70 lines
1.9 KiB
Python
70 lines
1.9 KiB
Python
# -*- coding: utf-8 -*-
|
||
|
||
"""
|
||
清洗阿里云日志，25-06-06修订
|
||
"""
|
||
import csv
|
||
import os
|
||
import re
|
||
import sys
|
||
from datetime import datetime
|
||
|
||
import pandas
|
||
|
||
from utils.pandas_extension import save_as_workbook
|
||
|
||
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
||
|
||
print("正在清洗阿里云日志...", end="")
|
||
|
||
# 清洗后数据
|
||
data_processed = []
|
||
|
||
# 打开阿里云日志（将文件对象作为迭代器）
|
||
with open("log.csv", "r", encoding="utf-8") as file:
|
||
records = csv.DictReader(file)
|
||
for record in records:
|
||
# noinspection PyDictCreation
|
||
data = {}
|
||
|
||
# 解析时间戳
|
||
data["time"] = datetime.fromtimestamp(int(record["__time__"])).strftime(
|
||
"%Y-%m-%d %H:%M:%S"
|
||
)
|
||
|
||
# 解析MESSAGE
|
||
message = record.get("message")
|
||
if message is None:
|
||
continue
|
||
|
||
for line in message.split("\n"):
|
||
# 解析用户标识
|
||
if line.startswith("user_id"):
|
||
if search := re.search(r"user_id\s*:\s*(?P<user_id>\d+)", line):
|
||
data["user_id"] = search.group("user_id")
|
||
|
||
# 解析登录设备终端和版本号
|
||
if line.startswith("request params"):
|
||
# 解析staticTerminal
|
||
if search := re.search(
|
||
r"staticTerminal=(?P<static_terminal>[^&]+)", line
|
||
):
|
||
data["static_terminal"] = search.group("static_terminal")
|
||
# 解析staticVersion
|
||
if search := re.search(
|
||
r"staticVersion=(?P<static_version>[^&]+)", line
|
||
):
|
||
data["static_version"] = search.group("static_version")
|
||
|
||
data_processed.append(data)
|
||
|
||
dataset = pandas.DataFrame(data=data_processed)
|
||
|
||
print("已完成")
|
||
|
||
print("正在保存为工作簿...", end="")
|
||
|
||
save_as_workbook(worksheets=[("Sheet1", dataset)], workbook_name="data_processed.xlsx")
|
||
|
||
print("已完成")
|