Python之words count

时间:2022-06-24 00:15:23

要求:

对文件单词进行统计,不区分大小写,并显示单词重复最多的十个单词

思路:

利用字典key,value的特性存单词及其重复的次数

每行进行特殊字符的处理,分离出被特殊字符包含的单词

def makekey(s:str)->list:
lst = []
s_complex = set(r"""!`#.,-*()\/[]*""") #利用集合装置特殊字符,前缀r不用转义
for word_i in s:
if word_i in s_complex:
lst.append(" ")
else:
lst.append(word_i)
new_string = "".join(lst).split()
return new_string src = '/tmp/sample.txt'
dic = {}
with open(src,'r') as f:
# f.readlines()
for line in f:
words_list=line.lower().split()
for word in words_list: #str in list
word = makekey(word) #return list
for words in word:
if words in dic.keys():
dic[words]+=1
else:
dic[words] = 1
reverse_dict = sorted(dic.items(),key=lambda x:x[1],reverse=True)
print(reverse_dict[:10])