code improvements

daemon.py

@@ -0,0 +1,15 @@
+import time
+import logging
+from main import read_emails
+
+def run_daemon():
+    while True:
+        try:
+            read_emails()
+            logging.info("Finished checking emails. Sleeping for 1 minutes.")
+        except Exception as e:
+            logging.error(f"An error occurred: {e}")
+        time.sleep(60)  # Sleep for 1 minute between checks
+
+if __name__ == "__main__":
+    run_daemon()

daemon.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Amazon Mail Converter Daemon
+
+[Service]
+ExecStart=/usr/bin/python3 /path/to/your_script.py
+Restart=always
+User=your_username
+WorkingDirectory=/path/to/your_script.py
+
+[Install]
+WantedBy=multi-user.target

main.py

@@ -1,116 +1,110 @@
-from gettext import find
+import os
-import os.path
 import base64
-import json
+import requests
-import re
+import logging
-import time
 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
-import logging
-import requests
 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']
+SCOPES = ['https://www.googleapis.com/auth/gmail.readonly', 'https://www.googleapis.com/auth/gmail.modify']
-search = 'Amazon Kindle Support'
+SEARCH_QUERY = 'Amazon Kindle Support'
-script_dir = os.path.dirname(os.path.abspath(__file__))
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
 
-def readEmails():
+def get_credentials():
-    """Shows basic usage of the Gmail API.
-    Lists the user's Gmail labels.
-    """
     creds = None
-    # The file token.json stores the user's access and refresh tokens, and is
-    # created automatically when the authorization flow completes for the first
-    # time.
     if os.path.exists('token.json'):
         creds = Credentials.from_authorized_user_file('token.json', SCOPES)
-    # If there are no (valid) credentials available, let the user log in.
     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(               
+            flow = InstalledAppFlow.from_client_secrets_file('/path/to/your/credentials.json', SCOPES)
-                # your creds file here. Please create json file as here https://cloud.google.com/docs/authentication/getting-started
-                '/home/maru/Dev/git/amznMailConverter/my_cred_file.json', SCOPES)
             creds = flow.run_local_server(port=0)
-        # Save the credentials for the next run
         with open('token.json', 'w') as token:
             token.write(creds.to_json())
+    return creds
+
+def fetch_unread_messages(service, max_results=10):
     try:
-        # Call the Gmail API
+        results = service.users().messages().list(userId='me', labelIds=['INBOX'], q="is:unread", maxResults=max_results).execute()
-        service = build('gmail', 'v1', credentials=creds)
+        return results.get('messages', [])
-        results = service.users().messages().list(userId='me', labelIds=['INBOX'], q="is:unread").execute()
-        messages = results.get('messages',[])
-        if not messages:
-            print('No new messages.')
-        else:
-            message_count = 0
-            for message in messages:
-                msg = service.users().messages().get(userId='me', id=message['id'], format='full').execute()                
-                email_data = msg['payload']['headers']
-
-                for values in email_data:
-                    name = values['name']
-                    if name == 'From':
-                        from_name= values['value'] 
-                        #print(f'{search} - {from_name}')
-                        if from_name.find(search) != -1:
-                            if 'payload' in msg and 'parts' in msg['payload']:   
-                                mail_body = ''         
-                                for part in msg['payload']['parts']:
-                                    try:
-                                        data = part['body']["data"]
-                                        byte_code = base64.urlsafe_b64decode(data)
-
-                                        text = byte_code.decode("utf-8")
-                                        mail_body += str(text)
-
-                                        # mark the message as read (optional)
-                                        #msg  = service.users().messages().modify(userId='me', id=message['id'], body={'removeLabelIds': ['UNREAD']}).execute()                                                       
-                                    except BaseException as error:
-                                        pass   
-                                # Parse the HTML with BeautifulSoup
-                                soup = BeautifulSoup(mail_body, "html.parser")
-
-                                # Find the "PDF herunterladen" link
-                                link = soup.find("a", string="PDF herunterladen")
-
-                                # Extract the href attribute
-                                if link:
-                                    pdf_link = link.get("href")
-                                        # Download the PDF file
-                                    response = requests.get(pdf_link)
-
-                                    # Parse the URL to extract 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]  # 'U' is the parameter holding the actual file URL
-
-                                    # Extract the file name from the actual file URL
-                                    file_name = os.path.basename(urlparse(actual_file_url).path) if actual_file_url else "downloaded_file.pdf"
-
-                                    
-                                    if response.status_code == 200:
-                                        # Define the file path for saving
-                                        data_dir = os.path.join(script_dir, "data")
-                                        file_path = os.path.join(data_dir, file_name)
-                                        
-                                        # Save the file
-                                        with open(file_path, "wb") as file:
-                                            file.write(response.content)
-                                        
-                                        print(f"File downloaded and saved to {file_path}")
-                                    else:
-                                        print("Failed to download the file. Status code:", response.status_code)
-
-                            else:
-                                pass # print(msg['payload']['body'])                   
     except Exception as error:
-        print(f'An error occurred: {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
 
-readEmails()
+    # 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()

web.service

@@ -0,0 +1,11 @@
+[Unit]
+Description=Amazon Mail Converter Daemon
+
+[Service]
+ExecStart=/usr/bin/python3 /path/to/your_script.py
+Restart=always
+User=your_username
+WorkingDirectory=/path/to/your_script.py
+
+[Install]
+WantedBy=multi-user.target