【python路上小记】request请求html并使用Xpath提取

使用 lxml提取

from lxml import etree
import re
import requests

ulr = 'www.csdn.net'
response = requests.get(url)
req = etree.HTML(response)
try:
	# 根据相应的xpath规则提取
	text = req.xpath("//body/div[3]/div[2]/div[1]/div[2]/div/p[3]/span/font/text()")[0] 
    text2 = req.xpath("//body/div[3]/div[2]/div[1]/ul/li[1]/text()")[0]