使用jieba去除文本里的姓名

import jieba
import jieba.posseg as pseg
import re

def replace_with_asterisks(match):
    return '*' * len(match.group())

def remove_personal_info(text):
    # 使用jieba对文本进行分词，同时获取词性
    words_with_flags = pseg.cut(text)

    # 遍历分词结果，将'nr'(人名)替换为相应数量的'*'
    filtered_sentence = ''.join(word if flag != 'nr' else '*' * len(word) for word, flag in words_with_flags)

    # 电话、身份证号码、电子邮箱、QQ号码的简单正则表达式
    regex_dict = {
        "phone": r"1[3-9]\d{9}",
        "employee_id": r"[a-z0-9]{4,50}",
        "id_card": r"[\dXx]",
        "email": r"\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b",
        "qq": r"[1-9][0-9]{4,10}(?!\.com)"
    }

    for info, regex in regex_dict.items():
        filtered_sentence = re.sub(regex, replace_with_asterisks, filtered_sentence, flags=re.IGNORECASE)

    return filtered_sentence

with open('input.txt', 'r', encoding='utf-8') as f:
    text_with_info = f.read()

filtered_text = remove_personal_info(text_with_info)
print(filtered_text)

with open('filtered_text.txt', 'w', encoding='utf-8') as f:
    f.write(filtered_text)

存在的问题，可能邮箱被分词写死，@qq.com替换不了