爬虫-----071xpath解析百度的百度一下

#(1)获取网页源码
#(2)解析服务器响应的数据  etree.HTML()
#(3)打印

import urllib.request
from lxml import etree

url = 'https://www.baidu.com/'

headers = {
    'User-Agent':' Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36 SLBrowser/9.0.3.1311 SLBChan/103'
}


request = urllib.request.Request(url=url,headers=headers)

response = urllib.request.urlopen(request)

content = response.read().decode('utf-8')

#解析网页源码 获取想要的数据
#解析服务器响应文件
tree = etree.HTML(content)
#获取想要的数据   xpath返回值为一个列表数据
result = tree.xpath('//input[@id="su"]/@value')[0]
print(result)