#-*- coding:utf-8 -*- #取一个字符串中最多出现次数的词 import re from collections import Counter my_str = """ Simple is better than complex. Complex is better than complicated. Flat is better than nested. Sparse is better than dense. Readability counts. Special cases aren't special enough to break the rules. Although practicality beats purity. Errors should never pass silently. Unless explicitly silenced. In the face of ambiguity, refuse the temptation to guess. There should be one-- and preferably only one --obvious way to do it. Although that way may not be obvious at first unless you're Dutch. Now is better than never. Although never is often better than *right* now. If the implementation is hard to explain, it's a bad idea. If the implementation is easy to explain, it may be a good idea. Namespaces are one honking great idea -- let's do more of those! """ word_count = Counter(re.split('[ .,;~!-<>/|@#$%^&*?\n\t]', my_str)) #取非空的前八个最多单词 most_11 = [x for x in word_count.most_common(8) if x[0] != ""] #直接取前八个最多单词 print word_count.most_common(8) print(most_11) for i in most_11: print i[0]