从基础到高级详解Python中文件操作的全攻略实战指南

with open('notes.txt', 'r', encoding='utf-8') as file:
    content = file.read()
    print(content[:50])  # 打印前50个字符

# 传统方式（易出错）
file = open('data.txt', 'w')
file.write('重要数据')
# 忘记close()导致数据未保存！

# 正确方式（自动关闭）
with open('data.txt', 'w') as file:
    file.write('自动保存的数据')
# 离开with块后文件自动关闭

with open('config.json', 'r') as f:
    full_content = f.read()  # 返回整个字符串
    print(full_content)

error_count = 0
with open('server.log', 'r') as f:
    for line in f:  # 逐行读取，内存占用恒定
        if 'ERROR' in line:
            error_count += 1
print(f"发现{error_count}个错误")

error_count = 0
with open('server.log', 'r') as f:
    for line in f:  # 逐行读取，内存占用恒定
        if 'ERROR' in line:
            error_count += 1
print(f"发现{error_count}个错误")

with open('output.txt', 'w') as f:
    f.write('第一行内容\n')  # 必须手动添加换行符

data = ['苹果\n', '香蕉\n', '橙子\n']
with open('fruits.txt', 'w') as f:
    f.writelines(data)  # 不会自动添加换行符！

clean_data = [f"{item}\n" for item in ['苹果', '香蕉']]

with open('demo.txt', 'r+') as f:
    # 定位到第5个字节
    f.seek(5)
    # 读取后续10个字符
    print(f.read(10))
    # 回到文件头插入内容
    f.seek(0)
    f.write('新开头')

# 复制图片
with open('original.jpg', 'rb') as src:
    data = src.read()
with open('copy.jpg', 'wb') as dst:
    dst.write(data)

import struct
with open('data.bin', 'rb') as f:
    # 读取4字节整数+8字节浮点数
    int_data, float_data = struct.unpack('if', f.read(12))

def analyze_log(log_path):
    errors, warnings = 0, 0
    with open(log_path, 'r') as f:
        for line in f:
            if 'ERROR' in line:
                errors += 1
            elif 'WARNING' in line:
                warnings += 1
    return errors, warnings

# 使用示例
err, warn = analyze_log('app.log')
print(f"错误:{err} 警告:{warn}")

import csv

def clean_csv(input_path, output_path):
    with open(input_path, 'r') as infile, \
         open(output_path, 'w', newline='') as outfile:
        
        reader = csv.DictReader(infile)
        fieldnames = reader.fieldnames
        writer = csv.DictWriter(outfile, fieldnames=fieldnames)
        writer.writeheader()

        for row in reader:
            # 填充缺失的age字段为0
            row['age'] = row.get('age', '0')
            writer.writerow(row)

# 使用示例
clean_csv('raw_data.csv', 'cleaned_data.csv')

def process_large_file(file_path, chunk_size=1024*1024):  # 默认1MB
    with open(file_path, 'r') as f:
        while True:
            chunk = f.read(chunk_size)
            if not chunk:
                break
            # 处理每个数据块
            analyze_chunk(chunk)

def analyze_chunk(chunk):
    # 示例：统计块中的IP地址
    ips = [line.split()[0] for line in chunk.splitlines() 
           if line.startswith('192.168')]
    print(f"发现{len(ips)}个内网IP")

import os

def safe_write(file_path, content):
    try:
        # 确保目录存在
        os.makedirs(os.path.dirname(file_path), exist_ok=True)
        with open(file_path, 'w') as f:
            f.write(content)
    except IOError as e:
        print(f"文件写入失败: {e}")
    except Exception as e:
        print(f"未知错误: {e}")

# 使用示例
safe_write('backup/2025.log', '系统备份数据')

from pathlib import Path

# 路径拼接
config_path = Path('config') / 'settings.ini'

# 检查文件是否存在
if config_path.exists():
    print(config_path.read_text(encoding='utf-8'))

import tempfile

# 创建临时文件（自动删除）
with tempfile.NamedTemporaryFile(mode='w+', delete=True) as tmp:
    tmp.write('临时数据')
    tmp.seek(0)
    print(tmp.read())  # 输出: 临时数据
# 离开with块后文件自动删除

import mmap

with open('huge_file.dat', 'r+b') as f:
    # 映射整个文件到内存
    with mmap.mmap(f.fileno(), 0) as mm:
        # 像操作字符串一样处理文件
        print(mm[:100].decode('utf-8'))  # 读取前100字节