python 导入excel 分词_语料工具--Python--jieba分词和Excel文件处理

#encoding=utf-8

import jieba

import xlrd

from datetime import date,datetime

import xdrlib,sys

import xlwt

def read_excel():

data =xlrd.open_workbook(r'C:\Users\weifu\Desktop\S0999\source_files.xls')

file = xlwt.Workbook()

table_w = file.add_sheet('fc',cell_overwrite_ok=True)

table = data.sheet_by_index(0)

nrows = table.nrows

ncols = table.ncols

for i in range(nrows):

seg_list = jieba.cut(str(table.row(i)[1].value))

print (table.row(i)[1].value)

value = " / ".join(seg_list)

if i > 0 :

table_w.write(i,0,table.row_values(i)[0])

table_w.write(i,1,table.row_values(i)[1])

table_w.write(i,2,value)

else :

table_w.write(0,0,"文件名")

table_w.write(0,1,"原词")

table_w.write(0,2,"分词结果")

file.save(r'C:\Users\weifu\Desktop\S0999\source_files_fc.xls')

read_excel()