爬虫-文本列表下载

点击查看代码

import requests
from lxml import etree

url = 'http://antpython.net/webspider/show_mingyan_jingju'
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)
lis = html_etree.xpath('//li[@class="list-group-item"]')
for li in lis:
    title = ''.join(li.xpath('./text()'))
    print(title)