commit a0706c95c352087b67d452051ed916368b2910fe
Author: friedemann.blume <friedemann.blume@yukawa.de>
Date:   Fri Jul 19 12:44:15 2024 +0200

    init

diff --git a/.DS_Store b/.DS_Store
new file mode 100644
index 0000000..72b17cc
Binary files /dev/null and b/.DS_Store differ
diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..968e59d
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1 @@
+mbox-files/*
diff --git a/Dockerfile b/Dockerfile
new file mode 100644
index 0000000..27c86cf
--- /dev/null
+++ b/Dockerfile
@@ -0,0 +1,20 @@
+# Use the official Python image from the Docker Hub
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+# Create and set the working directory
+WORKDIR /app
+
+# Copy the Python script and any other necessary files into the container
+COPY mbox_to_markdown.py /app/
+COPY requirements.txt /app/
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Define the command to run the Python script
+CMD ["python", "mbox_to_markdown.py"]
+
diff --git a/Readme.md b/Readme.md
new file mode 100644
index 0000000..ac800ca
--- /dev/null
+++ b/Readme.md
@@ -0,0 +1,7 @@
+## Mbox to Markdown converter
+
+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/
+
+
diff --git a/mbox_to_markdown.py b/mbox_to_markdown.py
new file mode 100644
index 0000000..3db2446
--- /dev/null
+++ b/mbox_to_markdown.py
@@ -0,0 +1,31 @@
+import mailbox
+import os
+from markdownify import markdownify
+
+# Configuration
+mbox_file = 'path/to/your/file.mbox'
+output_dir = 'path/to/output/directory'
+
+# Ensure output directory exists
+os.makedirs(output_dir, exist_ok=True)
+
+def save_email_as_markdown(email, index):
+    subject = email.get('subject', 'No Subject')
+    date = email.get('date', 'No Date')
+    body = email.get_payload(decode=True).decode(errors='ignore')
+    body_markdown = markdownify(body)
+
+    # 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(body_markdown)
+
+def convert_mbox_to_markdown(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)
+
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..3fafbc9
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,2 @@
+mailbox
+markdownify