data_integration.py 文件源码

def parse_xml_language_similarity(file_read,file_write):
    count = 0
    with open(file_read,'r') as f, open(file_write,'w') as out:
        for line in f:
            count +=1
            if count %1000 == 0: print(count)
            if "row Id" in line:
                line = line.strip()
                root = xml.etree.ElementTree.fromstring(line)
                try:
                    body = remove_tags(root.get('Body'))
                    title = remove_tags(root.get('Title'))
                    body_sentences = sent_tokenize(body)
                    title_sentences = sent_tokenize(title)
                    for line in body_sentences:
                        out.write(line+"\n")
                    for line in title_sentences:
                        out.write(line+"\n")
                except:
                    continue