This commit is contained in:
t0is 2025-07-21 08:36:19 +02:00
parent 251721f23f
commit 684b0c841c
2 changed files with 29 additions and 7 deletions

View File

@ -1,5 +1,7 @@
services:
mail_czsk:
stdin_open: true
tty: true
image: t0is/vat-mail-loader:latest
container_name: mail_czsk
environment:
@ -15,6 +17,8 @@ services:
- ./data/czsk:/data
mail_rcw:
stdin_open: true
tty: true
image: t0is/vat-mail-loader:latest
container_name: mail_rcw
environment:
@ -27,6 +31,8 @@ services:
- ./data/rcw:/data
mail_rcw_offers:
stdin_open: true
tty: true
image: t0is/vat-mail-loader:latest
container_name: mail_rcw_offers
environment:

30
main.py
View File

@ -1,6 +1,6 @@
#!/usr/bin/env python3
"""
download_emails.py
download_emails
- Uses Gmail API to fetch all messages delivered to a single support address.
- Pulls configured Gmail signatures (in any language) via Settings API.
@ -19,8 +19,10 @@ import re
from datetime import datetime
from collections import defaultdict
import logging
import sys
from google.oauth2.credentials import Credentials
from google.auth.transport.requests import Request
from google_auth_oauthlib.flow import InstalledAppFlow
from googleapiclient.discovery import build
@ -58,16 +60,32 @@ NAME_PATTERNS = {
def get_gmail_service(token_path: str):
"""
Load OAuth client credentials and per-account token.
Load OAuth credentials and handle refreshing.
Performs interactive auth only when no valid token/refresh available.
"""
creds = None
# Load existing tokens
if os.path.exists(token_path):
creds = Credentials.from_authorized_user_file(token_path, SCOPES)
# Refresh if expired
if creds and creds.expired and creds.refresh_token:
logger.info("Refreshing access token using refresh token...")
creds.refresh(Request())
# If no valid credentials, do full auth flow
if not creds or not creds.valid:
flow = InstalledAppFlow.from_client_secrets_file('credentials.json', SCOPES)
creds = flow.run_local_server(port=0)
with open(token_path, 'w') as f:
f.write(creds.to_json())
auth_url, _ = flow.authorization_url(access_type='offline', prompt='consent')
logger.warning("Please open this URL in your browser:\n%s", auth_url)
sys.stdout.write("Enter the authorization code here: ")
sys.stdout.flush()
code = sys.stdin.readline().strip()
flow.fetch_token(code=code)
creds = flow.credentials
# Save for next time
with open(token_path, 'w') as token_file:
token_file.write(creds.to_json())
logger.info("Saved new token to %s", token_path)
# Build service
return build('gmail', 'v1', credentials=creds)
@ -116,13 +134,11 @@ def extract_author(body: str, signatures: list) -> str:
sig = s.get('signature')
if sig and sig in body:
return s['name']
# 2) Manual name patterns
for name, patterns in NAME_PATTERNS.items():
for pat in patterns:
if pat in body:
return name
# 3) Regex fallback
match = re.search(
r'(?im)(?:Podpis|S pozdravem|Díky|Thanks|Regards|Best regards|Sincerely)[\s,]*\r?\n([^\r\n]{2,})',