Python爬虫识别中文字符和标点符号

Python爬虫识别中文字符和标点符号，并且保存成txt文档

import requests

href_list = final_df["隐私政策"].values
names = final_df["公司名称"].values

for i in range(len(href_list)):
    url = href_list[i]
    if url:
        try:
            res = requests.get(url).text
        except:
            print("失败:",url)
            continue
        try:
            res = res.encode("ISO-8859-1").decode("utf-8")
        except:
            try:
                res = res.encode("ISO-8859-1").decode("gbk")
            except:
                res = res
        res = re.sub("<.*?>", "", res)
        res = re.sub("{.*?}", "", res)
        res = res.replace('\n', '') 
        
        # 提取文字和标点符号！！！！！！！！！！！！！
        pattern = re.compile(u'[\u4e00-\u9fa5-\，\。]')
        result = pattern.findall(res)
        
        # 保存到txt文档中
        file = open("data/隐私政策/{}.txt".format(names[i]), 'w')
        string = "".join(result)
        file.write(string)