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
"""
author: 方星钧(ffman)
description: 清洗6大站点对应的 “ods_brand_analytics” 的表: 排名权重计算，用天补全周/30天/月，存储新增的关键词
table_read_name: ods_brand_analytics
table_save_name: ods_st_key
table_save_level: ods
version: 1.0
created_date: 2022-11-22
updated_date: 2022-11-22
"""
import os
import sys
sys.path.append(os.path.dirname(sys.path[0])) # 上级目录
from pyspark.storagelevel import StorageLevel
from utils.templates import Templates
# from ..utils.templates import Templates
# from AmazonSpider.pyspark_job.utils.templates_test import Templates
from pyspark.sql.types import StringType
# 分组排序的udf窗口函数
from pyspark.sql.window import Window
from pyspark.sql import functions as F
import uuid
class OdsStKey(Templates):
def __init__(self, site_name='us', date_type="month", date_info='2022-1'):
super().__init__()
self.site_name = site_name
self.db_save = f'ods_st_key'
self.spark = self.create_spark_object(app_name=f"{self.db_save}: {self.site_name}")
self.df_st = self.spark.sql(f"select 1+1;")
self.df_st_key = self.spark.sql(f"select 1+1;")
self.df_save = self.spark.sql(f"select 1+1;")
self.partitions_num = 1
self.reset_partitions(partitions_num=self.partitions_num)
self.partitions_by = ['site_name']
def read_data(self):
print("1.1 读取ods_brand_analytics表")
sql = f"select search_term from ods_brand_analytics where site_name='{self.site_name}' and date_type in ('day', 'week', 'month', 'quarter');"
print("sql:", sql)
self.df_st = self.spark.sql(sql).cache()
self.df_st.show(10, truncate=False)
print("1.2 读取ods_st_key表")
sql = f"select search_term, 1 as flag from ods_st_key where site_name='{self.site_name}';"
print("sql:", sql)
self.df_st_key = self.spark.sql(sql).cache()
self.df_st_key.show(10, truncate=False)
def handle_data(self):
self.df_st = self.df_st.drop_duplicates(['search_term'])
self.df_st = self.df_st.join(
self.df_st_key, on=['search_term'], how='left'
)
self.df_st = self.df_st.filter('flag is null')
if self.df_st.count() == 0:
print("新增关键词数量为0, 退出")
quit()
window = Window.orderBy(
self.df_st.search_term.asc()
)
self.df_st = self.df_st.withColumn("st_key", F.row_number().over(window=window))
self.df_st = self.df_st.withColumn("st_key", self.df_st_key.count()+self.df_st.st_key)
# self.df_st = self.df_st.withColumn("st_key", F.concat(F.lit("st_"), self.df_st.st_key))
self.df_st.show(10, truncate=False)
print("self.df_st新增:", self.df_st.count())
self.df_st = self.df_st.drop("flag")
self.df_st = self.df_st.withColumn("site_name", F.lit(self.site_name))
self.df_save = self.df_st
if __name__ == '__main__':
site_name = sys.argv[1] # 参数1：站点
handle_obj = OdsStKey(site_name=site_name)
handle_obj.run()