This repository has been archived on 2023-01-13. You can view files and clone it, but cannot push or open issues or pull requests.
uwm/main.py

70 lines
2.6 KiB
Python
Raw Normal View History

2021-05-24 22:22:03 +02:00
from sys import argv
2022-01-13 23:07:30 +01:00
from requests_html import BaseSession, HTMLResponse
from bs4 import BeautifulSoup # Peut-être retiré par les fonctions de requests_html ?
2021-05-24 22:22:03 +02:00
class Universite:
2022-01-13 23:07:30 +01:00
def __init__(self, url: str, pseudo: str, motDePasse: str):
2021-05-24 22:22:03 +02:00
self.url = url
self.loginData = {
"username": pseudo,
"password": motDePasse,
"_eventId": "submit",
"submit": "SE CONNECTER"
}
2022-01-13 21:23:22 +01:00
2022-01-13 23:07:30 +01:00
def maSoupe(self, page: HTMLResponse):
"""Macro pour utiliser le parser HTML de bs4."""
2021-05-24 22:22:03 +02:00
return BeautifulSoup(page.content, "html.parser")
2022-01-13 23:07:30 +01:00
def ecrirePageHTML(self, texte: str):
2022-01-13 22:52:32 +01:00
"""Affiche la page HTML pour le debug."""
2022-01-13 22:53:43 +01:00
with open("page.html", 'w') as f:
2022-01-13 22:52:32 +01:00
f.write(texte)
2021-05-25 00:25:59 +02:00
2022-01-13 23:07:30 +01:00
def recuperationNotes(self) -> str:
2022-01-13 22:52:32 +01:00
"""Récupère les notes."""
2022-01-13 23:07:30 +01:00
with BaseSession() as session:
2021-05-24 22:22:03 +02:00
# login
reponse = session.get(self.url)
2021-05-25 00:25:59 +02:00
soup = self.maSoupe(reponse)
2021-05-24 22:22:03 +02:00
self.loginData["lt"] = soup.find("input", attrs = {"name": "lt"})["value"]
self.loginData["execution"] = soup.find("input", attrs = {"name": "execution"})["value"]
reponse = session.post(self.url, data = self.loginData)
# page des résultats intermédiaire
2021-05-25 00:25:59 +02:00
soup = self.maSoupe(reponse)
try:
url = soup.find("a", attrs = {"id": "service-407"})["href"]
except:
raise TimeoutError("Le site a prit trop de temps pour répondre, veuillez réessayez plus tard.")
2021-05-24 22:22:03 +02:00
reponse = session.get(url, allow_redirects = False)
url = reponse.headers["Location"]
reponse = session.get(url)
2022-01-13 22:52:32 +01:00
# choix des années
2021-05-25 00:25:59 +02:00
soup = self.maSoupe(reponse)
2022-01-13 22:52:32 +01:00
url = f"{url}?{soup.find('form', attrs = {'enctype': 'application/x-www-form-urlencoded'})['action'].split('?')[1].replace('welcome', 'notes')}"
2021-05-24 22:22:03 +02:00
reponse = session.get(url)
2022-01-13 22:52:32 +01:00
self.ecrirePageHTML(reponse.text)
# page des notes
# TODO
2021-05-24 22:22:03 +02:00
2021-05-25 00:25:59 +02:00
# récupération tableaux des notes
soup = self.maSoupe(reponse)
for attrs in soup.findAll("table"):
try:
texte = str(attrs).split("thead")[1][2:-2]
2022-01-13 22:53:43 +01:00
while " " in texte:
texte = texte.replace(" ", ' ')
2021-05-25 00:25:59 +02:00
return texte
except:
pass
2021-05-24 22:22:03 +02:00
if __name__ == "__main__":
argv = argv[1:]
if len(argv) == 3:
print(Universite(*argv).recuperationNotes())
else:
print("Merci de renseigner l'URL, le pseudo et le mot de passe (avec des \").")