import os import sys 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 if __name__ == '__main__': site_name = CommonUtil.get_sys_arg(1, None) date_info = CommonUtil.get_sys_arg(2, None) # 获取最后一个参数 test_flag = CommonUtil.get_sys_arg(len(sys.argv) - 1, None) date_type = "day" # 工作时间不导出 CommonUtil.judge_is_work_hours(site_name=site_name, date_type=date_type, date_info=date_info, principal='wujicang', priority=1, export_tools_type=1) if test_flag == 'test': db_type = 'postgresql_test' else: db_type = "postgresql" print(f"导出到{db_type}中") engine = DBUtil.get_db_engine(db_type, site_name) d_month_now = CommonUtil.reformat_date(date_info, "%Y-%m-%d", "%Y_%m", ) rel_date_info = CommonUtil.reformat_date(date_info, "%Y-%m-%d", "%Y-%m", ) next_month = CommonUtil.get_month_offset(rel_date_info, 1) # 导出表 export_master_tb = f"{site_name}_nsr_asin_detail" export_tb = f"{export_master_tb}_{d_month_now}" export_tb_copy = f"{export_master_tb}_{d_month_now}_copy" with engine.connect() as connection: sql = f""" create table if not exists {export_tb} partition of {export_master_tb} for values from ('{rel_date_info}') to ('{next_month}'); drop table if exists {export_tb_copy}; create table if not exists {export_tb_copy} ( like {export_tb} including indexes including comments ); """ print("================================执行sql================================") print(sql) connection.execute(sql) connection.close() # 导出表名 sh = CommonUtil.build_export_sh( site_name=site_name, db_type=db_type, hive_tb="dwt_nsr_asin_detail", export_tb=export_tb_copy, col=[ "asin", "title", "img_url", "ao_val", "rating", "total_comments", "bsr_orders", "bsr_orders_change", "price", "weight", "launch_time", "date_info", "brand_name", "buy_box_seller_type", "account_name", "volume", "img_type", "last_update_time", "asin_type", "asin_air_freight_gross_margin", "asin_ocean_freight_gross_margin", "asin_unlaunch_time", "seller_id", "seller_country_name", "category_first_id", "first_category_rank", "first_category_rank_date", "package_quantity", "asin_launch_time_type", "seller_country_type", "asin_bought_month" ], partition_dict={ "site_name": site_name, "date_info": rel_date_info } ) client = SSHUtil.get_ssh_client() SSHUtil.exec_command_async(client, sh, ignore_err=False) client.close() # 交换分区表名 DBUtil.exchange_pg_part_tb( engine, source_tb_name=export_tb_copy, part_master_tb=export_master_tb, part_target_tb=export_tb, part_val={ "from": [rel_date_info], "to": [next_month] }, cp_index_flag=False, ) # 修改状态 sql = f"""insert ignore into workflow_everyday (site_name, report_date, status, status_val, table_name, date_type, page, is_end, remark) values ('{site_name}', '{date_info}', '导出PG数据库', 14, '{site_name}_nsr_asin_rank', 'day', 'NSR榜单', '是', 'NS榜单对应的TOP100ASIN') """ CommonUtil.modify_export_workflow_status( update_workflow_sql=sql, site_name=site_name, date_type=date_type, date_info=date_info ) print("success")