import requests from lxml import etree

url = 'http://www.weather.com.cn/weather/101090601.shtml' headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36' } response = requests.get(url, headers=headers) html = response.content.decode('utf-8') selector = etree.HTML(html)

方法 1：使用完整路径

high_temp = selector.xpath('/html/body/div[6]/div[1]/div[1]/div/ul/li[1]/p[2]/i/text()') low_temp = selector.xpath('/html/body/div[6]/div[1]/div[1]/div/ul/li[1]/p[2]/i/text()')

方法 2：使用相对路径

high_temp = selector.xpath('//ul[@class='t clearfix']/li/p[@class='tem']/span/text()') low_temp = selector.xpath('//ul[@class='t clearfix']/li/p[@class='tem']/i/text()')

print('最高温度：', high_temp[0]) print('最低温度：', low_temp[0])