first working version

This commit is contained in:
Maciej L. 2025-03-02 15:21:31 +01:00
parent 4203b0baee
commit 6adbae4b57
Signed by: maciej
GPG key ID: 4B09FB92BF90A797
5 changed files with 76 additions and 0 deletions

4
.env.sample Normal file
View file

@ -0,0 +1,4 @@
IMAP_USER="user@example.com"
IMAP_PASSWORD="password"
IMAP_HOST="imap.example.com"
IMAP_PORT="993"

3
.gitignore vendored
View file

@ -172,3 +172,6 @@ cython_debug/
# PyPI configuration file
.pypirc
# main.py output file
out/

13
README.md Normal file
View file

@ -0,0 +1,13 @@
## zst-38-notatki
### What does this do?
This python script downloads messages from an IMAP server, blindly parses them trying to extract the shitty-formatted notes our teacher sends us, and then saves them as JSON to be served by a webserver.
### Setup
```bash
python3 -m venv venv
source venv/bin/activate
pip3 install -r requirements.txt
cp .env.sample .env
nano .env
python3 main.py
```

54
main.py
View file

@ -0,0 +1,54 @@
import json
import os
import imaplib
import email
from datetime import datetime
from dotenv import load_dotenv
from bs4 import BeautifulSoup
load_dotenv()
IMAP_USER = os.getenv("IMAP_USER")
IMAP_PASSWORD = os.getenv("IMAP_PASSWORD")
IMAP_HOST = os.getenv("IMAP_HOST")
IMAP_PORT = int(os.getenv("IMAP_PORT"))
emails = []
with imaplib.IMAP4_SSL(host=IMAP_HOST, port=IMAP_PORT) as imap_ssl:
resp_code, response = imap_ssl.login(IMAP_USER, IMAP_PASSWORD)
print(f'Login: {resp_code}')
resp_code, mail_count = imap_ssl.select(mailbox="INBOX", readonly=True)
print(f'Select: {resp_code}, found {mail_count[0].decode()} messages in INBOX')
resp_code, mail_ids = imap_ssl.search(None, "ALL")
print(f'Search: {resp_code}, IDs: {mail_ids[0].decode().split()}')
for mail_id in mail_ids[0].decode().split():
resp_code, mail_data = imap_ssl.fetch(mail_id, '(RFC822)')
message = email.message_from_bytes(mail_data[0][1])
for part in message.walk():
if part.get_content_type() == "text/html":
content = part.get_payload(decode=True).decode(part.get_content_charset())
soup = BeautifulSoup(content, 'html.parser')
text = soup.get_text()
partition = text.partition('\r\n\r\n')
guessed_topic = partition[0]
guessed_topic = guessed_topic.replace('\r\n', ' ')
guessed_topic = guessed_topic.replace('"', '')
guessed_topic = guessed_topic.replace(' ', ' ')
guessed_topic = guessed_topic.replace(' .', '.')
guessed_body = partition[2]
recv_date = message.get("Date")
parsed_date = datetime.strptime(recv_date, "%a, %d %b %Y %H:%M:%S %z")
iso_date = parsed_date.isoformat()
emails.append({"date": iso_date, "guessed_topic": guessed_topic, "guessed_body": guessed_body})
print(f'Parsed {mail_id}, received at {iso_date}, guessed topic: {guessed_topic}')
with open("out/output.json", "w", encoding="utf-8") as file:
json.dump(emails, file, ensure_ascii=False, indent=4)
print('Wrote to file :)')

2
requirements.txt Normal file
View file

@ -0,0 +1,2 @@
python-dotenv~=1.0.1
beautifulsoup4~=4.13.3