Skip to content
Toggle navigation
P
Projects
G
Groups
S
Snippets
Help
岳巧源
/
python_script
This project
Loading...
Sign in
Toggle navigation
Go to a project
Project
Repository
Issues
0
Merge Requests
0
Pipelines
Wiki
Snippets
Settings
Activity
Graph
Charts
Create a new issue
Jobs
Commits
Issue Boards
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Charts
Commit
e84b5900
authored
Jul 31, 2024
by
岳巧源
Browse files
Options
_('Browse Files')
Download
Email Patches
Plain Diff
add config
parent
c62ff215
Show whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
65 additions
and
18 deletions
push.py
waldom_data_process_RMB.py
waldom_data_process_USD.py
push.py
View file @
e84b5900
...
...
@@ -2,11 +2,13 @@ import pika
import
toml
import
logging
# 正式环境配置文件位置
config_toml
=
"/data/golang/src/europa-erp-go/manifest/config/config.toml"
config
=
toml
.
load
(
config_toml
)
logging
.
basicConfig
(
level
=
logging
.
INFO
,
filename
=
log_path
,
format
=
'
%(asctime)
s -
%(name)
s -
%(levelname)
s -
%(message)
s'
)
logger
=
logging
.
getLogger
(
"
download
.py"
)
logging
.
basicConfig
(
level
=
logging
.
INFO
,
filename
=
'result.log'
,
format
=
'
%(asctime)
s -
%(name)
s -
%(levelname)
s -
%(message)
s'
)
logger
=
logging
.
getLogger
(
"
push
.py"
)
# 生产环境请修改rabbitmq连接信息
rabbit_mq_host
=
config
[
"producer"
][
"rabbit_mq_host"
]
...
...
@@ -36,3 +38,7 @@ class Producer:
logger
.
info
(
"rabbitmq重新获取连接!"
)
self
.
channel
.
basic_publish
(
exchange
=
rabbit_mq_exchange
,
routing_key
=
rabbit_mq_routing_key
,
body
=
str
.
encode
(
message
))
def
close
(
self
):
self
.
channel
.
close
()
self
.
channel
=
None
\ No newline at end of file
waldom_data_process_RMB.py
View file @
e84b5900
...
...
@@ -6,13 +6,13 @@ import time
import
requests
import
push
import
os
import
pandas
as
pd
file_name
=
'Tianyang_Inventory_Feed_RMB.xlsx'
url
=
"https://www.waldomchina.com/dailyFeed/Tianyang_Inventory_Feed_RMB.xlsx"
logging
.
basicConfig
(
level
=
logging
.
INFO
,
filename
=
'waldom_
usd
.log'
,
logging
.
basicConfig
(
level
=
logging
.
INFO
,
filename
=
'waldom_
rmb
.log'
,
format
=
'
%(asctime)
s -
%(name)
s -
%(levelname)
s -
%(message)
s'
)
logger
=
logging
.
getLogger
(
'waldom_data_process_RMB.py'
)
...
...
@@ -44,15 +44,21 @@ ladder_map = {
'Price Break Qty 9'
:
'Price Break 9'
,
}
producer
=
push
.
Producer
()
producer
.
get_connn
()
def
download_file
(
url
=
""
):
start
=
time
.
time
()
response
=
requests
.
get
(
url
=
url
)
with
open
(
file_name
,
'wb'
)
as
f
:
f
.
write
(
response
.
content
)
logger
.
info
(
"文件
%
s 下载完成"
%
file_name
)
end
=
time
.
time
()
logger
.
info
(
"文件
%
s 下载完成, 用时
%
s"
%
(
file_name
,
str
(
end
-
start
)))
class
HandleCSV
:
def
parse
(
self
,
path
):
result
=
[]
df
=
pd
.
read_excel
(
path
,
sheet_name
=
0
)
if
not
self
.
validate
(
df
.
columns
.
values
):
logger
.
error
(
"文件
%
s 格式错误"
%
path
)
...
...
@@ -107,9 +113,9 @@ class HandleCSV:
batch_sn_map
[
key
]
=
int
(
value
)
table
[
'batch_sn'
]
=
batch_sn_map
json_str
=
json
.
dumps
(
table
,
ensure_ascii
=
False
)
result
.
append
(
json_str
)
self
.
push_to_mq
(
json_str
)
print
(
json_str
)
return
result
...
...
@@ -121,6 +127,9 @@ class HandleCSV:
count
+=
1
return
count
==
size
def
push_to_mq
(
self
,
msg
:
str
):
producer
.
push
(
msg
)
if
__name__
==
'__main__'
:
...
...
@@ -128,11 +137,14 @@ if __name__ == '__main__':
# 首先下载所需的文件
download_file
(
url
)
time
.
sleep
(
1
)
# 处理成为json字符串数组
res
=
HandleCSV
()
.
parse
(
file_name
)
# 推送mq队列
# 处理并推送json字符串数组
HandleCSV
()
.
parse
(
file_name
)
time
.
sleep
(
1
)
producer
.
close
()
# 清理下载的文件
os
.
remove
(
file_name
)
end
=
time
.
time
()
logger
.
info
(
"spend time: "
+
str
(
end
-
start
))
logger
.
info
(
"
rmb file total
spend time: "
+
str
(
end
-
start
))
...
...
waldom_data_process_USD.py
View file @
e84b5900
import
csv
import
json
import
logging
import
os
import
time
import
requests
import
push
logging
.
basicConfig
(
level
=
logging
.
INFO
,
filename
=
'waldom_dollar.log'
,
format
=
'
%(asctime)
s -
%(name)
s -
%(levelname)
s -
%(message)
s'
)
logger
=
logging
.
getLogger
(
'waldom_data_process_USD.py'
)
# Tianyang_InventoryFeed title字段含义
...
...
@@ -23,10 +26,24 @@ ladder_map = {
'Price Break Qty 4'
,
'Price Break Qty 5'
,
'Price Break Qty 6'
,
'Price Break Qty 7'
,
'Price Break Qty 8'
,
'Price Break Qty 9'
,
}
file_name
=
"Tianyang_InventoryFeed.csv"
url
=
"https://www.waldomapac.com/dailyFeed/Tianyang_InventoryFeed.csv"
producer
=
push
.
Producer
()
producer
.
get_connn
()
def
download_file
(
url
=
""
):
start
=
time
.
time
()
response
=
requests
.
get
(
url
=
url
)
with
open
(
file_name
,
'wb'
)
as
f
:
f
.
write
(
response
.
content
)
end
=
time
.
time
()
logger
.
info
(
"文件
%
s 下载完成, 用时
%
s"
%
(
file_name
,
str
(
end
-
start
)))
class
HandleCSV
:
def
parse
(
self
,
path
):
with
open
(
path
,
encoding
=
'gbk'
,
errors
=
'ignore'
)
as
f
:
result
=
[]
first_line
=
[]
reader
=
csv
.
reader
(
f
)
for
index
,
row
in
enumerate
(
reader
):
...
...
@@ -38,10 +55,10 @@ class HandleCSV:
return
[]
else
:
json_str
=
self
.
generate_json
(
row
,
first_line
)
self
.
push_to_mq
(
json_str
)
print
(
json_str
)
result
.
append
(
json_str
)
logger
.
info
(
"文件
%
s 已解析"
%
path
)
return
result
# 校验excel表头符合既定格式
def
validate
(
self
,
arr
:
list
)
->
bool
:
...
...
@@ -103,9 +120,20 @@ class HandleCSV:
table
[
'batch_sn'
]
=
batch_sn_map
return
json
.
dumps
(
table
,
ensure_ascii
=
False
)
def
push_to_mq
(
self
,
msg
:
str
):
producer
.
push
(
msg
)
if
__name__
==
'__main__'
:
result
=
HandleCSV
()
.
parse
(
'Tianyang_InventoryFeed.csv'
)
print
(
result
)
start
=
time
.
time
()
download_file
(
url
)
time
.
sleep
(
1
)
HandleCSV
()
.
parse
(
file_name
)
time
.
sleep
(
1
)
producer
.
close
()
os
.
remove
(
file_name
)
end
=
time
.
time
()
logger
.
info
(
"usd file total spend time: "
+
str
(
end
-
start
))
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment