python-archieve-projects/M303/split_word.py

23 lines
479 B
Python

import jieba
excludes = {'风雨', '什么', '一个', '那里', '如今' }
text = open('红楼梦.txt', 'r', encoding='utf-8').read()
words = jieba.lcut(text)
counts = {}
for word in words:
if len(word) != 1:
counts[word] = counts.get(word, 0) + 1
for word in excludes:
del(counts[word])
items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(10):
word, count = items[i]
print('{0:<10}{1:>5}'.format(word, count))