python对文档批量分词再分别存在不同的txt中

# -*- coding:utf-8 -*-

import codecs

import os

import shutil

import jieba

import jieba.analyse

#Read file and cut

#create path

path ="E:\\python\\"

respath ="E:\\fc\\"

if os.path.isdir(respath):

shutil.rmtree(respath, True)

os.makedirs(respath)

stopwords = {}.fromkeys([line.strip()for linein open("E:\\哈工大停用词表.txt")])#导入用户自定义词典

num =1

while num<=2:

name ="%d" % num

fileName = path + str(name) +".txt"

    resName = respath + str(name) +".txt"

    source = open(fileName, 'r')

if os.path.exists(resName):

os.remove(resName)

result = codecs.open(resName, 'w', encoding='utf-8')

lines = source.readlines()

for linein lines:

line = line.rstrip('\r\n')

seglist = jieba.cut(line,cut_all=False)#精确模式

        output=''

        for segin seglist:

if segnot in stopwords:#去停用词

                if len(seg)>1:#去掉分词为1个字的结果

                    output += seg

output +=' '

        print (output)

result.write(output)

line = source.readline()

else:

print ('End file: ' + str(num))

source.close()

result.close()

num = num +1

else:

print ('End All')