【Python专项】Nginx访问日志分析时间范围处理示例

Nginx访问日志分析与处理

用 Python 实现 Nginx 日志的解析、筛选、存储与回读全流程

一、日志格式

1.224.235.228 - - [06/May/2025:14:47:15 +0000] "GET /login HTTP/1.1" 500 1665 "http://example.com/api/data" "PostmanRuntime/7.28.4"

按空格拆分，关键字段索引：

字段	索引	处理
IP	[0]	直接取
时间	[3]	去掉开头 [
方法	[5]	去掉开头 "
路径	[6]	直接取
状态码	[8]	直接取

二、时间筛选

import datetime

def log_filter_by_time(log_file, start_time, end_time):
    result = []
    with open(log_file, 'r', encoding='utf-8') as file:
        for line in file:
            parts = line.split()
            log_time = datetime.datetime.strptime(parts[3][1:], '%d/%b/%Y:%H:%M:%S')
            if start_time <= log_time <= end_time:
                result.append({
                    'IP': parts[0],
                    'Time': parts[3][1:],
                    'Method': parts[5][1:],
                    'Path': parts[6],
                    'Stats_Code': parts[8],
                })
    return result

三、JSON存储与回读

import json

def save_data_to_json(result, json_file):
    with open(json_file, 'w', encoding='utf-8') as file:
        json.dump(result, file, indent=2, ensure_ascii=False)
    print(f"数据已保存至 {json_file}")

def load_data_to_python(json_file):
    with open(json_file, 'r', encoding='utf-8') as file:
        return json.load(file)

参数说明：

• indent=2 --- 格式化输出，方便阅读
• ensure_ascii=False --- 正确显示中文

四、程序入口

if __name__ == '__main__':
    log_file = './nginx_access.log'
    start_time = datetime.datetime.strptime('09/May/2025:15:00:00', '%d/%b/%Y:%H:%M:%S')
    end_time = datetime.datetime.strptime('09/May/2025:15:30:00', '%d/%b/%Y:%H:%M:%S')

    log_filter = log_filter_by_time(log_file, start_time, end_time)
    save_data_to_json(log_filter, './xxx.json')
    log_result = load_data_to_python('./xxx.json')

    for i in log_result:
        print(i)

五、源码

"""
1.224.235.228 - - [06/May/2025:14:47:15 +0000] "GET /login HTTP/1.1" 500 1665 "http://example.com/api/data" "PostmanRuntime/7.28.4"
拆解索引位置：
    IP          -> 0 -> [0]
    Time        -> 3 -> [3][1:]
    Method      -> 5 -> [5][1:]
    Path        -> 6 -> [6]
    Stats_Code  -> 8 -> [8]

    "Nginx 访问日志时间筛选工具"
"""
import json
import datetime

# 定义日志筛选函数 --> 筛选出符合要求的信息
def log_filter_by_time(log_file,start_time,end_time):
    result = []
    with open(log_file,'r',encoding='utf-8') as file:
        for line in file:
            parts = line.split()
            log_time = datetime.datetime.strptime(parts[3][1:],'%d/%b/%Y:%H:%M:%S')
            if start_time <= log_time <= end_time:
                result.append({
                    'IP':parts[0],
                    'Time':parts[3][1:],
                    'Method':parts[5][1:],
                    'Path':parts[6],
                    'Stats_Code':parts[8],
                })
    return result

# 定义信息存储函数 --> 将筛选出的Python列表-->Json数据文件
def save_data_to_json(result,json_file):
    with open(json_file,'w',encoding='utf-8') as file:
        json.dump(result,file,indent=2,ensure_ascii=False)
    print(f"恭喜，数据已经保存至{json_file}文件中，你可以去查看一下！")

# 定义Json读取函数 --> 将Json数据转换成Python对象
def load_data_to_python(json_file):
    with open(json_file,'r',encoding='utf-8') as file:
        result = json.load(file)
    return result

# 定义程序入口
if __name__ == '__main__':
    log_file = './nginx_access.log'
    start_time = datetime.datetime.strptime('09/May/2025:15:00:00','%d/%b/%Y:%H:%M:%S')
    end_time = datetime.datetime.strptime('09/May/2025:15:30:00','%d/%b/%Y:%H:%M:%S')

    log_filter = log_filter_by_time(log_file,start_time,end_time)
    save_data_to_json(log_filter,'./xxx.json')
    log_result = load_data_to_python('./xxx.json')

    for i in log_result:
        print(i)