# coding:utf_8
import jieba
#first
# filePath='source.txt'
# fileSegWordDonePath ='sourceSegDone.txt'
#
# f = open(filePath, mode='r',encoding='utf-8')
# g = open(fileSegWordDonePath, mode='w',encoding='utf-8')
# sentence = f.read()
#
# words = jieba.cut(sentence,cut_all=False)
# # print(" ".join(words))#结果是"迭代器"。可以用循环打开,还可以用" “.join()的方式打开
# g.write(" ".join(words))
# f.close()
# g.close()
#second
with open('source.txt',encoding='utf-8') as f:
document = f.read()
document_cut = jieba.cut(document)
result = ' '.join(document_cut)
with open('sourceSegDone.txt', 'w',encoding="utf-8") as g:
g.write(result)
f.close()
g.close()
jieba打开文件进行分词,输出到另一个文件
最新推荐文章于 2022-07-03 17:10:30 发布