Commit 2d09090f by fangxingjun

no message

parent a26a500c
...@@ -120,12 +120,15 @@ class DwdNsrBsrKeepaAsin(Templates): ...@@ -120,12 +120,15 @@ class DwdNsrBsrKeepaAsin(Templates):
df_nsr_agg, on=['asin'], how='left' df_nsr_agg, on=['asin'], how='left'
) )
self.df_save_asin_cate = self.df_save_asin_cate.withColumn("site_name", F.lit(self.site_name)) self.df_save_asin_cate = self.df_save_asin_cate.withColumn("site_name", F.lit(self.site_name))
self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_type", F.lit(self.date_type))
self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_info", F.lit(self.date_info))
self.df_save_asin_cate.show(10, truncate=False) self.df_save_asin_cate.show(10, truncate=False)
self.save_data_common( self.save_data_common(
df_save=self.df_save_asin_cate, df_save=self.df_save_asin_cate,
db_save=self.db_save_cate, db_save=self.db_save_cate,
partitions_num=self.partitions_num, partitions_num=self.partitions_num,
partitions_by=["site_name"] partitions_by=self.partitions_by,
# partitions_by=["site_name"],
) )
# self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_type", F.lit(self.date_type)) # self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_type", F.lit(self.date_type))
# self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_info", F.lit(self.date_info)) # self.df_save_asin_cate = self.df_save_asin_cate.withColumn("date_info", F.lit(self.date_info))
......
...@@ -9,9 +9,10 @@ engine = get_remote_engine( ...@@ -9,9 +9,10 @@ engine = get_remote_engine(
db_type="postgresql_14", # -> 服务端 alias "mysql" db_type="postgresql_14", # -> 服务端 alias "mysql"
) )
site_name = 'us' site_name = sys.argv[1] # 参数1:站点
date_type = 'day' date_type = sys.argv[2] # 参数2:类型:day/week/4_week/month/quarter
date_info = '2026-02-04' date_info = sys.argv[3] # 参数3:年-月-日/年-周/年-月/年-季, 比如: 2022-1
partitions = { partitions = {
'site_name': site_name, 'site_name': site_name,
'date_type': date_type, 'date_type': date_type,
...@@ -19,9 +20,12 @@ partitions = { ...@@ -19,9 +20,12 @@ partitions = {
} }
cols_list = ['asin', 'asin_cate_flag', 'date_info'] cols_list = ['asin', 'asin_cate_flag', 'date_info']
import_table=f'{site_name}_all_syn_st_day_{date_info.replace("-", "_")}'
engine.execute(f"truncate {import_table};")
print(f"清空对应的pg14-asin导出表: {import_table}")
engine.sqoop_raw_export( engine.sqoop_raw_export(
hive_table='dwd_nsr_bsr_keepa_asin', hive_table='dwd_nsr_bsr_keepa_asin',
import_table=f'{site_name}_all_syn_st_day_{date_info.replace("-", "_")}', import_table=import_table,
partitions=partitions, partitions=partitions,
m=1, m=1,
cols=','.join(cols_list) cols=','.join(cols_list)
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment