first working version

.gitignore

@@ -175,3 +175,5 @@ cython_debug/
 *.vsix
 
 *.json
+*.pdf
+data/*

main.py

@@ -1,16 +1,22 @@
+from gettext import find
 import os.path
 import base64
 import json
 import re
 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
+
 
 SCOPES = ['https://www.googleapis.com/auth/gmail.readonly','https://www.googleapis.com/auth/gmail.modify']
+search = 'Amazon Kindle Support'
+script_dir = os.path.dirname(os.path.abspath(__file__))
 
 def readEmails():
     """Shows basic usage of the Gmail API.
@@ -29,7 +35,7 @@ def readEmails():
         else:
             flow = InstalledAppFlow.from_client_secrets_file(               
                 # your creds file here. Please create json file as here https://cloud.google.com/docs/authentication/getting-started
-                'my_cred_file.json', SCOPES)
+                '/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:
@@ -38,29 +44,73 @@ def readEmails():
         # Call the Gmail API
         service = build('gmail', 'v1', credentials=creds)
         results = service.users().messages().list(userId='me', labelIds=['INBOX'], q="is:unread").execute()
-        messages = results.get('messages',[]);
+        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']).execute()                
+                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")
-                                print ("This is the message: "+ str(text))
+                                        mail_body += str(text)
 
                                         # mark the message as read (optional)
-                                msg  = service.users().messages().modify(userId='me', id=message['id'], body={'removeLabelIds': ['UNREAD']}).execute()                                                       
+                                        #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}')
+
+
+readEmails()

web.py

@@ -75,6 +75,6 @@ class PDFServer:
 
 # Usage
 if __name__ == "__main__":
-    directory = '/path/to/your/directory'
+    directory = '/home/maru/Dev/git/amznMailConverter/data/'
     server = PDFServer(directory, port=8000)
     server.start_server()