list2 = [1, 2, 3, 4, 1, 2, 3]
lset = set()
[(lset.add(item), list2.append(item))
 for item in list2 if item not in lset]
print list(lset)

通过检查出现的次数，简单地遍历列表中的每个元素，然后将它们添加到一个集，然后打印重复的元素。希望这能帮助到一些人。

myList  = [2 ,4 , 6, 8, 4, 6, 12];
newList = set()

for i in myList:
    if myList.count(i) >= 2:
        newList.add(i)

print(list(newList))
## [4 , 6]

我们可以使用itertools。Groupby，以便找到所有有dup的项:

from itertools import groupby

myList  = [2, 4, 6, 8, 4, 6, 12]
# when the list is sorted, groupby groups by consecutive elements which are similar
for x, y in groupby(sorted(myList)):
    #  list(y) returns all the occurences of item x
    if len(list(y)) > 1:
        print x  

输出将是:

4
6

试试这个检查副本

>>> def checkDuplicate(List):
    duplicate={}
    for i in List:
            ## checking whether the item is already present in dictionary or not
            ## increasing count if present
            ## initializing count to 1 if not present

        duplicate[i]=duplicate.get(i,0)+1

    return [k for k,v in duplicate.items() if v>1]

>>> checkDuplicate([1,2,3,"s",1,2,3])
[1, 2, 3]

一个非常简单的解决方案，但是复杂度是O(n*n)。

>>> xs = [1,2,3,4,4,5,5,6,1]
>>> set([x for x in xs if xs.count(x) > 1])
set([1, 4, 5])

你不需要计数，只需要该物品之前是否被看到过。把这个答案用在这个问题上:

def list_duplicates(seq):
  seen = set()
  seen_add = seen.add
  # adds all elements it doesn't know yet to seen and all other to seen_twice
  seen_twice = set( x for x in seq if x in seen or seen_add(x) )
  # turn the set into a list (as requested)
  return list( seen_twice )

a = [1,2,3,2,1,5,6,5,5,5]
list_duplicates(a) # yields [1, 2, 5]

以防速度很重要，这里有一些时间安排:

# file: test.py
import collections

def thg435(l):
    return [x for x, y in collections.Counter(l).items() if y > 1]

def moooeeeep(l):
    seen = set()
    seen_add = seen.add
    # adds all elements it doesn't know yet to seen and all other to seen_twice
    seen_twice = set( x for x in l if x in seen or seen_add(x) )
    # turn the set into a list (as requested)
    return list( seen_twice )

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

def JohnLaRooy(L):
    seen = set()
    seen2 = set()
    seen_add = seen.add
    seen2_add = seen2.add
    for item in L:
        if item in seen:
            seen2_add(item)
        else:
            seen_add(item)
    return list(seen2)

l = [1,2,3,2,1,5,6,5,5,5]*100

以下是结果:(做得好@JohnLaRooy!)

$ python -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
10000 loops, best of 3: 74.6 usec per loop
$ python -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
10000 loops, best of 3: 91.3 usec per loop
$ python -mtimeit -s 'import test' 'test.thg435(test.l)'
1000 loops, best of 3: 266 usec per loop
$ python -mtimeit -s 'import test' 'test.RiteshKumar(test.l)'
100 loops, best of 3: 8.35 msec per loop

有趣的是，除了计时本身，当使用pypy时，排名也略有变化。最有趣的是，基于counter的方法极大地受益于pypy的优化，而我建议的方法缓存方法似乎几乎没有任何效果。

$ pypy -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
100000 loops, best of 3: 17.8 usec per loop
$ pypy -mtimeit -s 'import test' 'test.thg435(test.l)'
10000 loops, best of 3: 23 usec per loop
$ pypy -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
10000 loops, best of 3: 39.3 usec per loop

显然，这种效应与输入数据的“重复性”有关。我设置了l = [random.randrange(1000000) for I in xrange(10000)]，得到了这些结果:

$ pypy -mtimeit -s 'import test' 'test.moooeeeep(test.l)'
1000 loops, best of 3: 495 usec per loop
$ pypy -mtimeit -s 'import test' 'test.JohnLaRooy(test.l)'
1000 loops, best of 3: 499 usec per loop
$ pypy -mtimeit -s 'import test' 'test.thg435(test.l)'
1000 loops, best of 3: 1.68 msec per loop