Python要求使用网站登录

Posted 2021-04-16

我似乎无法使用python requests.session（）函数登录我的大学网站。我已经尝试检索登录所需的所有标题和cookie但它没有使用我的凭据成功登录。它没有显示任何错误，但我应该登录后查看的源代码显示它仍然没有登录。我被告知我需要使用csrf cookie信息，但我似乎无法动态检索csrf cookie数据因为它在我尝试检索时引发KeyError，就像我检索其他2个cookie信息一样。请帮助别人。

我的所有代码都在下面。我用我的凭据填写登录名和密码，但其余的都是确切的代码。

import requests

with requests.session() as r:
    url = "https://www.ouac.on.ca/apply/nonsecondary/intl/en_CA/user/login"
    page = r.get(url)
    aspsessionid = r.cookies["ASPSESSIONID"]
    ouacapply1 = r.cookies["OUACApply1"]
    LOGIN = ""
    PASSWORD = ""
    submit = "Log In"
    login_data = dict(ASPSESSIONID=aspsessionid, OUACApply1=ouacapply1, login=LOGIN, password=PASSWORD, submitButton=submit)
    header = {"Referer":"https://www.ouac.on.ca/apply/nonsecondary/intl/en_CA/user/login", "User-Agent":"Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0"}
    logged_in = r.post(url, data=login_data, headers=header)
    new_page = r.get(url="https://www.ouac.on.ca/apply/nonsecondary/intl/en_CA/profile/")
    plain_text = new_page.text
    print(plain_text)

答案

我没有帐户，所以我无法测试它，但它可能是这样的。

import requests
import bs4
import webbrowser

def display(content):
    # to see this HTML in web browser
    with open('temp.html', 'wb') as f:
        f.write(content)
        webbrowser.open('temp.html')

with requests.session() as r:

    LOGIN = ""
    PASSWORD = ""

    login_url = "https://www.ouac.on.ca/apply/nonsecondary/intl/en_CA/user/login"
    profile_url="https://www.ouac.on.ca/apply/nonsecondary/intl/en_CA/profile/"

    # session need it only once and it will remember it
    r.headers.update({
        "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:57.0) Gecko/20100101 Firefox/57.0"
    })

    # load page with form - to get cookies and `csrf` from HTML
    response = r.get(login_url)

    #display(response.content)

    # get `csrf` from HTML
    soup = bs4.BeautifulSoup(response.text, 'html.parser')
    csrf = soup.find('input', {'name': 'csrf'}).attrs['value']

    print('csrf:', csrf)

    # cookies are not part of form so you don't use in form_data,
    # session will use cookies from previous request so you don't have to copy them
    form_data = {
        'login': LOGIN,
        'password': PASSWORD,
        'submitButton': "Log In",
        'csrf': csrf,
    }

    # send form data to server
    response = r.post(login_url, data=form_data)

    print('status_code:', response.status_code)
    print('history:', response.history)
    print('url:', response.url)

    #display(response.content)

    response = r.get(profile_url)

    display(response.content)