在基于 aspx 的网站上使用 Python 请求进行身份验证

Question

我想从我们公司物流的基于 ASP 的运输页面中抓取数据。我在网上看了很多关于BeautifulSoup 和Requests 库的教程。但它并没有像我预期的那样工作。

登录网址为：

https://portal-vesta.sequoialog.com.br/tms/LoginPortal.aspx

我在 bash 脚本中编写了代码，我的登录尝试成功了，返回此消息：

69|dataItem||<script type="text/javascript">window.location="about:blank"</script>|32|pageRedirect||/tms/HomePortal.aspx?Usu=1070rpr|

但在 python 中，它返回给我这个消息：

b'69|dataItem||<script type="text/javascript">window.location="about:blank"</script>|21|pageRedirect||/TMS/LoginPortal.aspx|'

我的代码是：

with Session() as s:

        page = s.get(urls[0])

        get_ev_vs(page)

        payload = "Ajax=UpdatePanel1%7CButton1&Button1=ENTRAR&__ASYNCPOST=true&__EVENTARGUMENT=&__EVENTTARGET=&__EVENTVALIDATION={}&__LASTFOCUS=&__VIEWSTATE={}&txtSenha={}&txtUsuario={}&txtUsuarioSolicita=".format(ev, vs, password, user)
        head = {
            'sec-ch-ua': '" Not;A Brand";v="99", "Google Chrome";v="91", "Chromium";v="91"',
            'Cache-Control': 'no-cache',
            'X-MicrosoftAjax': 'Delta=true',
            'sec-ch-ua-mobile': '?0',
            'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36',
            'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
            'Accept': '*/*'
        }

        response = s.post(urls[0], data=payload, headers=head)

        payload = {}
        headers = {
          'sec-ch-ua': '"Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"',
          'sec-ch-ua-mobile': '?0',
          'Upgrade-Insecure-Requests': '1',
          'DNT': '1',
          'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.107 Safari/537.36',
          'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
          'Cookie': 'ASP.NET_SessionId=' + s.cookies["ASP.NET_SessionId"]
        }

        open_page = s.get(urls[1], data=payload, headers=headers)
        print(open_page.text)

def get_ev_vs(page):
    soup = BeautifulSoup(page.text, 'html.parser')
    global vs, ev
    vs = soup.select_one('#__VIEWSTATE')['value']
    ev = soup.select_one('#__EVENTVALIDATION')['value']

Answer 1

import requests
from bs4 import BeautifulSoup
import re
from urllib.parse import urljoin

target = ['__VIEWSTATE', '__EVENTVALIDATION']

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:91.0) Gecko/20100101 Firefox/91.0",
}


def main(url):
    with requests.Session() as req:
        req.headers.update(headers)
        r = req.get(url)
        soup = BeautifulSoup(r.text, 'lxml')
        values = [soup.select_one('#{}'.format(x))['value'] for x in target]
        data = {
            "Ajax": "UpdatePanel1|Button1",
            "__LASTFOCUS": "",
            "__EVENTTARGET": "",
            "__EVENTARGUMENT": "",
            "__VIEWSTATE": values[0],
            "__EVENTVALIDATION": values[1],
            "txtUsuario": "aaa",      #username should be here
            "txtSenha": "aaa",        #password too!
            "txtUsuarioSolicita": "",
            "__ASYNCPOST": "true",
            "Button1": "ENTRAR"
        }
        r = req.post(url, data=data)
        match = re.search(r'ScriptPath\|([^|]+db)\|', r.text).group(1)
        final = urljoin(url, match)
        r = req.get(final)
        print(r.text)


main('https://portal-vesta.sequoialog.com.br/tms/LoginPortal.aspx')