratio", "operating_costs", "costs", "advertise", "gross_profit_fee_air", "date_type", "date_info", "gross_profit_fee_sea", "price", "category_id", "longs", "width", "high", "weight" ], partition_dict=partition_dict ) client = SSHUtil.get_ssh_client() SSHUtil.exec_command_async(client, sh, ignore_err=False) client.close() if date_type in (DateTypes.month_week.name, DateTypes.last30day.name): # 构建索引并交换表名 DBUtil.exchange_tb(engine, source_tb_name=export_tb_rel, target_tb_name=export_tb_before, cp_index_flag=True) 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: 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) print("success")