python之扁平化字典

我有以下一系列字典(只有一个字典):

[{ 
    'RuntimeInMinutes': '21', 
    'EpisodeNumber': '21', 
    'Genres': ['Animation'], 
    'ReleaseDate': '2005-02-05', 
    'LanguageOfMetadata': 'EN', 
    'Languages': [{ 
        '_Key': 'CC', 
        'Value': ['en'] 
    }, { 
        '_Key': 'Primary', 
        'Value': ['EN'] 
    }], 
    'Products': [{ 
        'URL': 'http://www.hulu.com/watch/217566', 
        'Rating': 'TV-Y', 
        'Currency': 'USD', 
        'SUBSCRIPTION': '0.00', 
        '_Key': 'US' 
    }, { 
        'URL': 'http://www.hulu.com/d/217566', 
        'Rating': 'TV-Y', 
        'Currency': 'USD', 
        'SUBSCRIPTION': '0.00', 
        '_Key': 'DE' 
    }], 
    'ReleaseYear': '2005', 
    'TVSeriesID': '5638#TVSeries', 
    'Type': 'TVEpisode', 
    'Studio': '4K Media' 
}] 

我想按如下方式展平字典:

[{ 
    'RuntimeInMinutes': '21', 
    'EpisodeNumber': '21', 
    'Genres': ['Animation'], 
    'ReleaseDate': '2005-02-05', 
    'LanguageOfMetadata': 'EN', 
    'Languages._Key': ['CC', 'Primary'], 
    'Languages.Value': ['en', 'EN'], 
    'Products.URL': ['http://www.hulu.com/watch/217566', 'http://www.hulu.com/d/217566'], 
    'Products.Rating': ['TV-Y', 'TV-Y'], 
    'Products.Currency': ['USD', 'USD'], 
    'Products.SUBSCRIPTION': ['0.00', '0.00'], 
    'Products._Key': ['US', 'DE'], 
    'ReleaseYear': '2005', 
    'TVSeriesID': '5638#TVSeries', 
    'Type': 'TVEpisode', 
    'Studio': '4K Media' 
}] 

换句话说，无论何时遇到字典，都需要将其转换为字符串、数字或列表。

我目前拥有的是以下内容，它使用 while 循环遍历 json 的所有子路径。

    while True: 
 
        for key in copy(keys): 
 
            val = get_sub_object_from_path(obj, key) 
 
            if isinstance(val, dict): 
                FLAT_OBJ[key.replace('/', '.')] = val 
            else: 
                keys.extend(os.path.join(key, _nextkey) for _nextkey in val.keys()) 
            keys.remove(key) 
 
        if (not keys) or (n > 5): 
            break 
        else: 
            n += 1 
            continue 

请您参考如下方法:

您可以将递归与生成器一起使用:

from collections import defaultdict 
_d = [{'RuntimeInMinutes': '21', 'EpisodeNumber': '21', 'Genres': ['Animation'], 'ReleaseDate': '2005-02-05', 'LanguageOfMetadata': 'EN', 'Languages': [{'_Key': 'CC', 'Value': ['en']}, {'_Key': 'Primary', 'Value': ['EN']}], 'Products': [{'URL': 'http://www.hulu.com/watch/217566', 'Rating': 'TV-Y', 'Currency': 'USD', 'SUBSCRIPTION': '0.00', '_Key': 'US'}, {'URL': 'http://www.hulu.com/d/217566', 'Rating': 'TV-Y', 'Currency': 'USD', 'SUBSCRIPTION': '0.00', '_Key': 'DE'}], 'ReleaseYear': '2005', 'TVSeriesID': '5638#TVSeries', 'Type': 'TVEpisode', 'Studio': '4K Media'}] 
 
def get_vals(d, _path = []): 
  for a, b in getattr(d, 'items', lambda :{})(): 
    if isinstance(b, list) and all(isinstance(i, dict) or isinstance(i, list) for i in b): 
       for c in b: 
         yield from get_vals(c, _path+[a]) 
    elif isinstance(b, dict): 
       yield from get_vals(b, _path+[a]) 
    else: 
       yield ['.'.join(_path+[a]), b] 
 
results = [i for b in _d for i in get_vals(b)] 
_c = defaultdict(list) 
for a, b in results: 
  _c[a].append(b) 
 
result = [{a:list(b) if len(b) > 1 else b[0] for a, b in _c.items()}] 
import json 
print(json.dumps(result, indent=4)) 

输出:

[ 
  { 
    "RuntimeInMinutes": "21", 
    "EpisodeNumber": "21", 
    "Genres": [ 
        "Animation" 
    ], 
    "ReleaseDate": "2005-02-05", 
    "LanguageOfMetadata": "EN", 
    "Languages._Key": [ 
        "CC", 
        "Primary" 
    ], 
    "Languages.Value": [ 
        [ 
            "en" 
        ], 
        [ 
            "EN" 
        ] 
    ], 
    "Products.URL": [ 
        "http://www.hulu.com/watch/217566", 
        "http://www.hulu.com/d/217566" 
    ], 
    "Products.Rating": [ 
        "TV-Y", 
        "TV-Y" 
    ], 
    "Products.Currency": [ 
        "USD", 
        "USD" 
    ], 
    "Products.SUBSCRIPTION": [ 
        "0.00", 
        "0.00" 
    ], 
    "Products._Key": [ 
        "US", 
        "DE" 
    ], 
    "ReleaseYear": "2005", 
    "TVSeriesID": "5638#TVSeries", 
    "Type": "TVEpisode", 
    "Studio": "4K Media" 
  } 
] 

编辑:在外部函数中包装解决方案:

def flatten_obj(data): 
  def get_vals(d, _path = []): 
    for a, b in getattr(d, 'items', lambda :{})(): 
      if isinstance(b, list) and all(isinstance(i, dict) or isinstance(i, list) for i in b): 
        for c in b: 
          yield from get_vals(c, _path+[a]) 
      elif isinstance(b, dict): 
        yield from get_vals(b, _path+[a]) 
      else: 
        yield ['.'.join(_path+[a]), b] 
  results = [i for b in data for i in get_vals(b)] 
  _c = defaultdict(list) 
  for a, b in results: 
     _c[a].append(b) 
  return [{a:list(b) if len(b) > 1 else b[0] for a, b in _c.items()}]