Python解析不规则JSON数据的实战技巧

{
  'name': 'Alice',
  'age': 30,
  'tags': ['a', 'b',],
}

import ast

dirty_str = "{'name': 'Alice', 'age': 30, 'tags': ['a', 'b',]}"
try:
    data = ast.literal_eval(dirty_str)
    print(data)  # {'name': 'Alice', 'age': 30, 'tags': ['a', 'b']}
except (ValueError, SyntaxError) as e:
    print("无法解析为 Python 字面量")

{
  // 用户信息
  name: "Bob",
  age: 25,
  hobbies: [
    "coding",
    "gaming",  // 末尾逗号
  ],
}

pip install json5

import json5

with open('config.js', 'r', encoding='utf-8') as f:
    data = json5.load(f)  # 或 json5.loads(string)

print(data['name'])  # Bob

{
  "log": "User {"id": 123, "action": "login"} performed"
}

import json
import re

def extract_and_parse_nested_json(text):
    # 匹配最外层的 {...}，但需确保是完整 JSON 对象
    pattern = r'{(?:[^{}]|(?R))*}'  # 递归正则（Python 不支持 (?R)，改用循环）
    
    # 更稳健的做法：逐字符扫描括号匹配
    def find_outer_braces(s):
        stack = 0
        start = -1
        for i, c in enumerate(s):
            if c == '{':
                if stack == 0:
                    start = i
                stack += 1
            elif c == '}':
                stack -= 1
                if stack == 0 and start != -1:
                    return s[start:i+1]
        return None

    nested = find_outer_braces(text)
    if nested:
        try:
            return json.loads(nested)
        except json.JSONDecodeError:
            return None
    return None

log_str = 'User {"id": 123, "action": "login"} performed'
inner = extract_and_parse_nested_json(log_str)
print(inner)  # {'id': 123, 'action': 'login'}

import json5
import re

log_line = 'ERROR: Failed to parse {data: [1,2,,3]}'

# 提取花括号包围的内容
match = re.search(r'{.*}', log_line)
if match:
    candidate = match.group()
    try:
        data = json5.loads(candidate)
        print("Parsed:", data)
    except Exception as e:
        print("Still invalid:", e)