Python 学习 Day 27

import requests
from useragent import UserAgent
from lxml import etree

url = ‘http://www.farmer.com.cn/xwpd/rdjjl/201807/t201880722/_1393916.htm’

headers = {
‘User-Agent’: UserAgent().chrome
}

response = requests.get(url,headers=headers)
e = etree.HTML(response.text)
title = e.xpath(‘//h1/text()’)
content = e.xpath(‘string(div[@class=“content”]//p’)
img_urls = e.xpath(‘//div[@class=“content”]//img/@src’)
img_names = e.xpath(‘//div[@align=“center”’)
for img_name in img_names:
img_name =title + img_name.xpath(‘string(,)’)