如何通过未知深度JSON结构格式化生成器解析的返回值

Question

tl;dr：

为什么这是-> dict(yield dict(name=new_key, url=d['url']).items())呢？

这不是-> dict(yield dict(new_key = d['url']).items())

所涉全部守则如下：

import json

with open(".\OsintFrameWork.json", "r") as file:
    osintFramework = json.load(file)

from collections.abc import MutableMapping

def _flatten_dict_gen(d, parent_key, sep):
    if isinstance(d, dict):
       new_key = parent_key + sep + d['name'] if parent_key else d['name'] 
       if isinstance(d.get('children'), list):
           yield from flatten_dict(d['children'], new_key, sep=sep).items()
       else:
           # # This works
           yield dict(name=new_key, url=d['url']).items()
           # # The following doesn't work:
           # yield dict(new_key = d['url']).items()
    else:
        for k in d:
            yield from flatten_dict(k, parent_key, sep=sep).items()

def flatten_dict(d: MutableMapping, parent_key: str = '', sep: str = '-'):
    return dict(_flatten_dict_gen(d, parent_key, sep))

new_dict = flatten_dict(osintFramework)
clean_dict = {item[1]: value[1] for item,value in new_dict.items()}
__import__('pprint').pprint(clean_dict)

所讨论的数据来自https://osintframework.com/arf.json

这个问题涉及_flatten_dict_gen的第二个收益陈述。

为什么我必须使用一个数据理解clean_dict来获得我想要的输出？

我试过yield dict(new_key = d['url']).items()我也试过yield {new_key : d['url']}.items()

通常，我尝试过的任何其他方式都会得到ValueError: dictionary update sequence element #0 has length x; 2 is required

所以把它都煮了下去：

如何将new_key=d['url']作为外部dict()函数的关键字参数

清洁：

{'OSINT Framework-Archives-Data Leaks-Cryptome': 'http://cryptome.org/',
 'OSINT Framework-Archives-Data Leaks-Databases.Today': 'https://databases.today/',
 'OSINT Framework-Archives-Data Leaks-Weleakinfo': 'https://search.weleakinfo.com/',
 'OSINT Framework-Archives-Data Leaks-WikiLeaks': 'https://wikileaks.org/',
 'OSINT Framework-Archives-Other Media-Library of Congress: Digitized Newspapers - 1836-1922': 'http://chroniclingamerica.loc.gov/',
 'OSINT Framework-Archives-Other Media-Library of Congress: Newspaper Directory - 1690-Present': 'http://chroniclingamerica.loc.gov/search/title
s/',
 'OSINT Framework-Archives-Other Media-TV Closed Caption Search': 'https://archive.org/details/tv', ....

不清洗：

{('name', 'OSINT Framework-Archives-Data Leaks-Cryptome'): ('url',
                                                            'http://cryptome.org/'),
 ('name', 'OSINT Framework-Archives-Data Leaks-Databases.Today'): ('url',
                                                                   'https://databases.today/'),
 ('name', 'OSINT Framework-Archives-Data Leaks-Weleakinfo'): ('url',
                                                              'https://search.weleakinfo.com/'),
 ('name', 'OSINT Framework-Archives-Data Leaks-WikiLeaks'): ('url',
                                                             'https://wikileaks.org/'),

Answer 1

我的版本

生成器flatten_dict i中的

• 使用相同的生成器_flatten_dict_gen来运行产量，而不是使用函数_flatten_dict_gen。

生成器中的

• 我删除了所有items()，我可以使用items()

• 它生成字典列表，因此我不得不更改代码flatten_dict，将该列表转换为单一字典

。

现在我不需要clean_dict

import json
from pprint import pprint
from collections.abc import MutableMapping
import requests

response = requests.get('https://osintframework.com/arf.json')
osintFramework = response.json()

#with open(".\OsintFrameWork.json", "r") as file:
#    osintFramework = json.load(file)

def _flatten_dict_gen(d, parent_key, sep):
    if isinstance(d, dict):
       new_key = parent_key + sep + d['name'] if parent_key else d['name']
       #print('new_key:', new_key)
       
       if isinstance(d.get('children'), list):
           yield from _flatten_dict_gen(d['children'], new_key, sep=sep)
       else:
           yield {new_key: d['url']}
    else:
        for k in d:
            yield from _flatten_dict_gen(k, parent_key, sep=sep)

def flatten_dict(d: MutableMapping, parent_key: str = '', sep: str = '-'):
    return {key:val for item in _flatten_dict_gen(d, parent_key, sep) for key, val in item.items()}

new_dict = flatten_dict(osintFramework)

pprint(new_dict)

flatten_dic也可以

def flatten_dict(d: MutableMapping, parent_key: str = '', sep: str = '-'):
    result = {}
    for item in _flatten_dict_gen(d, parent_key, sep):
        result.update(item)
    return result