爬取一首唐诗

from lxml import etree
import requests
# 爬取一首唐诗
hercx={
    'User-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/105.0.0.0 Safari/537.36 Edg/105.0.1343.25'
}
xcvb=requests.get('https://so.gushiwen.cn/shiwenv_478043ea449a.aspx',headers=hercx).text
'爬取一首古诗'

html=etree.HTML(xcvb)


'标头的xpth的'
roto=html.xpath('//*[@id="sonsyuanwen"]/div[1]/h1/text()')
"作者的xpth"
roto1=html.xpath('//*[@id="sonsyuanwen"]/div[1]/p/a[1]/text()')
'诗句'
textuio=html.xpath('/html/body/div[2]/div[1]/div[2]/div[1]/div[2]/text()')


for i in textuio:
    print(str(i).replace(' ',''))

标签：xpath,唐诗,text,爬取,html,一首,hercx,div
来源： https://www.cnblogs.com/xxh12/p/16673877.html