爬虫-小说数据下载

点击查看代码

import requests
from lxml import etree

url = 'http://antpython.net/novels/01.html'
headers = {
    "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/129.0.0.0 Safari/537.36 Edg/129.0.0.0"
}
response = requests.get(url, headers=headers)
html_etree = etree.HTML(response.text)
divs = html_etree.xpath('//div[@class="row"]')
for div in divs:
    title = ','.join(div.xpath('./div/a/text()'))
    print(title)