markitdown-automatico

This project is a Windows setup guide and automation wrapper for MarkItDown, a Microsoft tool that converts office documents and PDFs into Markdown text files. The README itself is written in Spanish and walks a reader through the entire process step by step, from checking that Python and pip are installed, to creating a virtual environment, to installing MarkItDown with pip.

Once MarkItDown itself is set up, this project adds its own layer on top: a Python script that watches a folder, converts every supported file inside it such as PDF, Word, Excel, PowerPoint, CSV, JSON, XML, and HTML files into Markdown, and saves the results into a separate output folder while keeping the original file names. A special case is handled for older Excel .xlsm files, which get quietly converted to the newer .xlsx format first so that MarkItDown can read them properly.

To make running this even easier, the project includes a small Windows batch file that starts the Python script using the virtual environment automatically, so a user does not need to remember or type activation commands each time. The everyday workflow described is simple: drop files into an input folder, double click the batch file, and collect the converted Markdown files from an output folder.

The README also notes that Excel conversions can sometimes show a warning related to a library called openpyxl about data validation rules, but clarifies that this is usually harmless and the file still converts successfully.

This is a personal convenience project built by one developer to make an existing Microsoft tool easier to use repeatedly on Windows, rather than a new tool built from scratch. It is released under the MIT license.