紧接前面的xpath提取属性,这篇则提取文本
'''
xpath提取网页的文本
面向过程编程
'''
#导入第三方库
import requests
from lxml import etree
#定制请求头
headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/64.0.3282.140 Safari/537.36 Edge/18.17763'}
#请求的目标网页
url ='https://www.d4j.cn/book/xiaoshuowenxue'
#获取目标网页文本
html = requests.get(url,headers = headers).text
#xpath库解析网页,提取所需文本
e = etree.HTML(html)
#xpath解析语法
names = e.xpath('//div[@class="kratos-entry-thumb-new"]/a/img/@alt')
#遍历输出文本
for name in names:
print(name)