python分析红楼梦出现的虚词词频统计,python对红楼梦的每一章节进行词频统计

python对红楼梦的每一章节进行词频统计

python对红楼梦的每一章节进行词频统计

import jieba

f=open("G:\\红楼梦.txt","r",encoding="utf-8")

txt=f.read()

words=jieba.lcut(txt)#精准模式

ls=[]


for word in words:

a={}

if word[0] == "第" and word[-1] == "回":

if word in ls:

continue

else:

ls.append(word)

print(ls)

for i in range(len(ls)):

print(ls[i])

a={}

if i

for word in words[words.index(ls[i])+1:words.index(ls[i + 1])]:

if len(word) == 1: # 排除单个字符的统计结果

continue

else: