lxml解析网页例子

from lxml import etree
import requests

session = requests.session()
resp = session.get("https://www.hao123.com").content.decode("utf-8")
#print(resp)
html =etree.HTML(resp)

print(html.xpath('//*[@id="userCommonSites"]/text()'))
print(html.xpath('//a/@href'))