python 请求url乱码问题处理

废话不多做，直接开干！

用到知识点

 response.encoding = 'gb2312'  # 表示将gb2312编码的字符串str1转换成unicode编码。

看完整代码

# coding=gb2312
import requests
from lxml import etree


if __name__ == '__main__':
    url = 'https://pic.netbian.com/4kmeinv/'
    headers = {
        # "User-Agent": "Mozilla/5.0(Windows NT 10.0;Win64;x64;rv: 96.0) Gecko/20100101 Firefox/96.0"
    }
    response = requests.get(url=url, headers=headers)
    response.encoding = 'gb2312'  # 手动对数据进行编码
    page_text = response.text
    print(page_text)
    # 数据解析 alt属性
    # tree = etree.HTML(page_text)
    # li_list = tree.xpath('//div[@class="slist"]/ul/li')
    # for li in li_list:
    #     img_src = 'https://pic.netbian.com'+li.xpath('./a/img/@src')[0]
    #     img_name = li.xpath('./a/img/@alt')[0]+'.jpg'
    #     # 处理中文乱码的解决方案
    #     img_name = img_name.encode('raw_unicode_escape')
    #     ddd = 'cosplay\\u052d\\ufffd\\ufffd \\u027a\\ufffd\\ufffd\\ufffd\\ufffd\\ufffd\\u013a\\ufffd cos\\ufffd\\ufffd\\u016e4k\\ufffd\\ufffd\\u05bd.jpg'
    #     ddd = ddd.encode('gbk')
    #     print(ddd)
        # print(img_name)

运行正常显示中文了