这个问题的一个问题是字典的值可以是任意复杂的数据块。基于这些和其他答案，我得出了以下代码:

class YamlReaderError(Exception):
    pass

def data_merge(a, b):
    """merges b into a and return merged result

    NOTE: tuples and arbitrary objects are not handled as it is totally ambiguous what should happen"""
    key = None
    # ## debug output
    # sys.stderr.write("DEBUG: %s to %s\n" %(b,a))
    try:
        if a is None or isinstance(a, str) or isinstance(a, unicode) or isinstance(a, int) or isinstance(a, long) or isinstance(a, float):
            # border case for first run or if a is a primitive
            a = b
        elif isinstance(a, list):
            # lists can be only appended
            if isinstance(b, list):
                # merge lists
                a.extend(b)
            else:
                # append to list
                a.append(b)
        elif isinstance(a, dict):
            # dicts must be merged
            if isinstance(b, dict):
                for key in b:
                    if key in a:
                        a[key] = data_merge(a[key], b[key])
                    else:
                        a[key] = b[key]
            else:
                raise YamlReaderError('Cannot merge non-dict "%s" into dict "%s"' % (b, a))
        else:
            raise YamlReaderError('NOT IMPLEMENTED "%s" into "%s"' % (b, a))
    except TypeError, e:
        raise YamlReaderError('TypeError "%s" in key "%s" when merging "%s" into "%s"' % (e, key, b, a))
    return a

我的用例是合并YAML文件，其中我只需要处理可能的数据类型的子集。因此我可以忽略元组和其他对象。对我来说，合理的合并逻辑意味着

取代标量 添加列表 通过添加缺失键和更新现有键来合并字典

其他任何事情和不可预见的事情都会导致错误。

以下是来自@andrew cooke的回答。 它以更好的方式处理嵌套列表。

def deep_merge_lists(original, incoming):
    """
    Deep merge two lists. Modifies original.
    Recursively call deep merge on each correlated element of list. 
    If item type in both elements are
     a. dict: Call deep_merge_dicts on both values.
     b. list: Recursively call deep_merge_lists on both values.
     c. any other type: Value is overridden.
     d. conflicting types: Value is overridden.

    If length of incoming list is more that of original then extra values are appended.
    """
    common_length = min(len(original), len(incoming))
    for idx in range(common_length):
        if isinstance(original[idx], dict) and isinstance(incoming[idx], dict):
            deep_merge_dicts(original[idx], incoming[idx])

        elif isinstance(original[idx], list) and isinstance(incoming[idx], list):
            deep_merge_lists(original[idx], incoming[idx])

        else:
            original[idx] = incoming[idx]

    for idx in range(common_length, len(incoming)):
        original.append(incoming[idx])


def deep_merge_dicts(original, incoming):
    """
    Deep merge two dictionaries. Modifies original.
    For key conflicts if both values are:
     a. dict: Recursively call deep_merge_dicts on both values.
     b. list: Call deep_merge_lists on both values.
     c. any other type: Value is overridden.
     d. conflicting types: Value is overridden.

    """
    for key in incoming:
        if key in original:
            if isinstance(original[key], dict) and isinstance(incoming[key], dict):
                deep_merge_dicts(original[key], incoming[key])

            elif isinstance(original[key], list) and isinstance(incoming[key], list):
                deep_merge_lists(original[key], incoming[key])

            else:
                original[key] = incoming[key]
        else:
            original[key] = incoming[key]

换个答案怎么样?!?这也避免了突变/副作用:

def merge(dict1, dict2):
    output = {}

    # adds keys from `dict1` if they do not exist in `dict2` and vice-versa
    intersection = {**dict2, **dict1}

    for k_intersect, v_intersect in intersection.items():
        if k_intersect not in dict1:
            v_dict2 = dict2[k_intersect]
            output[k_intersect] = v_dict2

        elif k_intersect not in dict2:
            output[k_intersect] = v_intersect

        elif isinstance(v_intersect, dict):
            v_dict2 = dict2[k_intersect]
            output[k_intersect] = merge(v_intersect, v_dict2)

        else:
            output[k_intersect] = v_intersect

    return output

dict1 = {1:{"a":{"A"}}, 2:{"b":{"B"}}}
dict2 = {2:{"c":{"C"}}, 3:{"d":{"D"}}}
dict3 = {1:{"a":{"A"}}, 2:{"b":{"B"},"c":{"C"}}, 3:{"d":{"D"}}}

assert dict3 == merge(dict1, dict2)

这应该有助于将所有项从dict2合并到dict1:

for item in dict2:
    if item in dict1:
        for leaf in dict2[item]:
            dict1[item][leaf] = dict2[item][leaf]
    else:
        dict1[item] = dict2[item]

请测试一下，告诉我们这是否是你想要的。

编辑:

上述解决方案只合并了一个级别，但正确地解决了op给出的例子。如果合并多个级别，应该使用递归。

我一直在测试你的解决方案，并决定在我的项目中使用这个:

def mergedicts(dict1, dict2, conflict, no_conflict):
    for k in set(dict1.keys()).union(dict2.keys()):
        if k in dict1 and k in dict2:
            yield (k, conflict(dict1[k], dict2[k]))
        elif k in dict1:
            yield (k, no_conflict(dict1[k]))
        else:
            yield (k, no_conflict(dict2[k]))

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

#this helper function allows for recursion and the use of reduce
def f2(x, y):
    return dict(mergedicts(x, y, f2, lambda x: x))

print dict(mergedicts(dict1, dict2, f2, lambda x: x))
print dict(reduce(f2, [dict1, dict2]))

将函数作为参数传递是将jterrace解决方案扩展为所有其他递归解决方案的关键。

这是我做的递归合并字典到无限深度的解决方案。传递给函数的第一个字典是主字典——其中的值将覆盖第二个字典中相同键的值。

def merge(dict1: dict, dict2: dict) -> dict:
    merged = dict1

    for key in dict2:
        if type(dict2[key]) == dict:
            merged[key] = merge(dict1[key] if key in dict1 else {}, dict2[key])
        else:
            if key not in dict1.keys():
                merged[key] = dict2[key]

    return merged