Django Projects as PyPI Packages

You're right that Django typically focuses on reusable apps rather than distributing complete projects as packages. Based on the Django documentation, the framework is designed with reusability in mind, but this is usually at the app level rather than the project level.

Django's Approach to Reusability

Django emphasizes creating reusable components (apps) that can be composed into larger projects. As the documentation states:

Reusability is the way of life in Python. The Python Package Index (PyPI) has a vast range of packages you can use in your own Python programs. Check out Django Packages for existing reusable apps you could incorporate in your project.

The standard approach for packaging Django apps involves:

1. Creating a proper package structure
2. Including a license file
3. Setting up a pyproject.toml file
4. Creating a MANIFEST.in file to include templates and static files
5. Building and distributing the package

Packaging Complete Projects

While Django doesn't provide specific guidance for packaging entire projects, your approach of bundling a library with a minimal Django project is innovative. The Django documentation doesn't explicitly discourage this approach, but it's less common in the ecosystem.

For distributing complete Django projects, you have several options:

1. Package it on PyPI as you've done
2. Share it directly via email or your website
3. Post it on a public repository

Third-Party Distributions

It's worth noting that there are third-party distributors who package Django in various ways:

Many third-party distributors are now providing versions of Django integrated with their package-management systems. These can make installation and upgrading much easier for users of Django since the integration includes the ability to automatically install dependencies.

Your project with Granian as a production-ready server alternative seems to follow this spirit of making Django more accessible for specific use cases.

While I don't have specific examples of complete Django projects on PyPI to share from the documentation, your approach with carbon-txt-validator appears to be a practical solution for your specific needs, leveraging Django's strengths while packaging it in a more convenient way for your users.