利用xpath数据解析爬取百度新闻热榜

import requests
from lxml import etree
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.82 Safari/537.36'
    
}
url=' http://top.baidu.com/?fr=mhd_card&qq-pf-to=pcqq.c2c'
r = requests.get(url)
html=r.content
page_text=str(html,'gbk') #html_doc=html.decode("utf-8","ignore")

# 热点+链接
tree = etree.HTML(page_text)
# 定位到该热点的li中

text_list=tree.xpath('//*[@id="hot-list"]/li')
for li in text_list:
    title = li.xpath('./a/@title')
    a_herf = li.xpath('./a/@href')
    print(title,a_herf)