v1

.gitignore

@@ -1 +1,5 @@
 mbox-files/*
+output
+output/*
+trash
+trash/*

Readme.md

@@ -1,7 +1,13 @@
 ## Mbox to Markdown converter
 
+This simple docker image can be used to convert a .mbox file (for example from a google gmail account export / take out) to convert it to markdown files.
+I used it for archive purposes, wanted to store my old gmail emails.
+Nothing fancy, but usefull for those who dont want to use online converters nor mess with python directly.
+
+## Usage:
+
+```
 docker build -t mbox-to-markdown .
 
-docker run --rm -v ./mbox-files:/mnt/input -v /path/to/output/directory:/mnt/output mbox-to-markdown python mbox_to_markdown.py /mnt/input/yourfile.mbox /mnt/output/
+docker run --rm -v ./mbox-files:/mnt/input -v ./output/:/mnt/output mbox-to-markdown
-
+```
-

mbox_to_markdown.py

@@ -1,31 +1,114 @@
 import mailbox
 import os
+import re
+import logging
+from datetime import datetime
+from email.utils import parsedate_tz, mktime_tz
 from markdownify import markdownify
+from watchdog.observers import Observer
+from watchdog.events import FileSystemEventHandler
+from tqdm import tqdm
 
 # Configuration
-mbox_file = 'path/to/your/file.mbox'
+input_dir = '/mnt/input'
-output_dir = 'path/to/output/directory'
+output_dir = '/mnt/output'
+
+# Setup logging
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__name__)
 
 # Ensure output directory exists
 os.makedirs(output_dir, exist_ok=True)
 
-def save_email_as_markdown(email, index):
+def sanitize_filename(filename):
+    """Sanitize the filename to remove invalid characters."""
+    return re.sub(r'[<>:"/\\|?*\x00-\x1F]', '', filename)
+
+def format_date(date_str):
+    """Format the date string to be suitable for filenames."""
+    try:
+        parsed_date = parsedate_tz(date_str)
+        if parsed_date is not None:
+            timestamp = mktime_tz(parsed_date)
+            formatted_date = datetime.fromtimestamp(timestamp).strftime('%Y-%m-%d_%H-%M-%S')
+            return formatted_date
+    except Exception as e:
+        logger.error(f"Error formatting date: {e}")
+    return 'NoDate'
+
+def save_email_as_markdown(email, index, output_subdir):
     subject = email.get('subject', 'No Subject')
     date = email.get('date', 'No Date')
-    body = email.get_payload(decode=True).decode(errors='ignore')
+    sender = email.get('from', 'Unknown Sender')
-    body_markdown = markdownify(body)
+    recipients = email.get('to', 'Unknown Recipient')
+
+    # Sanitize and format the filename
+    sanitized_subject = sanitize_filename(subject)
+    sanitized_sender = sanitize_filename(sender.split('<')[0].strip())
+    sanitized_recipients = sanitize_filename(recipients.split(',')[0].strip())
+    formatted_date = format_date(date)
+    filename = f"{sanitized_subject} - {sanitized_sender} - {sanitized_recipients} - {formatted_date}.md"
+    filename = os.path.join(output_subdir, filename)
+
+    # Handle potential None payload
+    payload = email.get_payload(decode=True)
+    if payload is None:
+        body_markdown = "No content available"
+    else:
+        try:
+            body = payload.decode(errors='ignore')
+            body_markdown = markdownify(body)
+        except (UnicodeDecodeError, AttributeError) as e:
+            body_markdown = f"Error decoding content: {e}"
 
     # Create a Markdown file for each email
-    filename = os.path.join(output_dir, f'email_{index}.md')
     with open(filename, 'w', encoding='utf-8') as file:
         file.write(f'# {subject}\n')
-        file.write(f'*Date: {date}*\n\n')
+        file.write(f'*Date: {date}*\n')
+        file.write(f'*From: {sender}*\n')
+        file.write(f'*To: {recipients}*\n\n')
         file.write(body_markdown)
 
+    logger.info(f"Saved email {index + 1} as Markdown: {filename}")
+
 def convert_mbox_to_markdown(mbox_file):
+    # Create a subdirectory in the output directory with the name of the .mbox file
+    base_name = os.path.basename(mbox_file)
+    subdir_name = os.path.splitext(base_name)[0]  # Remove the .mbox extension
+    output_subdir = os.path.join(output_dir, subdir_name)
+    os.makedirs(output_subdir, exist_ok=True)
+
+    logger.info(f"Processing .mbox file: {mbox_file}")
     mbox = mailbox.mbox(mbox_file)
-    for i, email in enumerate(mbox):
-        save_email_as_markdown(email, i)
 
-convert_mbox_to_markdown(mbox_file)
+    # Show progress bar
+    total_emails = len(mbox)
+    logger.info(f"Total emails to process: {total_emails}")
+
+    for i, email in tqdm(enumerate(mbox), total=total_emails, desc='Converting emails'):
+        save_email_as_markdown(email, i, output_subdir)
+
+class MboxFileHandler(FileSystemEventHandler):
+    def on_created(self, event):
+        if event.is_directory:
+            return
+        if event.src_path.endswith('.mbox'):
+            logger.info(f"New .mbox file detected: {event.src_path}")
+            convert_mbox_to_markdown(event.src_path)
+
+def start_watching():
+    event_handler = MboxFileHandler()
+    observer = Observer()
+    observer.schedule(event_handler, path=input_dir, recursive=False)
+    observer.start()
+    logger.info(f"Watching for new .mbox files in {input_dir}...")
+    try:
+        while True:
+            pass  # Keep the script running
+    except KeyboardInterrupt:
+        observer.stop()
+    observer.join()
+
+if __name__ == "__main__":
+    start_watching()
 

requirements.txt

@@ -1,2 +1,4 @@
 mailbox
 markdownify
+watchdog
+tqdm