similarity_update.py 文件源码

def delstopwords(content):
    result = ''
    words = pseg.lcut("".join(content.split()))
    for word, flag in words:
        if word not in stopwords and flag not in ["/x", "/zg", "/uj", "/ul", "/e", "/d", "/uz",
                                                  "/y"]:  # ??????????????????
            result += word.encode('utf-8')  # +"/"+str(w.flag)+" "  #????
    return result