我有一个迭代的解决方案-工作得更好的大字典&很多(例如jsons等):

import collections


def merge_dict_with_subdicts(dict1: dict, dict2: dict) -> dict:
    """
    similar behaviour to builtin dict.update - but knows how to handle nested dicts
    """
    q = collections.deque([(dict1, dict2)])
    while len(q) > 0:
        d1, d2 = q.pop()
        for k, v in d2.items():
            if k in d1 and isinstance(d1[k], dict) and isinstance(v, dict):
                q.append((d1[k], v))
            else:
                d1[k] = v

    return dict1

注意，这将使用d2中的值来覆盖d1，以防它们都不是字典。(与python的dict.update()相同)

一些测试:

def test_deep_update():
    d = dict()
    merge_dict_with_subdicts(d, {"a": 4})
    assert d == {"a": 4}

    new_dict = {
        "b": {
            "c": {
                "d": 6
            }
        }
    }
    merge_dict_with_subdicts(d, new_dict)
    assert d == {
        "a": 4,
        "b": {
            "c": {
                "d": 6
            }
        }
    }

    new_dict = {
        "a": 3,
        "b": {
            "f": 7
        }
    }
    merge_dict_with_subdicts(d, new_dict)
    assert d == {
        "a": 3,
        "b": {
            "c": {
                "d": 6
            },
            "f": 7
        }
    }

    # test a case where one of the dicts has dict as value and the other has something else
    new_dict = {
        'a': {
            'b': 4
        }
    }
    merge_dict_with_subdicts(d, new_dict)
    assert d['a']['b'] == 4

我已经测试了大约1200个字典——这种方法花了0.4秒，而递归的解决方案花了2.5秒。

由于dictviews支持集合操作，我能够极大地简化jterrace的答案。

def merge(dict1, dict2):
    for k in dict1.keys() - dict2.keys():
        yield (k, dict1[k])

    for k in dict2.keys() - dict1.keys():
        yield (k, dict2[k])

    for k in dict1.keys() & dict2.keys():
        yield (k, dict(merge(dict1[k], dict2[k])))

任何将dict与非dict(技术上讲，一个带有'keys'方法的对象和一个没有'keys'方法的对象)组合的尝试都会引发AttributeError。这包括对函数的初始调用和递归调用。这正是我想要的，所以我离开了。您可以很容易地捕获递归调用抛出的AttributeErrors，然后生成您想要的任何值。

在不影响输入字典的情况下返回一个合并。

def _merge_dicts(dictA: Dict = {}, dictB: Dict = {}) -> Dict:
    # it suffices to pass as an argument a clone of `dictA`
    return _merge_dicts_aux(dictA, dictB, copy(dictA))


def _merge_dicts_aux(dictA: Dict = {}, dictB: Dict = {}, result: Dict = {}, path: List[str] = None) -> Dict:

    # conflict path, None if none
    if path is None:
        path = []

    for key in dictB:

        # if the key doesn't exist in A, add the B element to A
        if key not in dictA:
            result[key] = dictB[key]

        else:
            # if the key value is a dict, both in A and in B, merge the dicts
            if isinstance(dictA[key], dict) and isinstance(dictB[key], dict):
                _merge_dicts_aux(dictA[key], dictB[key], result[key], path + [str(key)])

            # if the key value is the same in A and in B, ignore
            elif dictA[key] == dictB[key]:
                pass

            # if the key value differs in A and in B, raise error
            else:
                err: str = f"Conflict at {'.'.join(path + [str(key)])}"
                raise Exception(err)

    return result

灵感来自@andrew cooke的解决方案

这里有一个使用生成器的简单方法:

def mergedicts(dict1, dict2):
    for k in set(dict1.keys()).union(dict2.keys()):
        if k in dict1 and k in dict2:
            if isinstance(dict1[k], dict) and isinstance(dict2[k], dict):
                yield (k, dict(mergedicts(dict1[k], dict2[k])))
            else:
                # If one of the values is not a dict, you can't continue merging it.
                # Value from second dict overrides one in first and we move on.
                yield (k, dict2[k])
                # Alternatively, replace this with exception raiser to alert you of value conflicts
        elif k in dict1:
            yield (k, dict1[k])
        else:
            yield (k, dict2[k])

dict1 = {1:{"a":"A"},2:{"b":"B"}}
dict2 = {2:{"c":"C"},3:{"d":"D"}}

print dict(mergedicts(dict1,dict2))

这个打印:

{1: {'a': 'A'}, 2: {'c': 'C', 'b': 'B'}, 3: {'d': 'D'}}

正如在许多其他答案中提到的，递归算法在这里最有意义。一般来说，在使用递归时，最好创建新值，而不是试图修改任何输入数据结构。

我们需要定义在每个合并步骤中发生的事情。如果两个输入都是字典，这很简单:我们从每一边复制唯一键，然后递归合并重复键的值。导致问题的是基本情况。如果我们拿出一个单独的函数，逻辑会更容易理解。作为占位符，我们可以将这两个值包装在一个元组中:

def merge_leaves(x, y):
    return (x, y)

现在我们的逻辑核心是这样的:

def merge(x, y):
    if not(isinstance(x, dict) and isinstance(y, dict)):
        return merge_leaves(x, y)
    x_keys, y_keys = x.keys(), y.keys()
    result = { k: merge(x[k], y[k]) for k in x_keys & y_keys }
    result.update({k: x[k] for k in x_keys - y_keys})
    result.update({k: y[k] for k in y_keys - x_keys})
    return result

让我们来测试一下:

>>> x = {'a': {'b': 'c', 'd': 'e'}, 'f': 1, 'g': {'h', 'i'}, 'j': None}
>>> y = {'a': {'d': 'e', 'h': 'i'}, 'f': {'b': 'c'}, 'g': 1, 'k': None}
>>> merge(x, y)
{'f': (1, {'b': 'c'}), 'g': ({'h', 'i'}, 1), 'a': {'d': ('e', 'e'), 'b': 'c', 'h': 'i'}, 'j': None, 'k': None}
>>> x # The originals are unmodified.
{'a': {'b': 'c', 'd': 'e'}, 'f': 1, 'g': {'h', 'i'}, 'j': None}
>>> y
{'a': {'d': 'e', 'h': 'i'}, 'f': {'b': 'c'}, 'g': 1, 'k': None}

我们可以很容易地修改叶子归并规则，例如:

def merge_leaves(x, y):
    try:
        return x + y
    except TypeError:
        return Ellipsis

并观察效果:

>>> merge(x, y)
{'f': Ellipsis, 'g': Ellipsis, 'a': {'d': 'ee', 'b': 'c', 'h': 'i'}, 'j': None, 'k': None}

我们还可以通过使用第三方库来根据输入的类型进行分派来潜在地清理这个问题。例如，使用multidispatch，我们可以这样做:

@dispatch(dict, dict)
def merge(x, y):
    x_keys, y_keys = x.keys(), y.keys()
    result = { k: merge(x[k], y[k]) for k in x_keys & y_keys }
    result.update({k: x[k] for k in x_keys - y_keys})
    result.update({k: y[k] for k in y_keys - x_keys})
    return result

@dispatch(str, str)
def merge(x, y):
    return x + y

@dispatch(tuple, tuple)
def merge(x, y):
    return x + y

@dispatch(list, list)
def merge(x, y):
    return x + y

@dispatch(int, int):
def merge(x, y):
    raise ValueError("integer value conflict")

@dispatch(object, object):
    return (x, y)

这允许我们在不编写自己的类型检查的情况下处理叶类型特殊情况的各种组合，并在主递归函数中替换类型检查。

from collections import defaultdict
from itertools import chain

class DictHelper:

@staticmethod
def merge_dictionaries(*dictionaries, override=True):
    merged_dict = defaultdict(set)
    all_unique_keys = set(chain(*[list(dictionary.keys()) for dictionary in dictionaries]))  # Build a set using all dict keys
    for key in all_unique_keys:
        keys_value_type = list(set(filter(lambda obj_type: obj_type != type(None), [type(dictionary.get(key, None)) for dictionary in dictionaries])))
        # Establish the object type for each key, return None if key is not present in dict and remove None from final result
        if len(keys_value_type) != 1:
            raise Exception("Different objects type for same key: {keys_value_type}".format(keys_value_type=keys_value_type))

        if keys_value_type[0] == list:
            values = list(chain(*[dictionary.get(key, []) for dictionary in dictionaries]))  # Extract the value for each key
            merged_dict[key].update(values)

        elif keys_value_type[0] == dict:
            # Extract all dictionaries by key and enter in recursion
            dicts_to_merge = list(filter(lambda obj: obj != None, [dictionary.get(key, None) for dictionary in dictionaries]))
            merged_dict[key] = DictHelper.merge_dictionaries(*dicts_to_merge)

        else:
            # if override => get value from last dictionary else make a list of all values
            values = list(filter(lambda obj: obj != None, [dictionary.get(key, None) for dictionary in dictionaries]))
            merged_dict[key] = values[-1] if override else values

    return dict(merged_dict)



if __name__ == '__main__':
  d1 = {'aaaaaaaaa': ['to short', 'to long'], 'bbbbb': ['to short', 'to long'], "cccccc": ["the is a test"]}
  d2 = {'aaaaaaaaa': ['field is not a bool'], 'bbbbb': ['field is not a bool']}
  d3 = {'aaaaaaaaa': ['filed is not a string', "to short"], 'bbbbb': ['field is not an integer']}
  print(DictHelper.merge_dictionaries(d1, d2, d3))

  d4 = {"a": {"x": 1, "y": 2, "z": 3, "d": {"x1": 10}}}
  d5 = {"a": {"x": 10, "y": 20, "d": {"x2": 20}}}
  print(DictHelper.merge_dictionaries(d4, d5))

输出:

{'bbbbb': {'to long', 'field is not an integer', 'to short', 'field is not a bool'}, 
'aaaaaaaaa': {'to long', 'to short', 'filed is not a string', 'field is not a bool'}, 
'cccccc': {'the is a test'}}

{'a': {'y': 20, 'd': {'x1': 10, 'x2': 20}, 'z': 3, 'x': 10}}