import spacy
nlp = spacy.load("en_core_web_lg")

# 读取停用词列表
from nltk.corpus import stopwords  
stopword_list = list(stopwords.words('english'))
add_stopword_list = ["'s",'also','even']
stopword_list+=add_stopword_list

# pos_tag = ['JJ','JJR','JJS','RB','RBR','RBS','VB','VBD','VBG','VBN','VBP','VBZ','NN','NNP','NNPS','NNS']
pos_tag = ['JJ','JJR','JJS','RB','RBR','RBS']

def dataPrepro(corpus,stopword_list,pos_tag):
    """corpus：语料，str格式；stopword_list停用词列表；pos_tag：词性列表，筛选出指定词性的词"""
    token_list = []
    for token in nlp(corpus):
        if token.text not in stopword_list and token.tag_ in pos_tag: # 去停用词 + 词性筛选
            token_list.append(token.text)
    
    output = " ".join(token_list)
    return output