爬虫标准框架

1
2
3
4
5
6
7
8
9
10
11
import requests
url="https://www.sogou.com/web?query=周杰伦"

headers={ "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/97.0.4692.71 Safari/537.36 Edg/97.0.1072.55" }
#以字典的形式设置请求头,处理反爬 resp=requests.get(url,headers=headers)
print(resp)
#结果:Response [200]
print(resp.text)
#拿到页面源代码
resp.close()
#关掉resp