1. 获取小说-笔趣阁

• 只用于技术研究，不允许非法用途

获取列表

​​

代码

# 地址: https://www.um399.com/
# 获取笔趣阁中最新入库内容

import requests
from lxml import etree

url = "https://www.um399.com/"
## 添加请求头
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/118.0.0.0 Safari/537.36'
}

response = requests.get(url,headers=headers)
response.encoding = 'utf8'

#获取响应页内容
data = response.content.decode()
#实例化匹配对象
tree = etree.HTML(data)

#获取最新入库列表
li_list = tree.xpath("//div[@class='border3-1 popular']/div[@class='list-out']")

count=0
for li in li_list:
    count = count + 1
    # 获取图书名称
    # text() 获取文本节点
    # 获取书名
    book_name = li.xpath('./span/a/text()')[0]
    # 获取作者
    author = li.xpath('./span/text()')[1]
    print("书名:{},作者:{}".format(book_name,author))

print("总数:{}".format(count))