113 lines
4.2 KiB
Python
113 lines
4.2 KiB
Python
#!/scrapy/venvs/amznMailConverter/bin/python
|
|
|
|
import os
|
|
import base64
|
|
import requests
|
|
import logging
|
|
from urllib.parse import parse_qs, urlparse
|
|
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 bs4 import BeautifulSoup
|
|
|
|
# Configure logging
|
|
logging.basicConfig(level=logging.INFO)
|
|
|
|
SCOPES = ['https://www.googleapis.com/auth/gmail.readonly', 'https://www.googleapis.com/auth/gmail.modify']
|
|
SEARCH_QUERY = 'Amazon Kindle Support'
|
|
SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
|
|
def get_credentials():
|
|
creds = None
|
|
if os.path.exists(SCRIPT_DIR+'/token.json'):
|
|
creds = Credentials.from_authorized_user_file(SCRIPT_DIR+'/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(SCRIPT_DIR+'/credentials.json', SCOPES)
|
|
creds = flow.run_local_server(port=0)
|
|
with open(SCRIPT_DIR+'/token.json', 'w') as token:
|
|
token.write(creds.to_json())
|
|
return creds
|
|
|
|
def fetch_unread_messages(service, max_results=10):
|
|
try:
|
|
results = service.users().messages().list(userId='me', labelIds=['INBOX'], q="is:unread", maxResults=max_results).execute()
|
|
return results.get('messages', [])
|
|
except Exception as error:
|
|
logging.error(f"Error fetching unread messages: {error}")
|
|
return []
|
|
|
|
def download_pdf(pdf_link):
|
|
# Parse URL and get the actual file URL
|
|
parsed_url = urlparse(pdf_link)
|
|
query_params = parse_qs(parsed_url.query)
|
|
actual_file_url = query_params.get('U', [None])[0]
|
|
if not actual_file_url:
|
|
logging.error("No valid file URL found in PDF link.")
|
|
return
|
|
|
|
# Extract the file name
|
|
file_name = os.path.basename(urlparse(actual_file_url).path) or "downloaded_file.pdf"
|
|
data_dir = os.path.join(SCRIPT_DIR, "data")
|
|
file_path = os.path.join(data_dir, file_name)
|
|
|
|
# Check if file exists
|
|
if os.path.exists(file_path):
|
|
logging.info(f"{file_name} already exists. Skipping download.")
|
|
return
|
|
|
|
# Download and save the file
|
|
try:
|
|
response = requests.get(actual_file_url)
|
|
if response.status_code == 200:
|
|
os.makedirs(data_dir, exist_ok=True)
|
|
with open(file_path, "wb") as file:
|
|
file.write(response.content)
|
|
logging.info(f"File downloaded and saved to {file_path}")
|
|
else:
|
|
logging.error(f"Failed to download the file. Status code: {response.status_code}")
|
|
except Exception as e:
|
|
logging.error(f"An error occurred during file download: {e}")
|
|
|
|
def process_email(service, message):
|
|
try:
|
|
msg = service.users().messages().get(userId='me', id=message['id'], format='full').execute()
|
|
headers = msg['payload']['headers']
|
|
if any(SEARCH_QUERY in header.get('value', '') for header in headers if header['name'] == 'From'):
|
|
mail_body = ''
|
|
for part in msg.get('payload', {}).get('parts', []):
|
|
try:
|
|
data = part['body']["data"]
|
|
byte_code = base64.urlsafe_b64decode(data)
|
|
mail_body += byte_code.decode("utf-8")
|
|
except Exception:
|
|
continue
|
|
|
|
# Parse HTML and find the PDF link
|
|
soup = BeautifulSoup(mail_body, "html.parser")
|
|
link = soup.find("a", string="PDF herunterladen")
|
|
if link:
|
|
pdf_link = link.get("href")
|
|
download_pdf(pdf_link)
|
|
else:
|
|
logging.info("No 'PDF herunterladen' link found in this email.")
|
|
except Exception as error:
|
|
logging.error(f"An error occurred while processing email: {error}")
|
|
|
|
def read_emails():
|
|
creds = get_credentials()
|
|
service = build('gmail', 'v1', credentials=creds)
|
|
messages = fetch_unread_messages(service)
|
|
|
|
if not messages:
|
|
logging.info("No new messages.")
|
|
else:
|
|
for message in messages:
|
|
process_email(service, message)
|
|
|
|
if __name__ == "__main__":
|
|
read_emails()
|