python requests lxml etree xpath 获取网页信息

python requests lxml etree xpath 获取网页信息

import requests
from lxml import etree
import re
baseurl = "https://desk.zol.com.cn/"
url = "https://desk.zol.com.cn/dongman/"
#获取网页
data = requests.get(url)   #获取网页内容
data.encoding = "gbk"    #编码为gbk
et = etree.HTML(data.text)   #将网页内容加载到etree中

#从网页中找链接
list_urls = et.xpath('//ul[@]/li/a/@href')     #使用xpath找到对应元素列表
for item in list_urls:           #拼接url
    urls = baseurl + item
#列出链接
    print(urls)