通过 Python 请求访问 Moodle

问：

你好，stackoverflowers，

我目前正在编写一个 python 脚本，该脚本应该从 Moodle 的课程中下载反馈文件，

脚本可以成功登录 moodle。但是对于每个 GET 请求，它都会将我重定向到未请求的某个页面。

import time
import requests
import configparser
import bs4


moodle_url = "https://moodle.uni-bielefeld.de/"


def login(session, id, password):

    def get_relay_state_saml(html):
        soup = bs4.BeautifulSoup(html, features="html.parser")
        divs = soup.findAll("div")
        divs = divs[0]
        relay_tag = divs.contents[1]
        saml_tag = divs.contents[3]
        relay_value = relay_tag['value']
        saml_value = saml_tag['value']
        return {'RelayState': str(relay_value), 'SAMLResponse': str(saml_value)}

    response = session.get('https://moodle.uni-bielefeld.de/auth/shibboleth/index.php')

    # select university
    payload_select = {
        'user_idp': 'https://shibboleth.uni-bielefeld.de/idp/shibboleth',
        'Select': 'Select'
    }
    # redirect to login page
    response_select = session.post(response.url, data=payload_select)
    # print(response_select.text)
    # login form
    payload_login = {
        'j_username': id,
        'j_password': password,
        '_eventId_proceed': ''
    }

    response_login = session.post(response_select.url, data=payload_login)
    # print(response_login.url)
    # print(response_login.text)

    payload_accept = {
        '_shib_idp_consentIds': 'givenname',
        '_eventId_proceed': 'Accept'
    }

    response_logged = session.post(response_login.url, data=payload_accept)
    # print(response_logged.url)
    # print(response_logged.text)
    # print(get_relay_state_saml(response_logged.text))

    payload_saml = get_relay_state_saml(response_logged.text)
    # print(payload_saml)

    response_moodle = session.post("https://moodle.uni-bielefeld.de/Shibboleth.sso/SAML2/POST", data=payload_saml)
    # print(response_moodle.url)
    # print(response_moodle.text)


def check_for_new_feedback(session):

    def get_uebungsblatter(html):
        soup = bs4.BeautifulSoup(html, features="html.parser")

        # print(soup)
        blaetter = []
        # retrieve all
        return blaetter
    # this is the part where i always get redirected to the profile editing page
    response = session.get(moodle_url)

    blaetter = get_uebungsblatter(response.text)


def scraper():
    config = configparser.ConfigParser()
    config.read('config.ini')
    student_id = config['config']['student_id']
    password = config['config']['password']
    mail = config['config']['mail']
    last_sent = int(config['config']['last_sent'])
    wait_between_calls = int(config['config']['wait_between_calls'])

    with requests.session() as session:
        login(session, student_id, password)
        while True:
            check_for_new_feedback(session)
            time.sleep(60*wait_between_calls)


if __name__ == '__main__':
    scraper()

经过一些研究和逆向工程，我发现通过使用浏览器单击某个课程，它会发送一个 GET 请求，其中包含带有课程 ID 的正确链接。 不久之后。它向此 URL 发送 POST 请求

https://moodle.uni-bielefeld.de/lib/ajax/service.php?sesskey=PWSjDeVJNC&info=core_courseformat_get_state

给定此有效载荷

[{"index":0,"methodname":"core_courseformat_get_state","args":{"courseid":2891}}]

我试图发送这些请求以访问我想要的页面，但它一直将我重定向到该页面。

如果有人能够提供帮助或至少了解这里发生的事情并告诉我代码出了什么问题，我很乐意收到您的来信。

非常感谢，

另一个堆叠花