# 文本文件
with open('data.txt', 'r', encoding='utf-8') as f:
    content = f.read()      # 读取全部内容
    # lines = f.readlines()  # 读取所有行
    # for line in f:         # 逐行读取（推荐）
    #     print(line.strip())

# 写入
with open('output.txt', 'w', encoding='utf-8') as f:
    f.write("Hello\n")
    f.writelines(["Line 1\n", "Line 2\n"])

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

# 大文件逐行处理
def process_large_file(filename):
    with open(filename, 'r') as f:
        for line in f:
            yield line.strip()

import csv

# 读取 CSV
with open('data.csv', 'r') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row['name'], row['age'])

# 写入 CSV
data = [
    {'name': 'Alice', 'age': 30, 'city': 'NYC'},
    {'name': 'Bob', 'age': 25, 'city': 'LA'},
]
with open('output.csv', 'w', newline='') as f:
    writer = csv.DictWriter(f, fieldnames=['name', 'age', 'city'])
    writer.writeheader()
    writer.writerows(data)

import json

# 序列化
data = {'name': 'Alice', 'age': 30, 'scores': [95, 87, 92]}
json_str = json.dumps(data, indent=2, ensure_ascii=False)
print(json_str)

# 反序列化
parsed = json.loads(json_str)
print(parsed['name'])

# 文件操作
with open('data.json', 'w') as f:
    json.dump(data, f, indent=2)

with open('data.json', 'r') as f:
    loaded = json.load(f)

# 自定义序列化
class User:
    def __init__(self, name, age):
        self.name = name
        self.age = age

def user_to_dict(user):
    return {'name': user.name, 'age': user.age}

user = User("Alice", 30)
print(json.dumps(user, default=user_to_dict))

import csv
from collections import defaultdict

def clean_csv(input_file, output_file):
    """清洗 CSV 数据：去除空行、标准化字段"""
    stats = defaultdict(int)
    
    with open(input_file, 'r') as fin, open(output_file, 'w', newline='') as fout:
        reader = csv.DictReader(fin)
        writer = csv.DictWriter(fout, fieldnames=reader.fieldnames)
        writer.writeheader()
        
        for row in reader:
            # 跳过空行
            if not any(row.values()):
                stats['empty'] += 1
                continue
            
            # 标准化字段
            cleaned = {}
            for key, value in row.items():
                cleaned[key] = value.strip() if value else ''
            
            writer.writerow(cleaned)
            stats['processed'] += 1
    
    print(f"Stats: {dict(stats)}")