Python 文件操作

7年前端辞职转AI2026-04-14 18:18

Python 文件操作

目录

  • 文件基础
  • 文本文件操作
  • 二进制文件操作
  • 文件和目录管理
  • [CSV 文件操作](#CSV 文件操作 "#csv-%E6%96%87%E4%BB%B6%E6%93%8D%E4%BD%9C")
  • [JSON 文件操作](#JSON 文件操作 "#json-%E6%96%87%E4%BB%B6%E6%93%8D%E4%BD%9C")
  • [Excel 文件操作](#Excel 文件操作 "#excel-%E6%96%87%E4%BB%B6%E6%93%8D%E4%BD%9C")
  • [路径操作 pathlib](#路径操作 pathlib "#%E8%B7%AF%E5%BE%84%E6%93%8D%E4%BD%9C-pathlib")
  • 综合实战

文件基础

打开和关闭文件

python 复制代码 
# 传统方式（不推荐）
file = open("test.txt", "r")
content = file.read()
file.close()  # 必须手动关闭

# 推荐方式：使用 with 语句
with open("test.txt", "r") as file:
    content = file.read()
# 自动关闭文件，即使发生异常

文件打开模式

模式 说明 文件不存在
r 只读（默认） 报错
w 写入（覆盖） 创建
a 追加 创建
x 独占创建 创建，已存在则报错
r+ 读写 报错
w+ 读写（覆盖） 创建
a+ 读写（追加） 创建
rb 二进制只读 报错
wb 二进制写入 创建

指定编码

python 复制代码 
# 处理中文文件时指定编码
with open("chinese.txt", "r", encoding="utf-8") as f:
    content = f.read()

# Windows 系统可能需要指定 encoding='gbk'
with open("windows_file.txt", "r", encoding="gbk") as f:
    content = f.read()

文本文件操作

读取文件

python 复制代码 
# 方法1: read() - 读取全部内容
with open("test.txt", "r", encoding="utf-8") as f:
    content = f.read()
    print(content)

# 方法2: readline() - 逐行读取
with open("test.txt", "r", encoding="utf-8") as f:
    line1 = f.readline()  # 读取第一行
    line2 = f.readline()  # 读取第二行
    print(line1.strip())  # strip() 去除换行符
    print(line2.strip())

# 方法3: readlines() - 读取所有行为列表
with open("test.txt", "r", encoding="utf-8") as f:
    lines = f.readlines()
    for line in lines:
        print(line.strip())

# 方法4: 直接遍历（推荐，内存效率高）
with open("test.txt", "r", encoding="utf-8") as f:
    for line in f:
        print(line.strip())

写入文件

python 复制代码 
# 写入文件（覆盖模式）
with open("output.txt", "w", encoding="utf-8") as f:
    f.write("第一行\n")
    f.write("第二行\n")
    f.write("第三行\n")

# 使用 print 写入
with open("output.txt", "w", encoding="utf-8") as f:
    print("Hello", file=f)
    print("World", file=f)

# 写入多行
lines = ["苹果\n", "香蕉\n", "橙子\n"]
with open("fruits.txt", "w", encoding="utf-8") as f:
    f.writelines(lines)

追加内容

python 复制代码 
# 追加模式
with open("log.txt", "a", encoding="utf-8") as f:
    f.write("2024-01-15 10:30:00 - 用户登录\n")
    f.write("2024-01-15 10:35:00 - 查看商品\n")

文件指针操作

python 复制代码 
with open("test.txt", "r", encoding="utf-8") as f:
    # 读取前10个字符
    content = f.read(10)
    print(f"当前位置: {f.tell()}")  # 显示当前指针位置

    # 移动指针到开头
    f.seek(0)

    # 再次读取
    content = f.read(10)
    print(content)

实战示例：文件复制

python 复制代码 
def copy_file(src, dst):
    """复制文件"""
    with open(src, "r", encoding="utf-8") as f_src:
        with open(dst, "w", encoding="utf-8") as f_dst:
            for line in f_src:
                f_dst.write(line)
    print(f"文件已从 {src} 复制到 {dst}")

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

二进制文件操作

读取二进制文件

python 复制代码 
# 读取图片
with open("image.jpg", "rb") as f:
    data = f.read()
    print(f"文件大小: {len(data)} 字节")

# 读取部分数据
with open("image.jpg", "rb") as f:
    header = f.read(100)  # 读取前100字节

写入二进制文件

python 复制代码 
# 写入二进制数据
data = bytes([0x89, 0x50, 0x4E, 0x47])  # PNG 文件头
with open("output.bin", "wb") as f:
    f.write(data)

复制二进制文件

python 复制代码 
def copy_binary_file(src, dst):
    """复制二进制文件"""
    with open(src, "rb") as f_src:
        with open(dst, "wb") as f_dst:
            while True:
                chunk = f_src.read(4096)  # 分块读取
                if not chunk:
                    break
                f_dst.write(chunk)
    print(f"二进制文件已复制")

copy_binary_file("photo.jpg", "photo_copy.jpg")

文件和目录管理

os 模块

python 复制代码 
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)

# 创建目录
os.mkdir("new_folder")
os.makedirs("parent/child/grandchild", exist_ok=True)  # 递归创建

# 删除目录
os.rmdir("empty_folder")
os.removedirs("parent/child/grandchild")  # 递归删除空目录

# 重命名
os.rename("old_name.txt", "new_name.txt")

# 删除文件
os.remove("file.txt")

# 判断路径类型
print(os.path.isfile("test.txt"))     # True/False
print(os.path.isdir("folder"))        # True/False
print(os.path.exists("path"))         # True/False

# 获取文件信息
stat_info = os.stat("test.txt")
print(f"文件大小: {stat_info.st_size} 字节")
print(f"创建时间: {stat_info.st_ctime}")
print(f"修改时间: {stat_info.st_mtime}")

shutil 模块

python 复制代码 
import shutil

# 复制文件
shutil.copy("source.txt", "destination.txt")
shutil.copy2("source.txt", "destination.txt")  # 保留元数据

# 复制目录
shutil.copytree("source_dir", "dest_dir")

# 移动文件/目录
shutil.move("old_path", "new_path")

# 删除目录及其内容
shutil.rmtree("directory")

# 获取磁盘使用情况
usage = shutil.disk_usage("/")
print(f"总空间: {usage.total / (1024**3):.2f} GB")
print(f"已用: {usage.used / (1024**3):.2f} GB")
print(f"可用: {usage.free / (1024**3):.2f} GB")

glob 模块 - 文件匹配

python 复制代码 
import glob

# 查找特定类型的文件
txt_files = glob.glob("*.txt")
print(txt_files)

# 递归查找
all_py_files = glob.glob("**/*.py", recursive=True)
print(all_py_files)

# 模式匹配
images = glob.glob("images/*.jpg")
logs = glob.glob("logs/2024-*.log")

CSV 文件操作

读取 CSV 文件

python 复制代码 
import csv

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

# 使用 DictReader（推荐）
with open("data.csv", "r", encoding="utf-8") as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row)
        # {'name': '张三', 'age': '25', 'city': '北京'}

写入 CSV 文件

python 复制代码 
import csv

# 基本写入
data = [
    ["姓名", "年龄", "城市"],
    ["张三", "25", "北京"],
    ["李四", "30", "上海"],
    ["王五", "28", "广州"]
]

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

# 使用 DictWriter（推荐）
data = [
    {"name": "张三", "age": 25, "city": "北京"},
    {"name": "李四", "age": 30, "city": "上海"},
    {"name": "王五", "age": 28, "city": "广州"}
]

fieldnames = ["name", "age", "city"]
with open("output.csv", "w", encoding="utf-8-sig", newline="") as f:
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerows(data)

CSV 实战：学生成绩管理

python 复制代码 
import csv
import os

class StudentManager:
    def __init__(self, filename="students.csv"):
        self.filename = filename
        self.students = []
        self.load_students()

    def load_students(self):
        """从 CSV 加载学生数据"""
        if not os.path.exists(self.filename):
            return

        with open(self.filename, "r", encoding="utf-8-sig") as f:
            reader = csv.DictReader(f)
            for row in reader:
                row["age"] = int(row["age"])
                row["score"] = float(row["score"])
                self.students.append(row)

    def save_students(self):
        """保存学生数据到 CSV"""
        fieldnames = ["name", "age", "major", "score"]
        with open(self.filename, "w", encoding="utf-8-sig", newline="") as f:
            writer = csv.DictWriter(f, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(self.students)

    def add_student(self, name, age, major, score):
        """添加学生"""
        student = {
            "name": name,
            "age": age,
            "major": major,
            "score": score
        }
        self.students.append(student)
        self.save_students()
        print(f"学生 {name} 添加成功")

    def show_all(self):
        """显示所有学生"""
        if not self.students:
            print("暂无学生数据")
            return

        print(f"\n{'姓名':<10}{'年龄':<6}{'专业':<15}{'成绩':<8}")
        print("-" * 45)
        for student in self.students:
            print(f"{student['name']:<10}{student['age']:<6}"
                  f"{student['major']:<15}{student['score']:<8.1f}")

        # 统计信息
        scores = [s["score"] for s in self.students]
        print("-" * 45)
        print(f"平均分: {sum(scores)/len(scores):.1f}")
        print(f"最高分: {max(scores):.1f}")
        print(f"最低分: {min(scores):.1f}")

# 使用示例
manager = StudentManager()
manager.add_student("张三", 20, "计算机科学", 90.5)
manager.add_student("李四", 22, "数学", 85.0)
manager.add_student("王五", 21, "物理", 92.3)
manager.show_all()

JSON 文件操作

基本操作

python 复制代码 
import json

# Python 对象转 JSON 字符串
data = {
    "name": "张三",
    "age": 25,
    "city": "北京",
    "hobbies": ["读书", "游泳", "编程"]
}

json_str = json.dumps(data, ensure_ascii=False, indent=2)
print(json_str)

# JSON 字符串转 Python 对象
parsed = json.loads(json_str)
print(parsed["name"])

读写 JSON 文件

python 复制代码 
import json

# 写入 JSON 文件
data = {
    "users": [
        {"name": "张三", "age": 25},
        {"name": "李四", "age": 30}
    ],
    "total": 2
}

with open("data.json", "w", encoding="utf-8") as f:
    json.dump(data, f, ensure_ascii=False, indent=2)

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

JSON 实战：配置文件管理

python 复制代码 
import json
import os

class ConfigManager:
    def __init__(self, filename="config.json"):
        self.filename = filename
        self.config = self.load_config()

    def load_config(self):
        """加载配置"""
        if os.path.exists(self.filename):
            with open(self.filename, "r", encoding="utf-8") as f:
                return json.load(f)
        return {}

    def save_config(self):
        """保存配置"""
        with open(self.filename, "w", encoding="utf-8") as f:
            json.dump(self.config, f, ensure_ascii=False, indent=2)

    def get(self, key, default=None):
        """获取配置项"""
        return self.config.get(key, default)

    def set(self, key, value):
        """设置配置项"""
        self.config[key] = value
        self.save_config()

    def delete(self, key):
        """删除配置项"""
        if key in self.config:
            del self.config[key]
            self.save_config()

# 使用示例
config = ConfigManager()

# 设置配置
config.set("database", {
    "host": "localhost",
    "port": 3306,
    "user": "root",
    "password": "123456"
})

config.set("app_name", "我的应用")
config.set("debug", True)

# 获取配置
db_config = config.get("database")
print(f"数据库主机: {db_config['host']}")
print(f"应用名称: {config.get('app_name')}")

Excel 文件操作

使用 openpyxl（需要安装）

bash 复制代码 
pip install openpyxl

创建 Excel 文件

python 复制代码 
from openpyxl import Workbook

# 创建工作簿
wb = Workbook()
ws = wb.active
ws.title = "学生成绩"

# 添加表头
headers = ["姓名", "语文", "数学", "英语", "总分"]
ws.append(headers)

# 添加数据
data = [
    ["张三", 90, 85, 92],
    ["李四", 88, 92, 87],
    ["王五", 95, 90, 88]
]

for row in data:
    # 计算总分
    total = sum(row[1:])
    ws.append(row + [total])

# 保存文件
wb.save("scores.xlsx")
print("Excel 文件已创建")

读取 Excel 文件

python 复制代码 
from openpyxl import load_workbook

# 加载工作簿
wb = load_workbook("scores.xlsx")
ws = wb.active

# 读取所有数据
print(f"工作表: {ws.title}")
print(f"行数: {ws.max_row}")
print(f"列数: {ws.max_column}")

# 遍历数据
for row in ws.iter_rows(min_row=1, values_only=True):
    print(row)

# 访问特定单元格
cell_value = ws["A2"].value
print(f"A2 的值: {cell_value}")

格式化 Excel

python 复制代码 
from openpyxl import Workbook
from openpyxl.styles import Font, Alignment, PatternFill

wb = Workbook()
ws = wb.active

# 设置字体
bold_font = Font(bold=True, color="FF0000", size=12)
normal_font = Font(size=11)

# 设置对齐
center_align = Alignment(horizontal="center", vertical="center")

# 设置填充
yellow_fill = PatternFill(start_color="FFFF00", end_color="FFFF00", fill_type="solid")

# 添加数据并格式化
ws["A1"] = "姓名"
ws["B1"] = "成绩"
ws["A1"].font = bold_font
ws["B1"].font = bold_font
ws["A1"].alignment = center_align
ws["B1"].alignment = center_align

ws["A2"] = "张三"
ws["B2"] = 95
ws["B2"].fill = yellow_fill

# 调整列宽
ws.column_dimensions["A"].width = 15
ws.column_dimensions["B"].width = 10

wb.save("formatted.xlsx")

路径操作 pathlib

Python 3.4+ 推荐的现代化路径操作方式。

基本操作

python 复制代码 
from pathlib import Path

# 创建路径对象
current_dir = Path(".")
absolute_path = Path("/home/user/documents")
relative_path = Path("folder/file.txt")

# 组合路径
config_path = Path.home() / ".config" / "myapp" / "config.json"
print(config_path)

# 获取路径信息
file_path = Path("documents/report.pdf")
print(file_path.name)       # report.pdf
print(file_path.stem)       # report
print(file_path.suffix)     # .pdf
print(file_path.parent)     # documents
print(file_path.absolute()) # 绝对路径

文件和目录操作

python 复制代码 
from pathlib import Path

# 创建目录
Path("new_folder").mkdir(exist_ok=True)
Path("parent/child").mkdir(parents=True, exist_ok=True)

# 检查路径
path = Path("test.txt")
print(path.exists())      # True/False
print(path.is_file())     # True/False
print(path.is_dir())      # True/False

# 读取文件
content = path.read_text(encoding="utf-8")
content_bytes = path.read_bytes()

# 写入文件
path.write_text("Hello, World!", encoding="utf-8")
path.write_bytes(b"binary data")

# 删除
path.unlink()             # 删除文件
Path("empty_dir").rmdir() # 删除空目录

遍历目录

python 复制代码 
from pathlib import Path

# 列出目录内容
current = Path(".")
for item in current.iterdir():
    print(item.name)

# 递归查找文件
for py_file in Path(".").rglob("*.py"):
    print(py_file)

# 查找特定模式
for txt_file in Path("documents").glob("*.txt"):
    print(txt_file)

路径操作示例

python 复制代码 
from pathlib import Path

def organize_files(directory):
    """按扩展名组织文件"""
    dir_path = Path(directory)

    if not dir_path.exists():
        print("目录不存在")
        return

    for file_path in dir_path.iterdir():
        if file_path.is_file():
            suffix = file_path.suffix.lower()
            if suffix:
                # 创建子目录
                subdir = dir_path / suffix[1:]  # 去掉点号
                subdir.mkdir(exist_ok=True)

                # 移动文件
                new_path = subdir / file_path.name
                file_path.rename(new_path)
                print(f"移动: {file_path.name} -> {subdir.name}/")

# 使用
organize_files("./downloads")

综合实战

实战1: 日志系统

python 复制代码 
import os
from datetime import datetime
from pathlib import Path

class Logger:
    def __init__(self, log_dir="logs"):
        self.log_dir = Path(log_dir)
        self.log_dir.mkdir(exist_ok=True)

        # 按日期创建日志文件
        today = datetime.now().strftime("%Y-%m-%d")
        self.log_file = self.log_dir / f"{today}.log"

    def _get_timestamp(self):
        """获取时间戳"""
        return datetime.now().strftime("%Y-%m-%d %H:%M:%S")

    def _write_log(self, level, message):
        """写入日志"""
        timestamp = self._get_timestamp()
        log_entry = f"[{timestamp}] [{level}] {message}\n"

        with open(self.log_file, "a", encoding="utf-8") as f:
            f.write(log_entry)

        # 同时输出到控制台
        print(log_entry.strip())

    def info(self, message):
        """信息日志"""
        self._write_log("INFO", message)

    def warning(self, message):
        """警告日志"""
        self._write_log("WARNING", message)

    def error(self, message):
        """错误日志"""
        self._write_log("ERROR", message)

    def debug(self, message):
        """调试日志"""
        self._write_log("DEBUG", message)

    def get_logs(self, date=None):
        """获取日志内容"""
        if date:
            log_file = self.log_dir / f"{date}.log"
        else:
            log_file = self.log_file

        if not log_file.exists():
            return []

        with open(log_file, "r", encoding="utf-8") as f:
            return f.readlines()

    def clear_old_logs(self, days=30):
        """清理旧日志"""
        from datetime import timedelta

        cutoff_date = datetime.now() - timedelta(days=days)

        for log_file in self.log_dir.glob("*.log"):
            # 从文件名提取日期
            try:
                file_date = datetime.strptime(log_file.stem, "%Y-%m-%d")
                if file_date < cutoff_date:
                    log_file.unlink()
                    print(f"删除旧日志: {log_file.name}")
            except ValueError:
                continue

# 使用示例
logger = Logger()

logger.info("应用程序启动")
logger.debug("加载配置文件")
logger.warning("磁盘空间不足")
logger.error("数据库连接失败")

# 查看日志
logs = logger.get_logs()
print("\n=== 今日日志 ===")
for log in logs:
    print(log.strip())

# 清理旧日志
logger.clear_old_logs(days=7)

实战2: 批量文件处理器

python 复制代码 
import os
import shutil
from pathlib import Path
from datetime import datetime

class BatchFileProcessor:
    def __init__(self, source_dir, target_dir):
        self.source_dir = Path(source_dir)
        self.target_dir = Path(target_dir)
        self.stats = {
            "processed": 0,
            "skipped": 0,
            "errors": 0
        }

    def process_files(self, pattern="*.*", action="copy"):
        """批量处理文件"""
        if not self.source_dir.exists():
            print(f"源目录不存在: {self.source_dir}")
            return

        # 创建目标目录
        self.target_dir.mkdir(parents=True, exist_ok=True)

        # 查找文件
        files = list(self.source_dir.glob(pattern))

        if not files:
            print("未找到匹配的文件")
            return

        print(f"找到 {len(files)} 个文件")

        for file_path in files:
            if file_path.is_file():
                try:
                    if action == "copy":
                        self._copy_file(file_path)
                    elif action == "move":
                        self._move_file(file_path)
                    elif action == "rename":
                        self._rename_file(file_path)
                    elif action == "backup":
                        self._backup_file(file_path)

                    self.stats["processed"] += 1
                except Exception as e:
                    print(f"处理失败 {file_path.name}: {e}")
                    self.stats["errors"] += 1

    def _copy_file(self, file_path):
        """复制文件"""
        target_path = self.target_dir / file_path.name
        shutil.copy2(file_path, target_path)
        print(f"复制: {file_path.name}")

    def _move_file(self, file_path):
        """移动文件"""
        target_path = self.target_dir / file_path.name
        shutil.move(str(file_path), str(target_path))
        print(f"移动: {file_path.name}")

    def _rename_file(self, file_path):
        """重命名文件（添加时间戳）"""
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        new_name = f"{file_path.stem}_{timestamp}{file_path.suffix}"
        target_path = self.target_dir / new_name
        shutil.copy2(file_path, target_path)
        print(f"重命名: {file_path.name} -> {new_name}")

    def _backup_file(self, file_path):
        """备份文件（创建备份目录）"""
        backup_dir = self.target_dir / "backups" / datetime.now().strftime("%Y-%m-%d")
        backup_dir.mkdir(parents=True, exist_ok=True)

        backup_path = backup_dir / file_path.name
        shutil.copy2(file_path, backup_path)
        print(f"备份: {file_path.name}")

    def filter_by_size(self, min_size=0, max_size=None):
        """按文件大小过滤"""
        filtered = []
        for file_path in self.source_dir.rglob("*"):
            if file_path.is_file():
                size = file_path.stat().st_size
                if size >= min_size:
                    if max_size is None or size <= max_size:
                        filtered.append(file_path)
        return filtered

    def filter_by_date(self, days_ago=7):
        """按修改日期过滤"""
        from datetime import timedelta

        cutoff_date = datetime.now() - timedelta(days=days_ago)
        filtered = []

        for file_path in self.source_dir.rglob("*"):
            if file_path.is_file():
                mtime = datetime.fromtimestamp(file_path.stat().st_mtime)
                if mtime >= cutoff_date:
                    filtered.append(file_path)

        return filtered

    def show_stats(self):
        """显示统计信息"""
        print("\n=== 处理统计 ===")
        print(f"成功处理: {self.stats['processed']}")
        print(f"跳过: {self.stats['skipped']}")
        print(f"错误: {self.stats['errors']}")

# 使用示例
processor = BatchFileProcessor("./source", "./processed")

# 复制所有 txt 文件
processor.process_files("*.txt", action="copy")

# 移动所有 jpg 文件
processor.process_files("*.jpg", action="move")

# 备份所有文件
processor.process_files("*.*", action="backup")

# 显示统计
processor.show_stats()

# 按大小过滤
large_files = processor.filter_by_size(min_size=1024*1024)  # 大于1MB
print(f"\n大文件数量: {len(large_files)}")

# 按日期过滤
recent_files = processor.filter_by_date(days_ago=7)
print(f"最近7天修改的文件: {len(recent_files)}")

实战3: 数据转换工具

python 复制代码 
import csv
import json
from pathlib import Path

class DataConverter:
    """数据格式转换工具"""

    @staticmethod
    def csv_to_json(csv_file, json_file):
        """CSV 转 JSON"""
        data = []

        with open(csv_file, "r", encoding="utf-8-sig") as f:
            reader = csv.DictReader(f)
            for row in reader:
                # 尝试转换数字类型
                converted_row = {}
                for key, value in row.items():
                    try:
                        if "." in value:
                            converted_row[key] = float(value)
                        else:
                            converted_row[key] = int(value)
                    except (ValueError, TypeError):
                        converted_row[key] = value

                data.append(converted_row)

        with open(json_file, "w", encoding="utf-8") as f:
            json.dump(data, f, ensure_ascii=False, indent=2)

        print(f"转换完成: {csv_file} -> {json_file}")
        print(f"共 {len(data)} 条记录")

    @staticmethod
    def json_to_csv(json_file, csv_file):
        """JSON 转 CSV"""
        with open(json_file, "r", encoding="utf-8") as f:
            data = json.load(f)

        if not data:
            print("JSON 文件为空")
            return

        # 获取所有字段名
        fieldnames = list(data[0].keys())

        with open(csv_file, "w", encoding="utf-8-sig", newline="") as f:
            writer = csv.DictWriter(f, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(data)

        print(f"转换完成: {json_file} -> {csv_file}")
        print(f"共 {len(data)} 条记录")

    @staticmethod
    def merge_csv_files(input_files, output_file):
        """合并多个 CSV 文件"""
        all_data = []
        fieldnames = None

        for file_path in input_files:
            with open(file_path, "r", encoding="utf-8-sig") as f:
                reader = csv.DictReader(f)

                if fieldnames is None:
                    fieldnames = reader.fieldnames

                for row in reader:
                    all_data.append(row)

        with open(output_file, "w", encoding="utf-8-sig", newline="") as f:
            writer = csv.DictWriter(f, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(all_data)

        print(f"合并完成: {len(input_files)} 个文件 -> {output_file}")
        print(f"共 {len(all_data)} 条记录")

    @staticmethod
    def split_csv(input_file, output_dir, rows_per_file=1000):
        """拆分大 CSV 文件"""
        output_path = Path(output_dir)
        output_path.mkdir(parents=True, exist_ok=True)

        with open(input_file, "r", encoding="utf-8-sig") as f:
            reader = csv.DictReader(f)
            fieldnames = reader.fieldnames

            file_count = 0
            current_rows = []

            for row in reader:
                current_rows.append(row)

                if len(current_rows) >= rows_per_file:
                    file_count += 1
                    output_file = output_path / f"part_{file_count}.csv"

                    with open(output_file, "w", encoding="utf-8-sig", newline="") as out_f:
                        writer = csv.DictWriter(out_f, fieldnames=fieldnames)
                        writer.writeheader()
                        writer.writerows(current_rows)

                    print(f"创建文件: {output_file} ({len(current_rows)} 条)")
                    current_rows = []

            # 处理剩余数据
            if current_rows:
                file_count += 1
                output_file = output_path / f"part_{file_count}.csv"

                with open(output_file, "w", encoding="utf-8-sig", newline="") as out_f:
                    writer = csv.DictWriter(out_f, fieldnames=fieldnames)
                    writer.writeheader()
                    writer.writerows(current_rows)

                print(f"创建文件: {output_file} ({len(current_rows)} 条)")

        print(f"拆分完成: 共 {file_count} 个文件")

# 使用示例
converter = DataConverter()

# CSV 转 JSON
converter.csv_to_json("students.csv", "students.json")

# JSON 转 CSV
converter.json_to_csv("students.json", "students_new.csv")

# 合并多个 CSV
csv_files = ["data1.csv", "data2.csv", "data3.csv"]
converter.merge_csv_files(csv_files, "merged.csv")

# 拆分大文件
converter.split_csv("large_file.csv", "split_output", rows_per_file=5000)

实战4: 文件搜索工具

python 复制代码 
import os
from pathlib import Path
from datetime import datetime

class FileSearcher:
    """文件搜索工具"""

    def __init__(self, search_dir="."):
        self.search_dir = Path(search_dir)
        self.results = []

    def search_by_name(self, pattern, case_sensitive=False):
        """按文件名搜索"""
        self.results = []

        if case_sensitive:
            for file_path in self.search_dir.rglob("*"):
                if file_path.is_file() and pattern in file_path.name:
                    self.results.append(file_path)
        else:
            for file_path in self.search_dir.rglob(f"*{pattern}*"):
                if file_path.is_file():
                    self.results.append(file_path)

        return self.results

    def search_by_extension(self, extensions):
        """按扩展名搜索"""
        self.results = []

        if isinstance(extensions, str):
            extensions = [extensions]

        for ext in extensions:
            if not ext.startswith("."):
                ext = f".{ext}"

            for file_path in self.search_dir.rglob(f"*{ext}"):
                if file_path.is_file():
                    self.results.append(file_path)

        return self.results

    def search_by_size(self, min_size=0, max_size=None):
        """按文件大小搜索"""
        self.results = []

        for file_path in self.search_dir.rglob("*"):
            if file_path.is_file():
                size = file_path.stat().st_size

                if size >= min_size:
                    if max_size is None or size <= max_size:
                        self.results.append(file_path)

        return self.results

    def search_by_date(self, days_ago=None, before_date=None, after_date=None):
        """按日期搜索"""
        from datetime import timedelta

        self.results = []

        for file_path in self.search_dir.rglob("*"):
            if not file_path.is_file():
                continue

            mtime = datetime.fromtimestamp(file_path.stat().st_mtime)

            if days_ago:
                cutoff = datetime.now() - timedelta(days=days_ago)
                if mtime >= cutoff:
                    self.results.append(file_path)
            elif before_date:
                if isinstance(before_date, str):
                    before_date = datetime.strptime(before_date, "%Y-%m-%d")
                if mtime < before_date:
                    self.results.append(file_path)
            elif after_date:
                if isinstance(after_date, str):
                    after_date = datetime.strptime(after_date, "%Y-%m-%d")
                if mtime > after_date:
                    self.results.append(file_path)

        return self.results

    def search_by_content(self, keyword, file_pattern="*.txt"):
        """按文件内容搜索"""
        self.results = []

        for file_path in self.search_dir.glob(file_pattern):
            if not file_path.is_file():
                continue

            try:
                with open(file_path, "r", encoding="utf-8") as f:
                    content = f.read()
                    if keyword in content:
                        self.results.append(file_path)
            except (UnicodeDecodeError, PermissionError):
                continue

        return self.results

    def show_results(self, max_results=20):
        """显示搜索结果"""
        if not self.results:
            print("未找到匹配的文件")
            return

        print(f"\n找到 {len(self.results)} 个文件:\n")
        print(f"{'文件名':<30}{'大小':<12}{'修改时间':<20}{'路径'}")
        print("-" * 100)

        for i, file_path in enumerate(self.results[:max_results]):
            stat = file_path.stat()
            size = self._format_size(stat.st_size)
            mtime = datetime.fromtimestamp(stat.st_mtime).strftime("%Y-%m-%d %H:%M")

            print(f"{file_path.name:<30}{size:<12}{mtime:<20}{file_path.parent}")

        if len(self.results) > max_results:
            print(f"\n... 还有 {len(self.results) - max_results} 个文件")

    def _format_size(self, size_bytes):
        """格式化文件大小"""
        for unit in ['B', 'KB', 'MB', 'GB']:
            if size_bytes < 1024:
                return f"{size_bytes:.1f} {unit}"
            size_bytes /= 1024
        return f"{size_bytes:.1f} TB"

    def export_results(self, output_file="search_results.txt"):
        """导出搜索结果"""
        with open(output_file, "w", encoding="utf-8") as f:
            f.write(f"搜索结果 - {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
            f.write(f"搜索目录: {self.search_dir}\n")
            f.write(f"找到文件: {len(self.results)}\n")
            f.write("=" * 80 + "\n\n")

            for file_path in self.results:
                stat = file_path.stat()
                size = self._format_size(stat.st_size)
                mtime = datetime.fromtimestamp(stat.st_mtime).strftime("%Y-%m-%d %H:%M")

                f.write(f"文件: {file_path.name}\n")
                f.write(f"路径: {file_path}\n")
                f.write(f"大小: {size}\n")
                f.write(f"修改时间: {mtime}\n")
                f.write("-" * 80 + "\n")

        print(f"结果已导出到: {output_file}")

# 使用示例
searcher = FileSearcher(".")

# 按名称搜索
print("=== 搜索 Python 文件 ===")
searcher.search_by_name(".py")
searcher.show_results()

# 按扩展名搜索
print("\n=== 搜索图片和文档 ===")
searcher.search_by_extension(["jpg", "png", "pdf", "docx"])
searcher.show_results()

# 按大小搜索
print("\n=== 搜索大文件（>10MB） ===")
searcher.search_by_size(min_size=10*1024*1024)
searcher.show_results()

# 按日期搜索
print("\n=== 搜索最近7天的文件 ===")
searcher.search_by_date(days_ago=7)
searcher.show_results()

# 按内容搜索
print("\n=== 搜索包含 'TODO' 的文件 ===")
searcher.search_by_content("TODO", "*.py")
searcher.show_results()

# 导出结果
searcher.export_results("results.txt")

常见错误与注意事项

1. 忘记关闭文件

python 复制代码 
# ❌ 危险：可能忘记关闭
f = open("test.txt", "r")
content = f.read()
# 如果中间出错，文件不会关闭

# ✅ 推荐：使用 with 语句
with open("test.txt", "r") as f:
    content = f.read()
# 自动关闭

2. 编码问题

python 复制代码 
# ❌ 可能导致中文乱码
with open("chinese.txt", "r") as f:
    content = f.read()

# ✅ 指定编码
with open("chinese.txt", "r", encoding="utf-8") as f:
    content = f.read()

3. 文件不存在

python 复制代码 
from pathlib import Path

# ❌ 可能抛出异常
# with open("not_exist.txt", "r") as f:
#     content = f.read()

# ✅ 先检查
file_path = Path("not_exist.txt")
if file_path.exists():
    content = file_path.read_text(encoding="utf-8")
else:
    print("文件不存在")

# 或使用 try-except
try:
    with open("not_exist.txt", "r", encoding="utf-8") as f:
        content = f.read()
except FileNotFoundError:
    print("文件不存在")

4. 写入时覆盖重要文件

python 复制代码 
# ❌ 危险：可能意外覆盖
with open("important.txt", "w") as f:
    f.write("new content")

# ✅ 先检查或使用追加模式
from pathlib import Path

file_path = Path("important.txt")
if file_path.exists():
    choice = input("文件已存在，是否覆盖？(y/n): ")
    if choice.lower() != "y":
        print("取消操作")
    else:
        file_path.write_text("new content", encoding="utf-8")
else:
    file_path.write_text("new content", encoding="utf-8")

5. 大文件内存溢出

python 复制代码 
# ❌ 危险：一次性加载大文件
with open("huge_file.txt", "r") as f:
    content = f.read()  # 可能占用大量内存

# ✅ 逐行读取
with open("huge_file.txt", "r") as f:
    for line in f:
        process(line)

# ✅ 分块读取
with open("huge_file.bin", "rb") as f:
    while True:
        chunk = f.read(8192)
        if not chunk:
            break
        process(chunk)

小结

操作类型 推荐模块/方法 适用场景
文本文件 open() + with 普通文本读写
二进制文件 open(mode="rb/wb") 图片、音频等
目录管理 os, shutil, pathlib 文件/目录操作
CSV 文件 csv 模块 表格数据
JSON 文件 json 模块 配置、API 数据
Excel 文件 openpyxl 电子表格
路径操作 pathlib 现代化路径处理

核心要点：

  • 始终使用 with 语句管理文件
  • 处理中文时指定 encoding="utf-8"
  • 大文件使用逐行或分块读取
  • pathlib 是现代化的路径操作方式
  • 操作前检查文件是否存在
  • 注意文件打开模式的选择
  • 合理使用异常处理

掌握文件操作是 Python 编程的重要技能！

相关推荐
龙文浩_4 小时前
AI梯度下降与PyTorch张量操作技术指南
人工智能·pytorch·python·深度学习·神经网络·机器学习·自然语言处理
呱牛do it4 小时前
企业级绩效考核系统设计与实现：基于FastAPI + Vue3的全栈解决方案
python·fastapi
7年前端辞职转AI4 小时前
Python 容器数据类型
python·编程语言
云霄IT4 小时前
安卓开发之java转dex再转smali
android·java·python
果汁华4 小时前
Typer：基于类型提示的现代Python CLI框架
开发语言·网络·python
Claw开发者4 小时前
第1课：用20行Python造出你的第一个AI Agent
python
7年前端辞职转AI4 小时前
Python 流程控制语句
python·编程语言
7年前端辞职转AI4 小时前
Python 运算符
python·编程语言
zhangzeyuaaa4 小时前
Python 异常机制深度剖析
开发语言·python
热门推荐
012026年4月技术前沿：AI大模型爆发、智能体革命与量子安全新纪元02GitHub 镜像站点03一周AI热点速览（2026.03.31-04.06）：GPT-6曝光、谷歌开源Gemma 4、资本狂飙与模型军备竞赛04基于 Docker 部署 Hermes Agent 并接入飞书机器人的完整指南05GPT-6核心能力解析及与现有主流大模型对比06免费！不限量！用opencode接入英伟达（NVIDIA）大模型，轻松打造你的 AI 编程助手07零成本！Ollama本地部署国产大模型全指南（支持Kimi-K2.5/GLM-5/Qwen，新手秒上手）08从限购到畅通：GLM-5.1 Coding Plan接入攻略09CodeBuddy与WorkBuddy深度对比：腾讯两款AI工具差异及实操指南10LLM Wiki：让大模型替你打理知识库的完整指南