第二十章：序列化与数据格式

完成本章学习后，你将能够：

掌握JSON数据的解析和生成
使用YAML配置文件
使用pickle进行对象序列化
处理CSV和XML数据
选择合适的序列化格式

import json
 
# Python对象转JSON字符串
data = {
    "name": "Alice",
    "age": 25,
    "is_student": False,
    "courses": ["Math", "Physics"],
    "address": {"city": "Beijing", "zip": "100000"}
}
 
json_str = json.dumps(data)
print(json_str)
# {"name": "Alice", "age": 25, "is_student": false, "courses": ["Math", "Physics"]...}
 
# 格式化输出
print(json.dumps(data, indent=2, ensure_ascii=False))

import json
 
# 写入JSON文件
data = {"users": [{"name": "Alice", "age": 25}, {"name": "Bob", "age": 30}]}
 
with open('data.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, indent=2, ensure_ascii=False)
 
# 读取JSON文件
with open('data.json', 'r', encoding='utf-8') as f:
    loaded_data = json.load(f)
 
print(loaded_data['users'][0]['name'])  # Alice

import json
from datetime import datetime
 
class DateTimeEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, datetime):
            return obj.isoformat()
        return super().default(obj)
 
data = {"name": "Event", "time": datetime.now()}
json_str = json.dumps(data, cls=DateTimeEncoder)
print(json_str)

# 需要安装: pip install PyYAML
import yaml
 
# 读取YAML
data = '''
name: Alice
age: 25
address:
  city: Beijing
  street: Main Road
skills:
  - Python
  - JavaScript
'''
 
parsed = yaml.safe_load(data)
print(parsed['name'])  # Alice
print(parsed['skills'])  # ['Python', 'JavaScript']
 
# 写入YAML
config = {
    'database': {
        'host': 'localhost',
        'port': 3306,
        'name': 'myapp'
    },
    'debug': True
}
 
with open('config.yaml', 'w') as f:
    yaml.dump(config, f, default_flow_style=False)

import pickle
 
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age
 
    def __repr__(self):
        return f"Person({self.name!r}, {self.age})"
 
# 序列化
person = Person("Alice", 25)
with open('person.pkl', 'wb') as f:
    pickle.dump(person, f)
 
# 反序列化
with open('person.pkl', 'rb') as f:
    loaded_person = pickle.load(f)
 
print(loaded_person)  # Person('Alice', 25)

import csv
 
# 写入CSV
with open('data.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerow(['Name', 'Age', 'City'])
    writer.writerow(['Alice', '25', 'Beijing'])
    writer.writerow(['Bob', '30', 'Shanghai'])
 
# 读取CSV
with open('data.csv', 'r', encoding='utf-8') as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)
 
# 字典方式处理
with open('data.csv', 'r', encoding='utf-8') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(f"{row['Name']} is {row['Age']} years old")

import xml.etree.ElementTree as ET
 
# 解析XML
xml_data = '''
<root>
    <user id="1">
        <name>Alice</name>
        <age>25</age>
    </user>
    <user id="2">
        <name>Bob</name>
        <age>30</age>
    </user>
</root>
'''
 
root = ET.fromstring(xml_data)
 
# 遍历
for user in root.findall('user'):
    user_id = user.get('id')
    name = user.find('name').text
    age = user.find('age').text
    print(f"User {user_id}: {name}, {age}")
 
# 创建XML
new_user = ET.Element('user', {'id': '3'})
ET.SubElement(new_user, 'name').text = 'Charlie'
ET.SubElement(new_user, 'age').text = '35'
root.append(new_user)
 
# 保存
ET.ElementTree(root).write('output.xml', encoding='utf-8')

格式	可读性	跨语言	支持类型	适用场景
——	——–	——–	———-	———-
JSON	好	是	基础类型	数据交换、配置
YAML	很好	是	基础类型	配置文件
Pickle	否	否	Python任意	临时存储、缓存
CSV	好	是	表格数据	数据表格
XML	好	是	层次数据	复杂配置、文档