从基础到进阶详解Python处理JSON数据的最佳实践指南

import json
 
# 字典转JSON字符串
data = {"name": "Alice", "age": 30, "hobbies": ["coding", "hiking"]}
json_str = json.dumps(data, indent=2, ensure_ascii=False)
print(json_str)
# 输出：
# {
#   "name": "Alice",
#   "age": 30,
#   "hobbies": ["coding", "hiking"]
# }
 
# JSON字符串转字典
parsed_data = json.loads(json_str)
print(parsed_data["hobbies"][0])  # 输出: coding

# 写入JSON文件
with open("config.json", "w", encoding="utf-8") as f:
    json.dump(data, f, indent=4, sort_keys=True)
 
# 读取JSON文件
with open("config.json", "r", encoding="utf-8") as f:
    loaded_data = json.load(f)

from datetime import datetime
 
# 序列化：datetime → ISO格式字符串
def datetime_serializer(obj):
    if isinstance(obj, datetime):
        return obj.isoformat()
    raise TypeError(f"Type {type(obj)} not serializable")
 
event_data = {
    "title": "Tech Conference",
    "start_time": datetime(2025, 10, 15, 9, 30)
}
json_str = json.dumps(event_data, default=datetime_serializer)
print(json_str)
# 输出: {"title": "Tech Conference", "start_time": "2025-10-15T09:30:00"}
 
# 反序列化：字符串 → datetime对象
def datetime_deserializer(dct):
    for k, v in dct.items():
        if k.endswith("_time"):  # 约定时间字段后缀
            try:
                dct[k] = datetime.fromisoformat(v)
            except ValueError:
                pass
    return dct
 
parsed_data = json.loads(json_str, object_hook=datetime_deserializer)
print(parsed_data["start_time"].year)  # 输出: 2025

class User:
    def __init__(self, name, email, join_date):
        self.name = name
        self.email = email
        self.join_date = join_date
        self.__password = "secret"  # 敏感字段不应序列化
 
    def to_dict(self):
        return {
            "name": self.name,
            "email": self.email,
            "join_date": self.join_date.isoformat()
        }
 
# 方法1：通过to_dict()手动转换
user = User("Bob", "bob@example.com", datetime.now())
json_str = json.dumps(user.to_dict())
 
# 方法2：继承JSONEncoder（推荐）
class UserEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, User):
            return obj.to_dict()
        return super().default(obj)
 
json_str = json.dumps(user, cls=UserEncoder)

import ijson
 
def process_large_log(file_path):
    total_errors = 0
    with open(file_path, "rb") as f:
        # 假设文件结构为数组：[{"level": "ERROR", ...}, {...}]
        for event in ijson.items(f, "item"):
            if event.get("level") == "ERROR":
                total_errors += 1
                if total_errors % 1000 == 0:
                    print(f"Processed {total_errors} errors...")
    return total_errors
 
error_count = process_large_log("server_logs.json")
print(f"Total errors: {error_count}")

import ujson  # 或 orjson
 
data = [{"id": i, "value": f"item-{i}"} for i in range(100000)]
 
# 标准库性能
%timeit json.dumps(data)  # 10 loops, best of 3: 123 ms per loop
 
# ujson性能
%timeit ujson.dumps(data)  # 100 loops, best of 3: 24.5 ms per loop

import json
from json.decoder import JSONDecodeError
 
def safe_parse_json(json_str):
    try:
        return json.loads(json_str)
    except JSONDecodeError as e:
        print(f"Invalid JSON: {e.msg} at line {e.lineno}, column {e.colno}")
        return None
    except UnicodeDecodeError:
        print("Encoding error: Ensure input is UTF-8")
        return None
 
# 测试用例
invalid_json = '{"name": "Alice", "age": 30,'  # 缺少闭合括号
data = safe_parse_json(invalid_json)
assert data is None

# 危险示例（绝对禁止）
evil_json = '{"name": "Alice", "age": "__import__("os").system("rm -rf /")"}'
# eval(evil_json)  # 这将执行系统命令！
 
# 安全方案
safe_data = json.loads(evil_json)  # 仅解析，不执行
print(safe_data["age"])  # 输出字符串，不会执行命令

import requests
import json
from datetime import datetime
 
# 1. 构造请求体（序列化）
new_user = {
    "name": "Charlie",
    "email": "charlie@example.com",
    "registered_at": datetime.now().isoformat()
}
headers = {"Content-Type": "application/json"}
 
# 2. 发送POST请求
response = requests.post(
    "https://api.example.com/users",
    data=json.dumps(new_user),
    headers=headers
)
 
# 3. 处理响应（反序列化）
if response.status_code == 201:
    try:
        created_user = response.json()  # 等价于 json.loads(response.text)
        print(f"Created user ID: {created_user['id']}")
    except json.JSONDecodeError:
        print("Invalid JSON response")
else:
    print(f"Error: {response.status_code} - {response.text}")

import math
 
def safe_float_serializer(obj):
    if isinstance(obj, float):
        if math.isnan(obj) or math.isinf(obj):
            return None  # 或替换为字符串如 "NaN"
    return obj
 
data = {"value": float("nan"), "ratio": 1.79e308}
json_str = json.dumps(data, default=safe_float_serializer)
print(json_str)  # 输出: {"value": null, "ratio": 1.79e+308}

import decimal
 
data = {"account_id": 12345678901234567890, "balance": decimal.Decimal("1000.50")}
 
# 方法1：转换为字符串（推荐用于ID）
class PrecisionEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, (int, decimal.Decimal)):
            return str(obj)
        return super().default(obj)
 
print(json.dumps(data, cls=PrecisionEncoder))
# 输出: {"account_id": "12345678901234567890", "balance": "1000.50"}

from jsonschema import validate
 
schema = {"type": "object", "properties": {"name": {"type": "string"}}}
validate(instance={"name": "Alice"}, schema=schema)  # 通过验证

# 使用jq处理JSON文件
cat data.json | jq '.users[] | select(.age > 30)'