python 爬取學(xué)信網(wǎng)登錄頁(yè)面的例子

import requests
from bs4 import BeautifulSoup
from http import cookies
import urllib
import http.cookiejar

headers = {
  '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'):   #模擬登入函數(shù)
  #構(gòu)造表單數(shù)據(jù)
  data = { #需要傳去的數(shù)據(jù)
      '_eventId':_eventId,
      'lt':lt,
      'password':password, 
      'submit':u'登錄',
      '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)
  #獲取 lt
  soup = BeautifulSoup(html.text,'lxml',from_encoding="utf-8")
  lt=soup.find('input',type="hidden")['value']
  return lt

lt = get_lt(url)#獲取登錄form表單信息 以學(xué)信網(wǎng)為例
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)