jieba 分词 聊斋
import jieba
# -*- coding: utf-8 -*-
txt = open("D:\\python\\jieba\\聊斋志异.txt", "r", encoding='gb18030').read()
words = jieba.lcut(txt)
counts = {}
for word in words:
if len(word) == 1: # 单个词语不计算在内
continue
else:
counts[word] = counts.get(word, 0) + 1 # 遍历所有词语,每出现一次其对应的值加 1
items = list(counts.items())#将键值对转换成列表
items.sort(key=lambda x: x[1], reverse=True) # 根据词语出现的次数进行从大到小排序
for i in range(20):
word, count = items[i]
print("{0:<5}{1:>5}".format(word, count))