python爬虫豆瓣评论实验报告_豆瓣爬虫实践-python版

豆瓣登录，无验证码版：

import requests

#starturl = "/accounts/login"

loginurl = "/login"

headers = {User-Agent:Mozilla/5.0 (Windows NT 6.3; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.113 Safari/537.36,

Accept: ext/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,

}

fromdata ={source:None,

edir:/,

form_email:yourAccount,

form_password:password,

login:登录}

s = requests.Session()

s.headers.update(headers)

resp = s.post(loginurl,fromdata)

with open(douban.html,wb) as f:

f.write(resp.text.encode(utf-8))