mCas.py

''' basic CAS authenticated page scraping using Requests and BeautifulSoup 
'''
__author__ = "swiatczak"

import requests
from bs4 import BeautifulSoup as soup
import urllib

def casSoup(user, password, serviceURL, casURL, targets = None):
    ''' somehow simplistic approach that authenticates requests against CAS using Requests.Session
        to persist cookies etc. And then sends to soup made of the content to a coroutine based 
        handlers.      
    '''
    with requests.Session() as sess:

        authResp = sess.get(serviceURL, verify = True)
        
        broth = soup(authResp.content, 'html.parser')
        ltParam = broth.form.find(name = 'input', attrs = {'name': 'lt'})['value']

        payload = { '_eventId': 'submit'
                  , 'execution': 'e1s1'
                  , 'submit': 'Login'
                  , 'username': user
                  , 'password': password
                  , 'lt': ltParam
                  }

        casResp = sess.post(casURL.format(urllib.quote(serviceURL)), data=payload, verify=True)
        broth2 = soup(casResp.content, 'html.parser')
        if targets is not None:
            for target in targets:
                target.send((broth2, sess.cookies))