更新搜索词key

Pyspark_job/sqoop_export/ods_st_key.py

+import os
+import sys
+
+sys.path.append(os.path.dirname(sys.path[0]))
+
+from utils.ssh_util import SSHUtil
+from utils.common_util import CommonUtil
+from utils.db_util import DBUtil
+
+if __name__ == '__main__':
+    site_name = CommonUtil.get_sys_arg(1, None)
+
+    CommonUtil.judge_is_work_hours(
+        site_name=site_name,
+        principal='chenyuanjie', priority=1, export_tools_type=1, belonging_to_process='更新搜索词key'
+    )
+
+    db_type = 'postgresql_cluster'
+    engine = DBUtil.get_db_engine(db_type, site_name)
+    export_cols = [
+        'st_key',
+        'search_term'
+    ]
+
+    export_tb = f"{site_name}_st_key_copy"
+    export_tb_target = f"{site_name}_st_key"
+
+    # 建表
+    sql = f"""
+        DROP TABLE IF EXISTS {export_tb};
+        CREATE TABLE IF NOT EXISTS {export_tb} (
+            st_key int8 NOT NULL,
+            search_term varchar(500) NOT NULL,
+            keyword_tsv tsvector
+        );
+    """
+    DBUtil.engine_exec_sql(engine, sql)
+
+    # 导出数据
+    partition_dict = {
+        "site_name": site_name
+    }
+    sh = CommonUtil.build_export_sh(
+        site_name=site_name,
+        db_type=db_type,
+        hive_tb="ods_st_key",
+        export_tb=export_tb,
+        col=export_cols,
+        partition_dict=partition_dict
+    )
+    client = SSHUtil.get_ssh_client()
+    SSHUtil.exec_command_async(client, sh, ignore_err=False)
+    client.close()
+
+    # 创建索引，交换表名
+    sql = f"""
+    update {export_tb} set keyword_tsv = to_tsvector('english_amazonword', search_term);
+    """
+    DBUtil.engine_exec_sql(engine, sql)
+    DBUtil.exchange_tb(
+        engine=engine,
+        source_tb_name=export_tb,
+        target_tb_name=export_tb_target,
+        cp_index_flag=True
+    )
+    print("success！")