為啥我的python code只能解析json的前半截？

注意:python3以后才支持yield from語法

import collections


def flatten(d, prefix="", sep="_"):
    def _take_prefix(k, v, p):
        if p:
            yield from flatten(v, "{}{}{}".format(p, sep, k))
        else:
            yield from flatten(v, str(k))

    if isinstance(d, dict):
        for k, v in d.items():
            if isinstance(v, str) or not isinstance(v, collections.Iterable):
                if prefix:
                    yield "{}{}{}".format(prefix, sep, k), v
                else:
                    yield k, v
            elif isinstance(v, dict):
                yield from _take_prefix(k, v, prefix)
            elif isinstance(v, list):
                for i in v:
                    yield from _take_prefix(k, i, prefix)
            else:
                pass
    else:
        pass

dic = {your dataset}
for key, value in flatten(dic):
    print("{}: {}".format(key, value))

結(jié)果如下,應(yīng)該能拍平了

status: changed
dataset_id: 5a4b463c855d783af4f5f695
dataset_name: AE_E
dataset_label: 1- ADVERSE EVENTS - Not Analyzed
details_variables_variable_id: 5a4b4647855d783b494f9d3f
details_variables_variable_name: CPEVENT
details_variables_variable_label: CPEVENT
details_variables_status: changed
details_variables_details_r_type_new_value: unary
details_variables_details_r_type_old_value: factor
details_variables_message: Variable with different R Type
details_variables_variable_id: 5a4b4647855d783b494f9d25
details_variables_variable_name: CPEVENT2
details_variables_variable_label: CPEVENT2
details_variables_status: changed
details_variables_details_r_type_new_value: unary
details_variables_details_r_type_old_value: binary
details_variables_message: Variable with different R Type
details_variables_variable_id: 5a4b4647855d783b494f9d26
details_variables_variable_name: CP_UNSCHEDULED
details_variables_variable_label: CP_UNSCHEDULED
details_variables_status: changed
details_variables_details_r_type_new_value: undefined
details_variables_details_r_type_old_value: unary
details_variables_message: Variable with different R Type
details_variables_variable_id: 5a4b4647855d783b494f9d02
details_variables_variable_name: VISIT_NUMBER
details_variables_variable_label: VISIT_NUMBER
details_variables_status: changed
details_variables_details_r_type_new_value: unary
details_variables_details_r_type_old_value: integer
details_variables_message: Variable with different R Type
details_variables_variable_id: 5a4b4647855d783b494f9ccf
details_variables_variable_name: VISIT_NUMBER2
details_variables_variable_label: VISIT_NUMBER2
details_variables_status: changed
details_variables_details_r_type_new_value: unary
details_variables_details_r_type_old_value: binary
details_variables_message: Variable with different R Type
details_many_visits: None

針對(duì)你修改后的問題, 再加個(gè)函數(shù)就搞定:

# 這個(gè)fuck_all函數(shù)比較特例, 完全是針對(duì)你要區(qū)分的dataset下面的N個(gè)變量信息這種需求
def fuck_all(dic, prefix="details_variables"):
    lst = list(flatten(dic))  # flatten函數(shù)則比較通用,任何嵌套數(shù)據(jù)集都可以用它拍平
    lines = []
    top = {k: v for k, v in lst if not k.startswith(prefix)}
    index = 0
    for key, value in lst:
        if not key.startswith(prefix):
            continue
        else:
            if not lines:
                lines.append(top.copy())
        if key in lines[index].keys():
            index += 1
            lines.append(top.copy())
        lines[index][key] = value
    return lines

d = {your dataset}
for i in fuck_all(d):
    print(i)    

結(jié)果長(zhǎng)這樣,應(yīng)該是能滿足你需求了

{'status': 'changed', 'dataset_id': '5a4b463c855d783af4f5f695', 'dataset_name': 'AE_E', 'dataset_label': '1- ADVERSE EVENTS - Not Analyzed', 'details_many_visits': None, 'details_variables_variable_id': '5a4b4647855d783b494f9d3f', 'details_variables_variable_name': 'CPEVENT', 'details_variables_variable_label': 'CPEVENT', 'details_variables_status': 'changed', 'details_variables_details_r_type_new_value': 'unary', 'details_variables_details_r_type_old_value': 'factor', 'details_variables_message': 'Variable with different R Type'}
{'status': 'changed', 'dataset_id': '5a4b463c855d783af4f5f695', 'dataset_name': 'AE_E', 'dataset_label': '1- ADVERSE EVENTS - Not Analyzed', 'details_many_visits': None, 'details_variables_variable_id': '5a4b4647855d783b494f9d25', 'details_variables_variable_name': 'CPEVENT2', 'details_variables_variable_label': 'CPEVENT2', 'details_variables_status': 'changed', 'details_variables_details_r_type_new_value': 'unary', 'details_variables_details_r_type_old_value': 'binary', 'details_variables_message': 'Variable with different R Type'}
{'status': 'changed', 'dataset_id': '5a4b463c855d783af4f5f695', 'dataset_name': 'AE_E', 'dataset_label': '1- ADVERSE EVENTS - Not Analyzed', 'details_many_visits': None, 'details_variables_variable_id': '5a4b4647855d783b494f9d26', 'details_variables_variable_name': 'CP_UNSCHEDULED', 'details_variables_variable_label': 'CP_UNSCHEDULED', 'details_variables_status': 'changed', 'details_variables_details_r_type_new_value': 'undefined', 'details_variables_details_r_type_old_value': 'unary', 'details_variables_message': 'Variable with different R Type'}
{'status': 'changed', 'dataset_id': '5a4b463c855d783af4f5f695', 'dataset_name': 'AE_E', 'dataset_label': '1- ADVERSE EVENTS - Not Analyzed', 'details_many_visits': None, 'details_variables_variable_id': '5a4b4647855d783b494f9d02', 'details_variables_variable_name': 'VISIT_NUMBER', 'details_variables_variable_label': 'VISIT_NUMBER', 'details_variables_status': 'changed', 'details_variables_details_r_type_new_value': 'unary', 'details_variables_details_r_type_old_value': 'integer', 'details_variables_message': 'Variable with different R Type'}
{'status': 'changed', 'dataset_id': '5a4b463c855d783af4f5f695', 'dataset_name': 'AE_E', 'dataset_label': '1- ADVERSE EVENTS - Not Analyzed', 'details_many_visits': None, 'details_variables_variable_id': '5a4b4647855d783b494f9ccf', 'details_variables_variable_name': 'VISIT_NUMBER2', 'details_variables_variable_label': 'VISIT_NUMBER2', 'details_variables_status': 'changed', 'details_variables_details_r_type_new_value': 'unary', 'details_variables_details_r_type_old_value': 'binary', 'details_variables_message': 'Variable with different R Type'}

送佛送到西好了

from functools import reduce
import json

import pandas as pd


with open("your dataset file", "r") as fh:
    dic = json.load(fh)

df = pd.DataFrame(reduce(lambda x, y: x + y, (fuck_all(i) for i in dic)))
df.to_csv("out.csv", index=False)

成品

你可以先測(cè)試一下，你的 details 里面的信息是否是 MutableMapping 對(duì)象實(shí)例。

你的if isinstance(v, collections.MutableMapping)沒有執(zhí)行。

試試看是否符合你的需求：

def flatten(d, parent_key='', sep='_'):
    items = []
    for k, v in d.items():
        new_key = parent_key + sep + k if parent_key else k
        
        is_lst = True if isinstance(v, list) else False
            
        if isinstance(v, collections.MutableMapping) or is_lst:
            if is_lst:
                items.extend(flatten(v[0], new_key, sep=sep).items())
            else:
                items.extend(flatten(v, new_key, sep=sep).items())
        else:
            items.append((new_key, v))
    return dict(items)