第8课: 文件操作

打开和关闭文件

Python提供了内置的open()函数来操作文件。

基本语法

# 打开文件
file = open("example.txt", "r")
content = file.read()
file.close()  # 必须关闭文件

# 推荐使用with语句（自动关闭）
with open("example.txt", "r") as file:
    content = file.read()
# 文件自动关闭

文件打开模式

r：只读模式（默认）
w：写入模式（覆盖原文件）
a：追加模式（在文件末尾添加）
r+：读写模式
b：二进制模式（如rb、wb）
x：独占创建模式（文件存在则失败）

读取文件

读取整个文件

with open("data.txt", "r", encoding="utf-8") as file:
    content = file.read()
    print(content)

按行读取

# 方法1：readline()
with open("data.txt", "r", encoding="utf-8") as file:
    line = file.readline()
    while line:
        print(line.strip())  # strip()去除换行符
        line = file.readline()

# 方法2：readlines()
with open("data.txt", "r", encoding="utf-8") as file:
    lines = file.readlines()
    for line in lines:
        print(line.strip())

# 方法3：迭代文件对象（推荐）
with open("data.txt", "r", encoding="utf-8") as file:
    for line in file:
        print(line.strip())

读取指定字节数

with open("data.txt", "r", encoding="utf-8") as file:
    chunk = file.read(100)  # 读取前100个字符
    print(chunk)

写入文件

写入文本

# 覆盖写入
with open("output.txt", "w", encoding="utf-8") as file:
    file.write("Hello, Python!\n")
    file.write("这是第二行\n")

# 追加写入
with open("output.txt", "a", encoding="utf-8") as file:
    file.write("追加的内容\n")

# 写入多行
lines = ["第一行\n", "第二行\n", "第三行\n"]
with open("output.txt", "w", encoding="utf-8") as file:
    file.writelines(lines)

文件路径操作

使用os和pathlib模块处理文件路径。

os模块

import os

# 获取当前工作目录
print(os.getcwd())

# 改变工作目录
os.chdir("/path/to/directory")

# 列出目录内容
files = os.listdir(".")
print(files)

# 检查路径是否存在
if os.path.exists("data.txt"):
    print("文件存在")

# 检查是否为文件或目录
print(os.path.isfile("data.txt"))  # True
print(os.path.isdir("folder"))     # True

# 获取文件大小
size = os.path.getsize("data.txt")
print(f"文件大小: {size}字节")

# 拼接路径
path = os.path.join("folder", "subfolder", "file.txt")
print(path)

pathlib模块（推荐）

from pathlib import Path

# 创建Path对象
p = Path("data.txt")

# 检查文件是否存在
if p.exists():
    print("文件存在")

# 读取文件
content = p.read_text(encoding="utf-8")

# 写入文件
p.write_text("Hello, World!", encoding="utf-8")

# 获取文件信息
print(p.name)        # 文件名
print(p.stem)        # 文件名（不含扩展名）
print(p.suffix)      # 扩展名
print(p.parent)      # 父目录

# 遍历目录
folder = Path(".")
for file in folder.glob("*.txt"):
    print(file)

目录操作

import os

# 创建目录
os.mkdir("new_folder")

# 创建多级目录
os.makedirs("parent/child/grandchild")

# 删除空目录
os.rmdir("new_folder")

# 删除文件
os.remove("file.txt")

# 重命名文件或目录
os.rename("old_name.txt", "new_name.txt")

# 遍历目录树
for root, dirs, files in os.walk("."):
    print(f"目录: {root}")
    for file in files:
        print(f"  文件: {file}")

处理CSV文件

import csv

# 读取CSV
with open("data.csv", "r", encoding="utf-8") as file:
    reader = csv.reader(file)
    for row in reader:
        print(row)

# 使用字典读取CSV
with open("data.csv", "r", encoding="utf-8") as file:
    reader = csv.DictReader(file)
    for row in reader:
        print(row["name"], row["age"])

# 写入CSV
data = [
    ["姓名", "年龄", "城市"],
    ["张三", "25", "北京"],
    ["李四", "30", "上海"]
]

with open("output.csv", "w", encoding="utf-8", newline="") as file:
    writer = csv.writer(file)
    writer.writerows(data)

处理JSON文件

import json

# 读取JSON
with open("data.json", "r", encoding="utf-8") as file:
    data = json.load(file)
    print(data)

# 写入JSON
data = {
    "name": "张三",
    "age": 25,
    "skills": ["Python", "Java", "JavaScript"]
}

with open("output.json", "w", encoding="utf-8") as file:
    json.dump(data, file, ensure_ascii=False, indent=4)

# JSON字符串转换
json_str = json.dumps(data, ensure_ascii=False)
data_dict = json.loads(json_str)

二进制文件操作

# 读取二进制文件
with open("image.jpg", "rb") as file:
    data = file.read()
    print(f"文件大小: {len(data)}字节")

# 写入二进制文件
with open("copy.jpg", "wb") as file:
    file.write(data)

# 复制文件
import shutil
shutil.copy("source.txt", "destination.txt")
shutil.copytree("source_folder", "dest_folder")

文件操作最佳实践

始终使用with语句管理文件
指定正确的编码（通常是utf-8）
处理可能的异常
使用pathlib处理路径
大文件分块读取

# 大文件分块读取
def read_large_file(file_path, chunk_size=1024):
    with open(file_path, "r", encoding="utf-8") as file:
        while True:
            chunk = file.read(chunk_size)
            if not chunk:
                break
            yield chunk

for chunk in read_large_file("large_file.txt"):
    process(chunk)

练习

创建一个程序，读取文本文件并统计单词数量
编写函数复制文件内容到新文件
创建一个学生信息管理程序，使用JSON存储数据
编写程序遍历目录，列出所有.py文件

练习答案：

# 练习1：统计单词
def count_words(filename):
    with open(filename, "r", encoding="utf-8") as file:
        content = file.read()
        words = content.split()
        return len(words)

print(f"单词数: {count_words('data.txt')}")

# 练习2：复制文件
def copy_file(source, destination):
    with open(source, "r", encoding="utf-8") as src:
        content = src.read()
    with open(destination, "w", encoding="utf-8") as dst:
        dst.write(content)

copy_file("source.txt", "copy.txt")

# 练习3：学生信息管理
import json

def save_students(students, filename):
    with open(filename, "w", encoding="utf-8") as f:
        json.dump(students, f, ensure_ascii=False, indent=4)

def load_students(filename):
    with open(filename, "r", encoding="utf-8") as f:
        return json.load(f)

students = [
    {"name": "张三", "age": 20, "grade": "A"},
    {"name": "李四", "age": 21, "grade": "B"}
]
save_students(students, "students.json")

# 练习4：列出Python文件
from pathlib import Path

def list_python_files(directory):
    path = Path(directory)
    for file in path.rglob("*.py"):
        print(file)

list_python_files(".")

上一课下一课: 常用标准库