这里有一个简洁明了的解决方案——

for x in set(li):
    li.remove(x)

li = list(set(li))

有点晚了，但可能对一些人有帮助。 对于一个比较大的列表，我发现这个方法很适合我。

l=[1,2,3,5,4,1,3,1]
s=set(l)
d=[]
for x in l:
    if x in s:
        s.remove(x)
    else:
        d.append(x)
d
[1,3,1]

显示正确和所有重复，并保持秩序。

我必须这样做，因为我挑战自己不使用其他方法:

def dupList(oldlist):
    if type(oldlist)==type((2,2)):
        oldlist=[x for x in oldlist]
    newList=[]
    newList=newList+oldlist
    oldlist=oldlist
    forbidden=[]
    checkPoint=0
    for i in range(len(oldlist)):
        #print 'start i', i
        if i in forbidden:
            continue
        else:
            for j in range(len(oldlist)):
                #print 'start j', j
                if j in forbidden:
                    continue
                else:
                    #print 'after Else'
                    if i!=j: 
                        #print 'i,j', i,j
                        #print oldlist
                        #print newList
                        if oldlist[j]==oldlist[i]:
                            #print 'oldlist[i],oldlist[j]', oldlist[i],oldlist[j]
                            forbidden.append(j)
                            #print 'forbidden', forbidden
                            del newList[j-checkPoint]
                            #print newList
                            checkPoint=checkPoint+1
    return newList

所以你的样本工作如下:

>>>a = [1,2,3,3,3,4,5,6,6,7]
>>>dupList(a)
[1, 2, 3, 4, 5, 6, 7]

简单地检查，对于所有列表项，如果一个项的第一个索引等于该项的最后一个索引:

>>> lastindex = lambda arr, el: len(arr) - arr[::-1].index(el) -1
>>> is_duplicate  = lambda arr, el: arr.index(el) != lastindex(arr, el)
>>> duplicates = lambda arr: [*set(x for x in arr if is_duplicate(arr, x))]
>>> 
>>> a=[2,3,5,7,11,13, 2,17,7,7,17,18,3,19,5,2,7,48,48,2,19]
>>> duplicates(a)
[2, 3, 5, 7, 48, 17, 19]
>>> 

还有其他测试。当然要做……

set([x for x in l if l.count(x) > 1])

.．.代价太大了。使用下一个final方法大约快500倍(数组越长结果越好):

def dups_count_dict(l):
    d = {}

    for item in l:
        if item not in d:
            d[item] = 0

        d[item] += 1

    result_d = {key: val for key, val in d.iteritems() if val > 1}

    return result_d.keys()

只有2个循环，没有非常昂贵的l.count()操作。

下面是一个比较方法的代码。代码如下，输出如下:

dups_count: 13.368s # this is a function which uses l.count()
dups_count_dict: 0.014s # this is a final best function (of the 3 functions)
dups_count_counter: 0.024s # collections.Counter

测试代码:

import numpy as np
from time import time
from collections import Counter

class TimerCounter(object):
    def __init__(self):
        self._time_sum = 0

    def start(self):
        self.time = time()

    def stop(self):
        self._time_sum += time() - self.time

    def get_time_sum(self):
        return self._time_sum


def dups_count(l):
    return set([x for x in l if l.count(x) > 1])


def dups_count_dict(l):
    d = {}

    for item in l:
        if item not in d:
            d[item] = 0

        d[item] += 1

    result_d = {key: val for key, val in d.iteritems() if val > 1}

    return result_d.keys()


def dups_counter(l):
    counter = Counter(l)    

    result_d = {key: val for key, val in counter.iteritems() if val > 1}

    return result_d.keys()



def gen_array():
    np.random.seed(17)
    return list(np.random.randint(0, 5000, 10000))


def assert_equal_results(*results):
    primary_result = results[0]
    other_results = results[1:]

    for other_result in other_results:
        assert set(primary_result) == set(other_result) and len(primary_result) == len(other_result)


if __name__ == '__main__':
    dups_count_time = TimerCounter()
    dups_count_dict_time = TimerCounter()
    dups_count_counter = TimerCounter()

    l = gen_array()

    for i in range(3):
        dups_count_time.start()
        result1 = dups_count(l)
        dups_count_time.stop()

        dups_count_dict_time.start()
        result2 = dups_count_dict(l)
        dups_count_dict_time.stop()

        dups_count_counter.start()
        result3 = dups_counter(l)
        dups_count_counter.stop()

        assert_equal_results(result1, result2, result3)

    print 'dups_count: %.3f' % dups_count_time.get_time_sum()
    print 'dups_count_dict: %.3f' % dups_count_dict_time.get_time_sum()
    print 'dups_count_counter: %.3f' % dups_count_counter.get_time_sum()

我注意到大多数解决方案的复杂度为O(n * n)，对于大型列表来说非常缓慢。所以我想分享一下我写的函数，它支持整数或字符串，在最好的情况下是O(n)。对于一个包含10万个元素的列表，最上面的解决方案需要超过30秒，而我的解决方案只需0.12秒

def get_duplicates(list1):
    '''Return all duplicates given a list. O(n) complexity for best case scenario.
    input: [1, 1, 1, 2, 3, 4, 4]
    output: [1, 1, 4]
    '''
    dic = {}
    for el in list1:
        try:
            dic[el] += 1
        except:
            dic[el] = 1
    dupes = []
    for key in dic.keys():
        for i in range(dic[key] - 1):
            dupes.append(key)
    return dupes


list1 = [1, 1, 1, 2, 3, 4, 4]
> print(get_duplicates(list1))
[1, 1, 4]

或者获得唯一的副本:

> print(list(set(get_duplicates(list1))))
[1, 4]