Pythonh中用json.load() json.loads()加载json数据的方法

最近在python里面用json读取json文件，可是老是不成功，特此记录一下。

预备知识：

def load(fp, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, kw): """Deserialize ``fp`` (a ``.read()``-supporting file-like object containing a JSON document) to a Python object.""" def loads(s, encoding=None, cls=None, object_hook=None, parse_float=None, parse_int=None, parse_constant=None, object_pairs_hook=None, kw): """Deserialize ``s`` (a ``str`` instance containing a JSON document) to a Python object.""" 

with open("文件名") as f: print(type(f)) # 
   
     也就是文本IO类型 
    result=json.load(f) with open("文件名") as f: line=f.readline(): print(type(line)) # 
    result=json.loads(line)

使用方法

从以上可以看出json.load()是用来读取文件的，即，将文件打开然后就可以直接读取。示例如下：

with open("文件名") as f: result=json.load(f)

json.loads()是用来读取字符串的，即，可以把文件打开，用readline()读取一行，然后json.loads()一行。示例如下：

#json文件为： { 
  "outputs": ["pool1/7x7/ets", "pool1/7x7/rf", "pool1/10x10/ets", "pool1/10x10/rf", "pool1/13x13/ets", "pool1/13x13/rf"]}

读取代码如下：

with open("文件名") as f: line=f.readline(): result=json.loads(line)

当json文件如下时，读取内容是错误的：

{ "dataset":{ "train": { 
  "type": "mnist", "data_set": "train", "layout_x": "tensor"}, "test": { 
  "type": "mnist", "data_set": "test", "layout_x": "tensor"} }, "train":{ "keep_model_in_mem":0, "random_state":0, "data_cache":{ "cache_in_disk":{ "default":1 }, "keep_in_mem":{ "default":0 }, "cache_dir":"/mnt/raid/fengji/gcforest/mnist/fg-tree500-depth100-3folds/datas" } }, "net":{ "outputs": ["pool1/7x7/ets", "pool1/7x7/rf", "pool1/10x10/ets", "pool1/10x10/rf", "pool1/13x13/ets", "pool1/13x13/rf"], "layers":[ { "type":"FGWinLayer", "name":"win1/7x7", "bottoms": ["X","y"], "tops":["win1/7x7/ets", "win1/7x7/rf"], "n_classes": 124, "estimators": [ { 
  "n_folds":3,"type":"ExtraTreesClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10}, { 
  "n_folds":3,"type":"RandomForestClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10} ], "stride_x": 2, "stride_y": 2, "win_x":7, "win_y":7 }, { "type":"FGWinLayer", "name":"win1/10x10", "bottoms": ["X","y"], "tops":["win1/10x10/ets", "win1/10x10/rf"], "n_classes": 10, "estimators": [ { 
  "n_folds":3,"type":"ExtraTreesClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10}, { 
  "n_folds":3,"type":"RandomForestClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10} ], "stride_x": 2, "stride_y": 2, "win_x":10, "win_y":10 }, { "type":"FGWinLayer", "name":"win1/13x13", "bottoms": ["X","y"], "tops":["win1/13x13/ets", "win1/13x13/rf"], "n_classes": 10, "estimators": [ { 
  "n_folds":3,"type":"ExtraTreesClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10}, { 
  "n_folds":3,"type":"RandomForestClassifier","n_estimators":500,"max_depth":100,"n_jobs":-1,"min_samples_leaf":10} ], "stride_x": 2, "stride_y": 2, "win_x":13, "win_y":13 }, { "type":"FGPoolLayer", "name":"pool1", "bottoms": ["win1/7x7/ets", "win1/7x7/rf", "win1/10x10/ets", "win1/10x10/rf", "win1/13x13/ets", "win1/13x13/rf"], "tops": ["pool1/7x7/ets", "pool1/7x7/rf", "pool1/10x10/ets", "pool1/10x10/rf", "pool1/13x13/ets", "pool1/13x13/rf"], "pool_method": "avg", "win_x":2, "win_y":2 } ] } }

因为在代码中，json.loads()并没有读取完整的json文件，只是读取了行，所以这时json.loads(line)读取的是不合符json语法的字符串，会报错：

with open("文件名") as f: line=f.readline(): # 这里line只是读取了json文件的一行，并没有全部读取，所以line里面所存的字符串是不符合json语法的，所以读取出错。 result=json.loads(line) Traceback (most recent call last): File "D:/PycharmProjects/mnistCheck/test.py", line 12, in 
  
    result = json.loads(row) File 
   "C:\ProgramData\Anaconda3\envs\tensorflow\lib\json\__init__.py", line 
   319, 
   in loads 
   return _default_decoder.decode(s) File 
   "C:\ProgramData\Anaconda3\envs\tensorflow\lib\json\decoder.py", line 
   339, 
   in decode obj, end = self.raw_decode(s, idx=_w(s, 
   0).end()) File 
   "C:\ProgramData\Anaconda3\envs\tensorflow\lib\json\decoder.py", line 
   355, 
   in raw_decode obj, end = self.scan_once(s, idx) json.decoder.JSONDecodeError: Expecting property name enclosed 
   in double quotes: line 
   2 column 
   1 (char 
   2) 
  

那么问题来了。。。。在实际应用中，我们会在json文件中做注释，比如以“//”开头的注释，除了注释部分外，其他内容都是符合json语法的，那么我们要怎么处理呢？

 def load_json(path): import json lines = [] # 第一步：定义一个列表， 打开文件 with open(path) as f: for row in f.readlines(): # 第二步：读取文件内容  if row.strip().startswith("//"): # 第三步：对每一行进行过滤  continue lines.append(row) # 第四步：将过滤后的行添加到列表中. return json.loads("\n".join(lines)) #将列表中的每个字符串用某一个符号拼接为一整个字符串，用json.loads()函数加载，这样就大功告成啦！！

今天的学习就到这里，明天见！！