实现原理很简单,通过xpath定位实现
贴代码:
import requests
from lxml import etree
url=input('输入网址:')
header={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36 Edg/116.0.1938.54'
}
web=requests.get(url=f'https://{url}',headers=header).text
html=etree.HTML(web)
title=html.xpath('/html/head/title/text()')
keywords=html.xpath('/html/head/meta[@name="Keywords"]/@content')
description=html.xpath('/html/head/meta[@name="description"]/@content')
print(title)
print(keywords)
print(description)