JSON Formatter Python — json.dumps() 指南

import json

user = {
    "id": "usr_9f3a2b",
    "name": "李明",
    "roles": ["admin", "editor"],
    "prefs": {"theme": "dark", "lang": "zh"}
}

print(json.dumps(user, indent=4, ensure_ascii=False))
# 输出：
# {
#     "id": "usr_9f3a2b",
#     "name": "李明",
#     "roles": [
#         "admin",
#         "editor"
#     ],
#     "prefs": {
#         "theme": "dark",
#         "lang": "zh"
#     }
# }

import json

api_response = {
    "timestamp": "2024-05-01T10:30:00Z",
    "status": "success",
    "data": {
        "user_id": "usr_9f3a2b",
        "display_name": "王芳",
        "city": "上海",
        "score": 4892.5,
        "tags": ["python", "backend", "api"]
    }
}

print(json.dumps(api_response, indent=4, sort_keys=True, ensure_ascii=False))
# 输出（键已排序，汉字保留原样）：
# {
#     "data": {
#         "city": "上海",
#         "display_name": "王芳",
#         "score": 4892.5,
#         "tags": ["api", "backend", "python"],
#         "user_id": "usr_9f3a2b"
#     },
#     "status": "success",
#     "timestamp": "2024-05-01T10:30:00Z"
# }

import json

payload = {
    "endpoint": "/api/v2/events",
    "filters": {"status": "active", "limit": 100},
    "sort": "desc"
}

# 默认 — 分隔符后有空格（可读）
default_out = json.dumps(payload)
# {"endpoint": "/api/v2/events", "filters": {"status": "active", "limit": 100}, "sort": "desc"}
# len = 88

# 紧凑 — 完全无空格
compact_out = json.dumps(payload, separators=(',', ':'))
# {"endpoint":"/api/v2/events","filters":{"status":"active","limit":100},"sort":"desc"}
# len = 80  (节省 9%；对更大、嵌套更深的 payload 效果更明显)

# 紧凑 + 排序键，用于可复现的缓存键或内容哈希
canonical = json.dumps(payload, separators=(',', ':'), sort_keys=True)
print(canonical)
# {"endpoint":"/api/v2/events","filters":{"limit":100,"status":"active"},"sort":"desc"}

import json
from datetime import datetime, timezone
import uuid

order = {
    "order_id": uuid.uuid4(),            # ❌ TypeError: UUID is not JSON serializable
    "placed_at": datetime.now(timezone.utc),  # ❌ TypeError: datetime is not JSON serializable
    "total_usd": 142.50,
    "items": ["pro-subscription", "addon-storage"]
}

json.dumps(order)  # 抛出 TypeError

import json
from datetime import datetime, timezone, date
import uuid
from decimal import Decimal

def json_default(obj):
    if isinstance(obj, (datetime, date)):
        return obj.isoformat()
    if isinstance(obj, uuid.UUID):
        return str(obj)
    if isinstance(obj, Decimal):
        return float(obj)
    raise TypeError(f"Type {type(obj).__name__!r} is not JSON serializable")

order = {
    "order_id": uuid.uuid4(),
    "placed_at": datetime(2024, 5, 1, 10, 30, 0, tzinfo=timezone.utc),
    "total_usd": Decimal("142.50"),
    "items": ["pro-subscription", "addon-storage"]
}

print(json.dumps(order, indent=4, default=json_default))
# {
#     "order_id": "a3f1c2d4-e5b6-7890-abcd-ef1234567890",
#     "placed_at": "2024-05-01T10:30:00+00:00",
#     "total_usd": 142.5,
#     "items": ["pro-subscription", "addon-storage"]
# }

import json
from datetime import datetime, timezone
import uuid
from decimal import Decimal

class AppEncoder(json.JSONEncoder):
    def default(self, obj):
        if isinstance(obj, datetime):
            return obj.isoformat()
        if isinstance(obj, uuid.UUID):
            return str(obj)
        if isinstance(obj, Decimal):
            return float(obj)
        return super().default(obj)  # 对未知类型抛出 TypeError

order = {
    "order_id": uuid.uuid4(),
    "placed_at": datetime(2024, 5, 1, 10, 30, 0, tzinfo=timezone.utc),
    "total_usd": Decimal("142.50"),
}

# 通过 cls= 传入编码器类
print(json.dumps(order, indent=4, cls=AppEncoder))
# 与 default= 方式的输出完全相同

import json
from datetime import datetime
from dataclasses import dataclass

@dataclass
class Event:
    name: str
    occurred_at: datetime
    user_id: str

def encode_event(obj):
    if isinstance(obj, Event):
        return {
            "__type__": "Event",
            "name": obj.name,
            "occurred_at": obj.occurred_at.isoformat(),
            "user_id": obj.user_id,
        }
    raise TypeError(f"Cannot serialize {type(obj)}")

def decode_event(d):
    if d.get("__type__") == "Event":
        return Event(
            name=d["name"],
            occurred_at=datetime.fromisoformat(d["occurred_at"]),
            user_id=d["user_id"],
        )
    return d

# 编码
event = Event("login", datetime(2024, 5, 1, 10, 30), "usr_9f3a2b")
json_str = json.dumps(event, default=encode_event, indent=4)

# 解码回 Event 实例
restored = json.loads(json_str, object_hook=decode_event)
print(type(restored))           # <class 'Event'>
print(restored.occurred_at)     # 2024-05-01 10:30:00

import json, pprint

raw = '{"sensor_id":"s-441","readings":[23.1,23.4,22.9],"unit":"celsius","active":true}'
data = json.loads(raw)

# pprint — 有效的 Python repr，而非有效的 JSON
pprint.pprint(data, sort_dicts=False)
# {'sensor_id': 's-441',
#  'readings': [23.1, 23.4, 22.9],
#  'unit': 'celsius',
#  'active': True}        ← Python True，而非 JSON true

# json.dumps — 有效的 JSON
print(json.dumps(data, indent=4))
# {
#     "sensor_id": "s-441",
#     "readings": [23.1, 23.4, 22.9],
#     "unit": "celsius",
#     "active": true      ← 有效的 JSON
# }

import json

try:
    with open("config.json", "r", encoding="utf-8") as f:
        data = json.load(f)

    # 格式化输出到控制台
    print(json.dumps(data, indent=4, ensure_ascii=False))

    # 或将格式化版本写回磁盘
    with open("config.pretty.json", "w", encoding="utf-8") as f:
        json.dump(data, f, indent=4, ensure_ascii=False)

except json.JSONDecodeError as e:
    print(f"无效 JSON: {e}")
except FileNotFoundError:
    print(f"文件未找到: config.json")

import json, requests
from requests.exceptions import HTTPError, ConnectionError, Timeout

def pretty_print_api(url: str) -> None:
    try:
        resp = requests.get(url, timeout=10)
        resp.raise_for_status()
        print(json.dumps(resp.json(), indent=4, ensure_ascii=False))
    except HTTPError as e:
        print(f"HTTP {e.response.status_code}: {e}")
    except (ConnectionError, Timeout) as e:
        print(f"网络错误: {e}")
    except json.JSONDecodeError:
        print(f"响应体不是 JSON:\n{resp.text[:500]}")

pretty_print_api("https://api.github.com/repos/python/cpython")

# 格式化本地文件
python -m json.tool config.json

# 通过格式化器管道传输 API 响应
curl -s https://api.github.com/users/gvanrossum | python -m json.tool

# 从标准输入格式化
echo '{"service":"api-gateway","version":"2.1.0","healthy":true}' | python -m json.tool

# 按字母顺序排序键
python -m json.tool --sort-keys data.json

# 自定义缩进（Python 3.9+）
python -m json.tool --indent 2 data.json

pip install orjson

import orjson
from datetime import datetime, timezone
import uuid

event = {
    "event_id": uuid.uuid4(),                  # 无需 str() — orjson 处理 UUID
    "timestamp": datetime.now(timezone.utc),   # 无需 isoformat()
    "service": "auth-service",
    "level": "INFO",
    "payload": {
        "user_id": "usr_9f3a2b",
        "action": "login",
        "ip": "192.168.1.42",
        "latency_ms": 34
    }
}

# orjson.dumps 返回 bytes；.decode() 转换为 str
print(orjson.dumps(event, option=orjson.OPT_INDENT_2).decode())
# {
#   "event_id": "a3f1c2d4-e5b6-7890-abcd-ef1234567890",
#   "timestamp": "2024-05-01T10:30:00+00:00",
#   "service": "auth-service",
#   ...
# }

pip install rich

from rich import print_json
import json

# print_json() 接受 JSON 字符串
raw = '{"event":"login","user_id":"usr_9f3a2b","timestamp":"2024-05-01T10:30:00Z","success":true,"meta":{"ip":"192.168.1.42","attempts":1}}'
print_json(raw)

# 要格式化 Python dict，先转换为字符串
data = {
    "status": "success",
    "count": 42,
    "tags": ["python", "api", "backend"]
}
print_json(json.dumps(data))

pip install simplejson

import simplejson as json  # 与标准库 API 完全相同
from decimal import Decimal

order = {
    "item": "API subscription",
    "price": Decimal("49.99"),   # stdlib json 在此处会抛出 TypeError
    "quantity": 3,
}

# simplejson 原生序列化 Decimal — 无需 default=
print(json.dumps(order, indent=4, use_decimal=True))
# {
#     "item": "API subscription",
#     "price": 49.99,
#     "quantity": 3
# }

pip install ijson

import ijson
from decimal import Decimal

# events.json 结构: {"events": [...数百万个对象...]}
total_revenue = Decimal("0")
login_count = 0

with open("events.json", "rb") as f:   # ijson 需要二进制模式
    for event in ijson.items(f, "events.item"):
        if event.get("type") == "purchase":
            total_revenue += Decimal(str(event["amount_usd"]))
        elif event.get("type") == "login":
            login_count += 1

print(f"Revenue: ${total_revenue:.2f}  |  Logins: {login_count}")
# 处理 2 GB 文件，峰值内存约 30 MB

import json
from pathlib import Path

# 写入 NDJSON — 每个事件一行
events = [
    {"ts": "2024-05-01T10:00:00Z", "user": "usr_9f3a2b", "action": "login"},
    {"ts": "2024-05-01T10:01:03Z", "user": "usr_9f3a2b", "action": "purchase", "sku": "pro-plan"},
    {"ts": "2024-05-01T10:15:42Z", "user": "usr_4ab1d9", "action": "login"},
]

with open("events.ndjson", "w", encoding="utf-8") as f:
    for event in events:
        f.write(json.dumps(event, ensure_ascii=False) + "\n")

# 读取 NDJSON — 无论文件多大，内存恒定
purchase_count = 0
with open("events.ndjson", "r", encoding="utf-8") as f:
    for line in f:
        line = line.strip()
        if not line:           # 跳过空行
            continue
        event = json.loads(line)
        if event.get("action") == "purchase":
            purchase_count += 1
            print(f"{event['ts']} — {event['user']} bought {event['sku']}")