用Python 爬取并保存小说
1. 安装requests pip install requests
2. 安装lxml pip install lxml
3. 斗罗大陆网页
- 代码
4 import requests
from lxml import etree
url='https://www.85xs.cc/book/douluodalu1/1.html'
while True:
headers={
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/125.0.0.0 Safari/537.36 Edg/125.0.0.0'
}
resp=requests.get(url,headers=headers)
resp.encoding='utf-8'
#print(resp.text)
e=etree.HTML(resp.text)
info='\n'.join(e.xpath('//div[@class="m-post"]/p/text()'))
title=e.xpath('//h1/text()')[0]
url=f'https://www.85xs.cc{e.xpath("//tr/td[2]/a/@href")[0]}'
#print(info)
#print(title,'utf-8')
with open('斗罗大陆.txt','w',encoding='utf-8') as f:
f.write(title+'\n\n'+info+'\n\n')- 效果