爬虫之自动登录

from lxml import etree
import requests
from bs4 import BeautifulSoup
il = requests.get('https://github.com/login')
soup = BeautifulSoup(il.text,features='html.parser')
tag = soup.find(name='input',attrs={'name':'authenticity_token'}) #找到input标签 跟token
authenticity_token = tag.get('value') #拿到token值
c1 = il.cookies.get_dict()#获取cookies
il.close()
from_data = {
'commit': 'Sign in',
'utf8': '✓',
'authenticity_token': authenticity_token,
'login':'247133278@qq.com',
'password':'67260767a',
'webauthn-support': 'supported'
}
i2 = requests.post('https://github.com/s ession',from_data,cookies=c1) #带着cookies再次去访问
c2 = i2.cookies.get_dict() #更新cookies
c1.update(c2)
i3  =  requests.get('https://github.com/',cookies=c1) #带着更新后的cookies去访问
soup3 = BeautifulSoup(i3.text,features='html.parser')
print(soup3)