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
import os
import sys
sys.path.append(os.path.dirname(sys.path[0]))
from utils.common_util import CommonUtil
from utils.hdfs_utils import HdfsUtils
from utils.spark_util import SparkUtil
from pyspark.sql import functions as F
from pyspark.sql.types import IntegerType
from yswg_utils.common_udf import udf_title_number_parse_reg
from utils.db_util import DBUtil
"""
根据不同的历史asin解析asin标题 获取标题中的信息
"""
class DwdAsinTitleNumber(object):
def __init__(self, site_name, date_type, date_info):
self.site_name = site_name
self.date_type = date_type
self.date_info = date_info
app_name = f"{self.__class__.__name__}:{site_name}:{date_type}:{date_info}"
self.spark = SparkUtil.get_spark_session(app_name)
self.hive_tb = "dwd_asin_title_number"
self.udf_title_number_parse_reg = udf_title_number_parse_reg()
def run(self):
sql = f"""
select
asin_title as title,
asin
from dim_asin_detail
where site_name = '{self.site_name}'
and date_type = '{CommonUtil.get_rel_date_type('dim_asin_detail', self.date_type)}'
and date_info = '{self.date_info}'
"""
print(sql)
df_asin_detail = self.spark.sql(sql)
sql = f"""
WITH ranked_edit_logs AS (
SELECT
edit_key_id,
val_after,
ROW_NUMBER() OVER (PARTITION BY edit_key_id ORDER BY create_time DESC) AS rn
FROM sys_edit_log
WHERE module = '流量选品'
AND filed = 'package_quantity'
AND site_name='{self.site_name}'
)
SELECT
edit_key_id AS asin,
cast(val_after as int) AS user_package_num
FROM ranked_edit_logs
WHERE rn = 1
"""
print(sql)
pg_con_info = DBUtil.get_connection_info("postgresql", "us")
if pg_con_info is not None:
df_user_package_num = SparkUtil.read_jdbc_query(
session=self.spark,
url=pg_con_info['url'],
pwd=pg_con_info['pwd'],
username=pg_con_info['username'],
query=sql
)
df_user_package_num = F.broadcast(df_user_package_num)
df_asin_detail = df_asin_detail.withColumn(
"split_detail",
F.explode(self.udf_title_number_parse_reg(F.col("title")))
)
df_all = df_asin_detail.join(
df_user_package_num, on='asin', how='left'
)
df_all = df_all.select(
F.col("asin"),
F.col("title"),
F.col("split_detail").getField("label").alias("label"),
# 注意强转成数字类型
F.coalesce(
F.col("user_package_num"),
F.col("split_detail").getField("value").cast(IntegerType())
).alias("value"),
F.col("split_detail").getField("match").alias("match"),
F.current_date().alias("update_time"),
F.lit(self.site_name).alias("site_name"),
F.lit(self.date_type).alias("date_type"),
F.lit(self.date_info).alias("date_info")
)
# 分区数量调整
df_save = df_all.repartition(5)
partition_dict = {
"site_name": self.site_name,
"date_type": self.date_type,
"date_info": self.date_info,
}
partition_by = list(partition_dict.keys())
hdfs_path = CommonUtil.build_hdfs_path(self.hive_tb, partition_dict=partition_dict)
print(f"清除hdfs目录中.....{hdfs_path}")
HdfsUtils.delete_hdfs_file(hdfs_path)
print(f"当前存储的表名为：{self.hive_tb},分区为{partition_by}", )
df_save.write.saveAsTable(name=self.hive_tb, format='hive', mode='append', partitionBy=partition_by)
print("success")
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)
obj = DwdAsinTitleNumber(site_name, date_type, date_info)
obj.run()