python 爬取学信网登录页面的例子

import requestsfrom bs4 import BeautifulSoupfrom http import cookiesimport urllibimport http.cookiejarheaders = {  'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64; rv:54.0) Gecko/20100101 Firefox/54.0',  'Referer':'https://account.chsi.com.cn/passport/login?service=https://my.chsi.com.cn/archive/j_spring_cas_security_check',}session = requests.Session()session.headers.update(headers)username = 'xxx'password = 'xxx'url = 'https://account.chsi.com.cn/passport/login?service=https://my.chsi.com.cn/archive/j_spring_cas_security_check'def login(username,password,lt,_eventId='submit'):   #模拟登入函数  #构造表单数据  data = { #需要传去的数据      '_eventId':_eventId,      'lt':lt,      'password':password,       'submit':u'登录',      'username':username,   }  html = session.post(url,data=data,headers=headers)def get_lt(url):    #解析登入界面_eventId  html = session.get(url)  #获取 lt  soup = BeautifulSoup(html.text,'lxml',from_encoding="utf-8")  lt=soup.find('input',type="hidden")['value']  return ltlt = get_lt(url)#获取登录form表单信息 以学信网为例login(username,password,lt)login_url = 'https://my.chsi.com.cn/archive/gdjy/xj/show.action'per_html = session.get(login_url)soup = BeautifulSoup(per_html.text,'lxml',from_encoding="utf-8")print(soup)for tag in soup.find_all('table',class_='mb-table'):  print(tag)  for tag1 in tag.find_all('td'):    title= tag1.get_text();     print(title)