Python，根据字符串长度将行拆分为字典中的多列

Question

我正在解析一个只有3列的XML文件。第三列（叙述性）有时（每100条记录中的1条）长于4000个字符。如果长度超过4000个字符，我想在字典中创建一个附加字段。因此，每增加4000个字符，就创建一个新字段。

#this function does various xml cleanups 
def getvalueofnode(node):
    if node is None:
        return None
    else:
        soup = BeautifulSoup(node.text)
        text = soup.get_text()
        text = text.replace("\n", " ")
        text = text.replace("\r", " ")
        text = text.replace(' +', ' ')
        text = text.replace('|', '-')
        text = text.replace('_+', '_') 
        return text

    record = []
    for node in parsedXML.getroot():
        recordline = node.find('DATA_RECORD'), node.find('CASE_KEY'), node.find('DESCRIPTION'), node.find('CASE_NARRATIVE') 
        recordlineprocessed = {
            'casekey': getvalueofnode(recordline[1]), 
            'description': getvalueofnode(recordline[2]), 
            'narrative': getvalueofnode(recordline[3])
                }
        record.append(recordlineprocessed)

    df_xml = pd.DataFrame.from_dict(record) 
    df_xml.to_csv(outfile, sep='\t', index = False)