jieba对word文档词频分析

import docx

import jieba

from collections import Counter

import pandas as pd

import xlwt

document=docx.Document(r"C:\Users\fj\Desktop\讲话稿.docx")

content=" ".join([para.text for para in document.paragraphs])

seg_list=jieba.cut(content,cut_all=False)

seg_list=[

word

for word in seg_list

if len(word)>1

]

counter=Counter(seg_list)

data=pd.DataFrame(list(counter.items()),columns=[“词语”,“频率”])

data.to_excel(“词频统计.xlsx”,index=False)