made it simpler and to be run within a webserver on scrapy

Dockerfile

@@ -0,0 +1,21 @@
+# Use an official Python runtime as a base image
+FROM python:3.9
+
+# Set working directory in the container
+WORKDIR /app
+
+# Copy requirements file and install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code
+COPY . .
+
+# Expose the port for the PDF server
+EXPOSE 8000
+
+# Environment variables for Google API credentials
+ENV GOOGLE_APPLICATION_CREDENTIALS="/app/credentials.json"
+
+# Run the script as a daemon to check emails and download PDFs
+CMD ["python", "daemon.py"]

amznMailConverter.service

@@ -0,0 +1,13 @@
+
+[Unit]
+Description=Amazon Mail Converter Daemon
+
+[Service]
+ExecStart=/scrapy/venvs/amznMailConverter/bin/python3 /scrapy/amznMailConverter/daemon.py
+
+Restart=always
+User=root
+WorkingDirectory=/scrapy/amznMailConverter/
+
+[Install]
+WantedBy=multi-user.target

daemon.py

@@ -1,6 +1,10 @@
+#!/scrapy/venvs/amznMailConverter/bin/python
+
 import time
 import logging
-from amznMailConverter.email_pdf_downloader import read_emails
+import os
+from webSimple import generate_pdf_list_html
+from email_pdf_downloader import read_emails
 
 def run_daemon():
     while True:
@@ -9,6 +13,10 @@ def run_daemon():
             logging.info("Finished checking emails. Sleeping for 1 minutes.")
         except Exception as e:
             logging.error(f"An error occurred: {e}")
+
+        directory = '/scrapy/amznMailConverter/data'
+        output_file = os.path.join(directory, "/scrapy/amznMailConverter/index.html")
+        generate_pdf_list_html(directory, output_file)
         time.sleep(60)  # Sleep for 1 minute between checks
 
 if __name__ == "__main__":

daemon.service

@@ -1,11 +0,0 @@
-[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

email_pdf_downloader.py

@@ -1,3 +1,5 @@
+#!/scrapy/venvs/amznMailConverter/bin/python
+
 import os
 import base64
 import requests
@@ -18,15 +20,15 @@ SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
 
 def get_credentials():
     creds = None
-    if os.path.exists('token.json'):
+    if os.path.exists('/scrapy/amznMailConverter/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('/path/to/your/credentials.json', SCOPES)
+            flow = InstalledAppFlow.from_client_secrets_file('/scrapy/amznMailConverter/credentials.json', SCOPES)
             creds = flow.run_local_server(port=0)
-        with open('token.json', 'w') as token:
+        with open('/scrapy/amznMailConverter/token.json', 'w') as token:
             token.write(creds.to_json())
     return creds
 

pdf_server.py

@@ -1,3 +1,5 @@
+#!/scrapy/venvs/amznMailConverter/bin/python
+
 import os
 from http.server import HTTPServer, SimpleHTTPRequestHandler
 from io import BytesIO
@@ -75,6 +77,6 @@ class PDFServer:
 
 # Usage
 if __name__ == "__main__":
-    directory = '/home/maru/Dev/git/amznMailConverter/data/'
+    directory = '/scrapy/amznMailConverter/data'
     server = PDFServer(directory, port=8000)
     server.start_server()

requirements.txt

@@ -0,0 +1,7 @@
+google-auth
+google-auth-oauthlib
+google-auth-httplib2
+google-api-python-client
+requests
+beautifulsoup4
+python-daemon  # Only if using the daemon library

webSimple.py

@@ -0,0 +1,54 @@
+#!/scrapy/venvs/amznMailConverter/bin/python
+
+import os
+
+from datetime import datetime
+
+def generate_pdf_list_html(directory, output_file="pdf_list.html"):
+    """Generate an HTML file listing PDF files in the specified directory with the generation timestamp."""
+    try:
+        # Get a list of PDF files in the directory
+        file_list = [f for f in os.listdir(directory) if f.endswith('.pdf')]
+        file_list.sort(key=lambda a: a.lower())
+
+        # Get the current timestamp
+        generation_time = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+
+        # HTML content with dark and blue-themed Material Design styling
+        html_content = f'''<html>
+        <head>
+            <title>PDF Files</title>
+            <style>
+                body {{ font-family: Arial, sans-serif; background-color: #121212; color: #e0e0e0; display: flex; justify-content: center; align-items: center; height: 100vh; margin: 0; }}
+                .container {{ max-width: 600px; background: #1e1e1e; box-shadow: 0px 4px 8px rgba(0, 0, 0, 0.5); border-radius: 8px; padding: 20px; text-align: center; }}
+                h2 {{ color: #bb86fc; font-size: 24px; margin-bottom: 20px; }}
+                ul {{ list-style-type: none; padding: 0; }}
+                li {{ margin: 10px 0; }}
+                a {{ text-decoration: none; color: #03dac6; font-weight: bold; padding: 10px 15px; border-radius: 5px; transition: background-color 0.2s ease; }}
+                a:hover {{ background-color: #333; color: #bb86fc; }}
+                .footer {{ margin-top: 20px; font-size: 12px; color: #666; }}
+            </style>
+        </head>
+        <body>
+            <div class="container">
+                <h2>Available PDF Files for Download</h2>
+                <ul>'''
+        
+        for name in file_list:
+            html_content += f'<li><a href="data/{name}" download>{name}</a></li>'
+        
+        html_content += f'''</ul>
+                <div class="footer">Generated on: {generation_time}</div>
+            </div>
+        </body>
+        </html>'''
+
+        # Write the HTML content to the output file
+        with open(output_file, "w") as file:
+            file.write(html_content)
+        print(f"HTML file generated at: {os.path.abspath(output_file)}")
+
+    except Exception as e:
+        print(f"An error occurred: {e}")
+
+