JSONDecodeError: Extra data: line 4 column 2 (char 545) json逐条存入后，读取报错解决办法

json 逐条存入总是报错,遇到不少坑，下面是自己测试可以使用的代码

使用缩进（indent=2）便于查看，读取方法：

import json
import os 

from random import sample
# import time
def save_load_json(save_dir,filename='data.json',save_data=None):
    '''
    save_dir:存时表示文件夹 
    filename:存入文件夹名 
    savedata:save_data is not None
    loaddata:if save_data == None
    读取文件时：传入目标文件地址
    '''

    if save_data!=None:
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)          
        with open(os.path.join(save_dir,filename),'a',encoding='utf-8') as f:
                json_str = json.dumps(save_data,ensure_ascii=False,indent=2)
                # json.dump(save_data,f,ensure_ascii=False,indent=2)
                f.write(json_str)
                f.write(',\n')
                print('already saved in {}'.format(os.path.join(save_dir,filename)))
        f.close()
        return None
    else:
        with open('{}'.format(save_dir),'r') as f:
            data = json.load(f)
            print('already load {}'.format(save_dir))
        f.close()
        return data

但是读取会报错，如下：

---------------------------------------------------------------------------
JSONDecodeError                           Traceback (most recent call last)
Cell In[3], line 1
----> 1 data = save_load_json('/exp1_ins0_4shot.json',"",None)

Cell In[2], line 27, in save_load_json(save_dir, filename, save_data)
     25 else:
     26     with open('{}'.format(save_dir),'r') as f:
---> 27         data = json.load(f)
     28         print('already load {}'.format(save_dir))
     29     f.close()

File /usr/lib/python3.9/json/__init__.py:293, in load(fp, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
    274 def load(fp, *, cls=None, object_hook=None, parse_float=None,
    275         parse_int=None, parse_constant=None, object_pairs_hook=None, **kw):
    276     """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing
    277     a JSON document) to a Python object.
    278 
   (...)
    291     kwarg; otherwise ``JSONDecoder`` is used.
    292     """
--> 293     return loads(fp.read(),
    294         cls=cls, object_hook=object_hook,
    295         parse_float=parse_float, parse_int=parse_int,
    296         parse_constant=parse_constant, object_pairs_hook=object_pairs_hook, **kw)

File /usr/lib/python3.9/json/__init__.py:346, in loads(s, cls, object_hook, parse_float, parse_int, parse_constant, object_pairs_hook, **kw)
    341     s = s.decode(detect_encoding(s), 'surrogatepass')
    343 if (cls is None and object_hook is None and
    344         parse_int is None and parse_float is None and
    345         parse_constant is None and object_pairs_hook is None and not kw):
--> 346     return _default_decoder.decode(s)
    347 if cls is None:
    348     cls = JSONDecoder

File /usr/lib/python3.9/json/decoder.py:340, in JSONDecoder.decode(self, s, _w)
    338 end = _w(s, end).end()
    339 if end != len(s):
--> 340     raise JSONDecodeError("Extra data", s, end)
    341 return obj

JSONDecodeError: Extra data: line 4 column 2 (char 545)

遇到这种情况 找了很多解决方案,比如逐条读出,key双引号都没有解决问题。

后来观察比赛数据的json格式，发现只要在文件两头加上’['']‘，

用大括号把逐条存入数据括起来就解决问题了。

最后一行逗号要删除。

改前

 

改后

注意逐条存入在两条数据间需要写入 ‘,\n’

正确的格式如下：

还有个方法就是别用indent，然后逐条读取 方法如下：（测试过了 可以使用）

import json
import os 

from random import sample
# import time
def save_load_json(save_dir,filename='data.json',save_data=None):
    '''
    save_dir:存时表示文件夹 
    filename:存入文件夹名 
    savedata:save_data is not None
    loaddata:if save_data == None
    读取文件时：传入目标文件地址
    '''

    if save_data!=None:
        if not os.path.exists(save_dir):
            os.makedirs(save_dir)          
        with open(os.path.join(save_dir,filename),'a',encoding='utf-8') as f:
                json_str = json.dumps(save_data,ensure_ascii=False)
                # json.dump(save_data,f,ensure_ascii=False)
                f.write(json_str)
                f.write('\n')
                print('already saved in {}'.format(os.path.join(save_dir,filename)))
        f.close()
        return None
    else:
        data = []
        with open(data_dir, encoding='utf-8') as f:
            while True:
                line = f.readline()
                if not line: # 到 EOF，返回空字符串，则终止循环
                    break
                js = json.loads(line)
                data.append(js)
        f.close()
        return data

数据格式：

头部这样

尾部是没有逗号的

但是最近又爆了个读取bug 有些莫名其妙，改天写