-
-
Save a6kme/0786dc4e2445303e206b44f42aac36fa to your computer and use it in GitHub Desktop.
gmail-gpt-4
This file contains 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 os | |
import base64 | |
import io | |
from google.oauth2.credentials import Credentials | |
from google_auth_oauthlib.flow import InstalledAppFlow | |
from googleapiclient.discovery import build | |
from googleapiclient.errors import HttpError | |
from PyPDF2 import PdfReader, PdfWriter | |
from pypdfocr.pypdfocr_gs import PyGs | |
from pypdfocr.pypdfocr_tesseract import PyTesseract | |
# Set the destination folder and PDF password | |
destination_folder = "/path/to/destination/folder" | |
pdf_password = "your-pdf-password" | |
# Authenticate with the Gmail API | |
def authenticate(): | |
creds = None | |
if os.path.exists('token.pickle'): | |
with open('token.pickle', 'rb') as token: | |
creds = Credentials.from_authorized_user_file('token.pickle') | |
if not creds or not creds.valid: | |
if creds and creds.expired and creds.refresh_token: | |
creds.refresh(Request()) | |
else: | |
flow = InstalledAppFlow.from_client_secrets_file( | |
'credentials.json', ['https://www.googleapis.com/auth/gmail.readonly']) | |
creds = flow.run_local_server(port=0) | |
with open('token.pickle', 'wb') as token: | |
pickle.dump(creds, token) | |
return build('gmail', 'v1', credentials=creds) | |
# Download and decrypt the PDF attachments | |
def download_attachments(service, query): | |
result = service.users().messages().list(userId='me', q=query).execute() | |
messages = result.get('messages', []) | |
for message in messages: | |
msg = service.users().messages().get(userId='me', id=message['id'], format='full').execute() | |
payload = msg['payload'] | |
filename = None | |
for part in payload.get("parts"): | |
filename = part.get("filename") | |
file_data = part.get("body", {}).get("data") | |
if filename.endswith(".pdf") and file_data: | |
file_path = os.path.join(destination_folder, filename) | |
file_data = base64.urlsafe_b64decode(file_data) | |
decrypt_pdf(file_data, file_path, pdf_password) | |
def decrypt_pdf(file_data, file_path, password): | |
with io.BytesIO(file_data) as input_pdf: | |
reader = PdfReader(input_pdf, password=password) | |
writer = PdfWriter() | |
for page in reader.pages: | |
writer.add_page(page) | |
with open(file_path, "wb") as output_pdf: | |
writer.write(output_pdf) | |
if __name__ == '__main__': | |
try: | |
service = authenticate() | |
query = 'from:ebill@airtel.com after:2022-03-01 has:attachment' | |
download_attachments(service, query) | |
except HttpError as error: | |
print(f"An error occurred: {error}") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment