Created
October 11, 2020 16:42
-
-
Save takidog/5c29852a9e277cd6d720aadea9eac4d4 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import hashlib | |
from lxml import etree | |
HOST = "https://sso.wzu.edu.tw" | |
CAPTCHA_DICT = { | |
"9bcd5ab8fc729c83bdbbc784e3002d2f": "3", | |
"543cd21e5aaa43d056d8068654c54b9a": "4", | |
"5b24f8c135fee3ae3b14a1b9d0594704": "5", | |
"2e81195ea486bd3704e94d8738cce591": "6", | |
"88a220af9e880ed9089f64067a09e9b3": "7", | |
"961ad1052e35d01d1a0cafc0917183a9": "8", | |
"ed6b4795dd09ba4aab1d728657ac825a": "a", | |
"ada5aca56c49ebdd600af0e74f1b91fd": "d", | |
"f2a05ef72e154278ab4e6665d5200458": "e", | |
"9f729a736e3590d919d52ae4c6bc2346": "f", | |
"51203198720eb3c05e5acf73f209c285": "h", | |
"969f09793ed0900a9d86768f013446c5": "i", | |
"4d12aa55f5402f24a86cf848ccbdaad7": "m", | |
"a41049298340e857d905972dca4d4732": "n", | |
"de5ad6fec2d3e65cabdc79077aff44fd": "r", | |
"9197aa82ba8921840737c118d1a12f79": "t" | |
} | |
def get_md5(data: bytes): | |
md5_object = hashlib.md5() | |
md5_object.update(data) | |
return md5_object.hexdigest() | |
def get_captcha_text(session: requests.session, login_page_html: str): | |
# parse image url | |
root = etree.HTML(login_page_html) | |
single_captcha_text_dom = root.xpath( | |
'//span[@id="table1"]/img[@border="0"]') | |
result = "" | |
for i in single_captcha_text_dom: | |
# get image file on single session | |
image_request = session.get(f"{HOST}{i.get('src')}") | |
result += CAPTCHA_DICT[get_md5(image_request.content)] | |
return result | |
def login(session: requests.session, username: str, password: str) -> bool: | |
login_page_url = f'{HOST}/Portal/login.htm' | |
login_page_request = session.get(url=login_page_url) | |
if login_page_request.status_code != 200: | |
return False | |
# get captcha text part | |
form_captcha_text = get_captcha_text(session=session, | |
login_page_html=login_page_request.text) | |
# print(captcha_text) | |
# get SYSTEM_MAGICNUMBER | |
root = etree.HTML(login_page_request.text) | |
form_system_magicnumber = root.xpath( | |
'//input[@name="SYSTEM_MAGICNUMBER"]')[0].get('value') | |
# login request | |
login_request = session.post(url=f'{HOST}/Portal/loginprocess', | |
data={ | |
'USERID': username, | |
'PASSWD': password, | |
'SYSTEM_MAGICNUMBERTEXT': form_captcha_text, | |
'SYSTEM_MAGICNUMBER': form_system_magicnumber | |
}, | |
allow_redirects=False) | |
if login_request.status_code == 302: | |
return True | |
return False | |
if __name__ == "__main__": | |
# session | |
session = requests.session() | |
login_request_status = login(session=session, | |
username='', | |
password='') | |
print("login status: ", login_request_status) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment