# import jieba
#
# # 读取文件
# file1 = open("test.txt", "rb").read()
# # 统计词数
# words = jieba.lcut(file1)
#
# # 定义一个空字典
# counts = {}
# for word in words:
# if len(word) == 1:
# continue
# else:
# counts[word] = counts.get(word, 0) + 1
# items = list(counts.items())
# # 排序
# items.sort(key=lambda x: x[1], reverse=True)
# resultFile = open("outPut.txt", "a+", encoding="utf-8")
# for i in range(5):
# word, count = items[i]
# resultFile.write("{0:<10}{1:>5}\n".format(word, count))

import jieba


def openFile(path):
 text = open(path, 'r', encoding='ANSI').read()
 return text


text = openFile('test.txt')
words = jieba.lcut(text)
lst = ['һ']
dict = {}

for word in words:
 if word.isalpha():
 if len(word) == 1:
 continue
 else:
 dict[word] = dict.get(word, 0) + 1
items = list(dict.items())
items.sort(key=lambda x: x[1], reverse=True)
str1 = ''

for i in lst:
 for j in items:
 if j[0] == i:
 items.remove(j)

for i in range(5):
 word, count = items[i]
 str1 += "{} : {}".format(word, count) + '\n'

file = open("output.txt", 'w+', encoding='utf-8')
file.writelines(str1)
file.close