jieba 分词 聊斋

import jieba
f = open(r'C:\liaozhai.txt', mode="r", encoding='gbk')
txt=f.read()
words  = jieba.lcut(txt)

counts = {}
for word in words:
    if len(word)  == 1:
        continue

    else:
        counts[word] =counts.get(word,0)+1

items = list(counts.items())
items.sort(key=lambda x:x[1], reverse=True)
for i in range(20):
    word,count = items[i]
    print (u"{0:<10}{1:>5}".format(word, count))