如果你有一个未知级别的字典，那么我会建议一个递归函数:

def combineDicts(dictionary1, dictionary2):
    output = {}
    for item, value in dictionary1.iteritems():
        if dictionary2.has_key(item):
            if isinstance(dictionary2[item], dict):
                output[item] = combineDicts(value, dictionary2.pop(item))
        else:
            output[item] = value
    for item, value in dictionary2.iteritems():
         output[item] = value
    return output

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]

这个版本的函数将处理N个字典，并且只处理字典——不能传递不恰当的参数，否则将引发TypeError。合并本身解释了键冲突，它不是覆盖来自合并链下的字典的数据，而是创建一组值并追加到该值;没有数据丢失。

它可能不是页面上最有效的，但它是最彻底的，当你合并2到N字典时，你不会丢失任何信息。

def merge_dicts(*dicts):
    if not reduce(lambda x, y: isinstance(y, dict) and x, dicts, True):
        raise TypeError, "Object in *dicts not of type dict"
    if len(dicts) < 2:
        raise ValueError, "Requires 2 or more dict objects"


    def merge(a, b):
        for d in set(a.keys()).union(b.keys()):
            if d in a and d in b:
                if type(a[d]) == type(b[d]):
                    if not isinstance(a[d], dict):
                        ret = list({a[d], b[d]})
                        if len(ret) == 1: ret = ret[0]
                        yield (d, sorted(ret))
                    else:
                        yield (d, dict(merge(a[d], b[d])))
                else:
                    raise TypeError, "Conflicting key:value type assignment"
            elif d in a:
                yield (d, a[d])
            elif d in b:
                yield (d, b[d])
            else:
                raise KeyError

    return reduce(lambda x, y: dict(merge(x, y)), dicts[1:], dicts[0])

print merge_dicts({1:1,2:{1:2}},{1:2,2:{3:1}},{4:4})

输出:{1:[1,2]，2:{1:2,3:1}，4:4}

如果有人想要另一种方法来解决这个问题，这是我的解决方案。

优点:简洁、声明性和函数式风格(递归，没有突变)。

潜在缺点:这可能不是你想要的合并。查阅文档字符串以了解语义。

def deep_merge(a, b):
    """
    Merge two values, with `b` taking precedence over `a`.

    Semantics:
    - If either `a` or `b` is not a dictionary, `a` will be returned only if
      `b` is `None`. Otherwise `b` will be returned.
    - If both values are dictionaries, they are merged as follows:
        * Each key that is found only in `a` or only in `b` will be included in
          the output collection with its value intact.
        * For any key in common between `a` and `b`, the corresponding values
          will be merged with the same semantics.
    """
    if not isinstance(a, dict) or not isinstance(b, dict):
        return a if b is None else b
    else:
        # If we're here, both a and b must be dictionaries or subtypes thereof.

        # Compute set of all keys in both dictionaries.
        keys = set(a.keys()) | set(b.keys())

        # Build output dictionary, merging recursively values with common keys,
        # where `None` is used to mean the absence of a value.
        return {
            key: deep_merge(a.get(key), b.get(key))
            for key in keys
        }

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。

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。