爬取内容为百度百科,保存在同目录的1.html下,更改了headers作为隐藏
import requests
from bs4 import BeautifulSoup
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.169 Safari/537.36'
}
r = requests.get("https://baike.baidu.com/item/李隆基", headers=headers)
r.encoding = r.apparent_encoding
f1 = open("1.html", "w", encoding="UTF-8")
f1.write(r.text)
f1.close()