爬取网页小说

最新推荐文章于 2025-05-11 08:42:46 发布

巫巫仔

最新推荐文章于 2025-05-11 08:42:46 发布

阅读量91

点赞数 1

文章标签： python

本文链接：https://blog.csdn.net/weixin_71163337/article/details/144595655

版权

# 怎么发送请求
# pip install requests
import requests
# pip install lxml
from lxml import etree
# 发送给谁
url = 'https://www.22biqu.com/biqu74803/36891342.html'
while True:
    # 伪装自己
    headers ={'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0'}
    resp = requests.get(url,headers=headers)
    # 设置编码
    resp.encoding = 'utf-8'
    # 发送请求
    # 响应信息
    e = etree.HTML(resp.text)
    info = '\n'.join(e.xpath('//div[@class="content"]/p/text()'))
    title = e.xpath('//div/h1[@class="title"]/text()')[0]
    url = f'https://www.22biqu.com/{e.xpath('//div[@class="section-opt"]/a[@id="next_url"]/@href')[0]}'
    # 保存文件
    print(title)
    with open('奇洛李维斯回信.txt','a',encoding='utf-8') as f:
         f.write(title+'\n\n'+info)

    if url == 'https://dldl1.nsbuket.cc/xiaoshuo/douluodalu/218020.html':
        break

需要提前安装request、lxml、xpath-helper