Created
April 26, 2023 14:01
-
-
Save tbbooher/e00cd3ddc1d03462057400e7d59f67df to your computer and use it in GitHub Desktop.
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
from __future__ import print_function | |
import base64 | |
import os | |
import os.path | |
from google.auth.transport.requests import Request | |
from google.oauth2.credentials import Credentials | |
from google_auth_oauthlib.flow import InstalledAppFlow | |
from googleapiclient.discovery import build | |
from googleapiclient.errors import HttpError | |
import sys | |
import email | |
import datetime | |
import pytz | |
from email import policy | |
from email.parser import BytesParser | |
from bs4 import BeautifulSoup | |
from weasyprint import HTML | |
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly'] | |
def get_email_body(email_message): | |
if email_message.is_multipart(): | |
for part in email_message.walk(): | |
if part.get_content_type() == 'text/html': | |
return part.get_payload(decode=True) | |
else: | |
if email_message.get_content_type() == 'text/html': | |
return email_message.get_payload(decode=True) | |
return None | |
def main(): | |
creds = None | |
if os.path.exists('token.json'): | |
creds = Credentials.from_authorized_user_file('token.json', SCOPES) | |
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', SCOPES) | |
creds = flow.run_local_server(port=0) | |
with open('token.json', 'w') as token: | |
token.write(creds.to_json()) | |
try: | |
service = build('gmail', 'v1', credentials=creds) | |
query = 'from:"Uber Receipts"' | |
results = service.users().messages().list(userId='me', q=query, maxResults=10).execute() | |
messages = results.get('messages', []) | |
if not messages: | |
print('No messages found.') | |
return | |
for message in messages: | |
msg = service.users().messages().get(userId='me', id=message['id'], format='raw').execute() | |
msg_str = base64.urlsafe_b64decode(msg['raw'].encode('ASCII')) | |
email_message = BytesParser(policy=policy.default).parsebytes(msg_str) | |
email_body = get_email_body(email_message) | |
if email_body: | |
soup = BeautifulSoup(email_body, 'html.parser') | |
pdf_file_name = message['id'] | |
pdf_file_path = os.path.join('.', pdf_file_name+'.pdf') | |
subject = email_message['subject'] | |
received_time_str = email_message['Date'] | |
received_time = datetime.datetime.fromisoformat(received_time_str).replace(tzinfo=pytz.utc).astimezone(pytz.timezone('US/Pacific')) | |
received_time_str = received_time.strftime('%Y%m%d_%H%M') | |
pdf_file_path = os.path.join('.', received_time_str + '_' + subject + '.pdf') | |
HTML(string=str(soup)).write_pdf(pdf_file_path) | |
print(f"PDF file saved as {pdf_file_path}") | |
else: | |
print("No HTML content found in the email") | |
except HttpError as error: | |
print(f'An error occurred: {error}') | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment