Created
April 26, 2023 14:39
-
-
Save tbbooher/aaad12a58395903158d6d95721a431f6 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 | |
import sys | |
import email | |
import datetime | |
import pytz | |
import base64 | |
import email | |
from weasyprint import HTML | |
from email import policy | |
from email.parser import BytesParser | |
from bs4 import BeautifulSoup | |
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 weasyprint | |
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly'] | |
def get_email_body(msg): | |
if 'payload' in msg: | |
payload = msg['payload'] | |
if 'parts' in payload: | |
parts = payload['parts'] | |
for part in parts: | |
if part['mimeType'] == 'text/html': | |
body_data = part['body']['data'] | |
break | |
else: | |
body_data = payload['body']['data'] | |
else: | |
body_data = msg['raw'].decode('utf-8') | |
body_data = base64.urlsafe_b64decode(body_data.encode('UTF-8')).decode('UTF-8') | |
soup = BeautifulSoup(body_data, 'html.parser') | |
return soup.prettify() | |
def get_subject(msg): | |
if 'payload' in msg: | |
headers = msg['payload']['headers'] | |
else: | |
headers = msg['headers'] | |
for header in headers: | |
if header['name'].lower() == 'subject': | |
return header['value'] | |
return None | |
def get_received_time(msg): | |
""" | |
Given a message, extract the received time from the headers | |
and return it as a datetime object with timezone info | |
""" | |
# Get the "internal date" field from the message (in UTC) | |
internal_date_str = msg.get('internalDate') | |
if internal_date_str is None: | |
raise ValueError("Message has no internalDate field") | |
internal_date = datetime.datetime.fromtimestamp(int(internal_date_str) / 1000, tz=datetime.timezone.utc) | |
# Get the timezone offset from the raw message data | |
headers = msg.get('payload', {}).get('headers', []) or msg.get('headers', []) | |
for header in headers: | |
if header['name'].lower() == 'date': | |
date_str = header['value'] | |
try: | |
date = datetime.datetime.strptime(date_str, '%a, %d %b %Y %H:%M:%S %z') | |
except ValueError: | |
date = datetime.datetime.strptime(date_str, '%a, %d %b %Y %H:%M:%S %z (UTC)') | |
return date.astimezone(internal_date.tzinfo) | |
# If no date header was found, just return the internal date | |
return internal_date | |
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='full').execute() | |
subject = get_subject(msg) | |
received_time = get_received_time(msg) | |
file_name = f"{subject}_{received_time.strftime('%Y%m%d_%H%M')}.pdf" | |
body = get_email_body(msg) | |
if body: | |
soup = BeautifulSoup(body, 'html.parser') | |
html = str(soup) | |
with open(file_name, 'wb') as f: | |
HTML(string=html).write_pdf(f) | |
print(f'Saved email {message["id"]} as {file_name}') | |
else: | |
print(f'Skipped email {message["id"]} because it has no HTML body') | |
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