使用 python 递归 json 到 csv

Question

我有一个 json 文件可以在 json 中转换它，但这里的情况是嵌套的 json 结构：

[ { "node":[ { "node":[ { "node":[ { "node":[ { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Industry is in bank exclusion list" ] }, { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Borrower is currently under bankruptcy law" ] }, { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Borrower is flagged as Unwilling" ] }, { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Borrower is flagged as non-viable" ] }, { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Borrower has blocked access of bank to Tiresias" ] }, { "valBool":false, "valStr1":[ "true" ], "valStr2":[ "Borrower is default (NPE/NPF eba status) " ] }, { "valBool":true, "valStr1":[ "false" ], "valStr2":[ "Default value" ] } ] } ] }, { "node":[ { "node":[ { "node":[ { "node":[ { "node":[ { "valBool":false, "valStr1":[ "1" ], "valStr2":[ "There are less \nthan 10 employees" ] }, { "valBool":false, "valStr1":[ "1" ], "valStr2":[ "Annual turnover is \nlower than annual \nturnover threshold" ] }, { "valBool":false, "valStr1":[ "1" ], "valStr2":[ "Total assets are \nlower than total \nassets threshold" ] }, { "valBool":true, "valStr1":[ "0" ], "valStr2":[ "Default" ] } ] } ] } ] } ] } ] } ] } ] } ]

如您所见，'node' 可以在任何级别找到。我尝试了一些递归方法，但输出不是我们想要的。我们需要将每个具有三个值的节点取出来，并将它们写入 csv 上的一行。

预期的输出应该是：

valBool,valStr1,valStr2
false,"true","Industry is in bank exclusion list"
false,"true","Borrower is currently under bankruptcy law"

我试过 this 但输出只是在新行中附加每个值，在键上写下整个路径。

有什么想法吗？

谢谢！

Answer 1

如果你的数据是 processing 是一个列表或字典。如果它是一个列表，您只需在其项目上追溯调用您的函数。如果它是你尝试的字典打印与 'valBool'、'valStr1' 和 'valStr2' 关联的值，如果它们存在并递归地调用关联的值 'node' 如果有的话。

data = [ { "node":[ { "node":[ { "node":[ { "node":[ { "valBool":False, "valStr1":[ "true" ], "valStr2":[ "Industry is in bank exclusion list" ] }, { "valBool":False, "valStr1":[ "true" ], "valStr2":[ "Borrower is currently under bankruptcy law" ] }, { "valBool": False, "valStr1":[ "true" ], "valStr2":[ "Borrower is flagged as Unwilling" ] }, { "valBool": False, "valStr1":[ "true" ], "valStr2":[ "Borrower is flagged as non-viable" ] }, { "valBool": False, "valStr1":[ "true" ], "valStr2":[ "Borrower has blocked access of bank to Tiresias" ] }, { "valBool":False, "valStr1":[ "true" ], "valStr2":[ "Borrower is default (NPE/NPF eba status) " ] }, { "valBool":True, "valStr1":[ "false" ], "valStr2":[ "Default value" ] } ] } ] }, { "node":[ { "node":[ { "node":[ { "node":[ { "node":[ { "valBool":False, "valStr1":[ "1" ], "valStr2":[ "There are less \nthan 10 employees" ] }, { "valBool":False, "valStr1":[ "1" ], "valStr2":[ "Annual turnover is \nlower than annual \nturnover threshold" ] }, { "valBool":False, "valStr1":[ "1" ], "valStr2":[ "Total assets are \nlower than total \nassets threshold" ] }, { "valBool":True, "valStr1":[ "0" ], "valStr2":[ "Default" ] } ] } ] } ] } ] } ] } ] } ] } ]

result = list()
def loop(data):
    if isinstance(data, list):
        for item in data:  # data is a list => recursive call on all its items
            loop(item)
    elif isinstance(data, dict):  # data is a dictionary
        try:
            row = f"{data['valBool']};{data['valStr1'][0]};{data['valStr2'][0]}"
            print(row)
            result.append(row)
        except KeyError: # dictionary does not have all valXXX keys
            pass
        if 'node' in data:  # recursive call if the dictionary has a "node" key
            loop(data['node'])

print('valBool;valStr1;valStr2')
loop(data)

这并不完全是您期望的输出，但您会发现如何修改。

[编辑] 修改代码以将行放入列表 result

使用 python 递归 json 到 csv

Recursive json to csv with python

python

csv

recursion

json