文件操作与数据序列化

# 读取
with open("example.txt", "r", encoding="utf-8") as f:
    content = f.read()          # 读取全部内容

with open("example.txt", "r", encoding="utf-8") as f:
    lines = f.readlines()       # 读取所有行（含换行符）
    first_line = f.readline()    # 读取一行

# 逐行迭代（推荐，最内存友好）
with open("example.txt", "r", encoding="utf-8") as f:
    for line in f:
        print(line.rstrip())     # rstrip() 去除换行符

# 写入
with open("output.txt", "w", encoding="utf-8") as f:
    f.write("Hello, Python!\n")   # 写入字符串
    f.writelines(["line1\n", "line2\n"])  # 写入多行

# 追加
with open("log.txt", "a", encoding="utf-8") as f:
    f.write("New log entry\n")

# 读取二进制
with open("image.png", "rb") as f:
    data = f.read()

# 写入二进制
with open("copy.png", "wb") as f:
    f.write(data)

# 明确指定编码，避免平台差异
with open("file.txt", "r", encoding="utf-8") as f:
    content = f.read()

# 处理编码错误
with open("file.txt", "r", encoding="utf-8", errors="replace") as f:
    content = f.read()

# 常见 errors 参数
# "replace"：用 ? 替换无法解码的字符
# "ignore"：忽略无法解码的字符
# "surrogateescape"：保留原始字节（用于调试）

from pathlib import Path

# 路径对象
p = Path("src/main.py")

# 基本属性
print(p.name)        # main.py          文件名
print(p.stem)        # main             不含扩展名
print(p.suffix)      # .py              扩展名
print(p.parent)      # src              父目录
print(p.parts)       # ('src', 'main.py') 路径各部分

# 判断
print(p.exists())    # True
print(p.is_file())   # True
print(p.is_dir())    # False

# 路径拼接
reports = Path("data") / "reports" / "2026"
reports.mkdir(parents=True, exist_ok=True)  # 创建目录（递归）

from pathlib import Path

src = Path("src")

# 遍历所有 .py 文件（递归）
for py_file in src.rglob("*.py"):
    print(py_file)

# 遍历顶级文件（不递归）
for item in src.iterdir():
    print(item.name)

# .glob vs .rglob
src.glob("*.py")     # 仅当前目录
src.rglob("*.py")    # 递归所有子目录

from pathlib import Path

p = Path("example.txt")

# 创建 / 删除
p.touch()                    # 创建空文件
p.unlink()                   # 删除文件（不存在会报错）
p.unlink(missing_ok=True)    # 删除（不存在不报错，Python 3.8+）

# 复制（需要 shutil）
import shutil
shutil.copy("src.txt", "dst.txt")

# 重命名 / 移动
p.rename("renamed.txt")
shutil.move("old_path", "new_path")

import json

# Python 对象 → JSON 字符串
data = {"name": "Alice", "age": 25, "scores": [98, 87, 95]}

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

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

# JSON 字符串 → Python 对象
parsed = json.loads(json_str)

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

import json
from datetime import datetime

class DatetimeEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, datetime):
            return {"__datetime__": obj.isoformat()}
        return super().default(obj)

def datetime_decoder(dct):
    """配合 DatetimeEncoder 的解码器"""
    if "__datetime__" in dct:
        return datetime.fromisoformat(dct["__datetime__"])
    return dct

data = {"event": "会议", "time": datetime(2026, 4, 10, 9, 0)}

json_str = json.dumps(data, cls=DatetimeEncoder)
print(json_str)
# {"event": "会议", "time": {"__datetime__": "2026-04-10T09:00:00"}}

# 解码时使用 object_hook
loaded = json.loads(json_str, object_hook=datetime_decoder)
print(loaded["time"])  # 2026-04-09 09:00:00（恢复为 datetime 对象）

import csv

# 写入 CSV
with open("users.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.writer(f)
    writer.writerow(["姓名", "年龄", "城市"])    # 表头
    writer.writerows([                        # 批量写入
        ["Alice", 25, "北京"],
        ["Bob", 30, "上海"],
    ])

# 使用字典写入（更清晰）
with open("users.csv", "w", newline="", encoding="utf-8") as f:
    writer = csv.DictWriter(f, fieldnames=["姓名", "年龄", "城市"])
    writer.writeheader()
    writer.writerows([
        {"姓名": "Alice", "年龄": 25, "城市": "北京"},
        {"姓名": "Bob", "年龄": 30, "城市": "上海"},
    ])

# 读取 CSV
with open("users.csv", "r", encoding="utf-8") as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row)
    # {'姓名': 'Alice', '年龄': '25', '城市': '北京'}

import yaml

config = {
    "database": {
        "host": "localhost",
        "port": 5432,
        "users": ["Alice", "Bob"]
    },
    "debug": True
}

# 写入 YAML
with open("config.yaml", "w", encoding="utf-8") as f:
    yaml.dump(config, f, allow_unicode=True, default_flow_style=False)

# 读取 YAML
with open("config.yaml", "r", encoding="utf-8") as f:
    loaded = yaml.safe_load(f)

print(loaded["database"]["host"])  # localhost

import pickle

data = {"name": "Alice", "skills": ["Python", "Go"]}

# 序列化到文件
with open("data.pkl", "wb") as f:
    pickle.dump(data, f)

# 反序列化
with open("data.pkl", "rb") as f:
    loaded = pickle.load(f)

# 序列化为字节
bytes_data = pickle.dumps(data)
restored = pickle.loads(bytes_data)