THULAC包文本预处理，去停用词、分词

Python借助THULAC包对中文txt文档去停用词、分词`

import thulac
 
# 创建停用词list
def stopwordslist(filepath):
    stopwords = [line.strip() for line in open(filepath, 'r', encoding='utf-8').readlines()]
    return stopwords
 
# 对句子进行分词
def seg_sentence(sentence):
    sentence_seged = jieba.cut(sentence.strip())
    stopwords = stopwordslist('D:/stopwords.txt') 
     # 这里加载停用词的路径
    outstr = ''
    for word in sentence_seged:
        if word not in stopwords:
            if word != '\t':
                outstr += word
                outstr += " "
    return outstr
 
thu1 = thulac.thulac(seg_only=True)  #只进行分词，不进行词性标注
thu1.cut_f("input.txt", "output.txt")   #对input.txt文件内容进行分词，输出到output.txt