Native Python library that extracts text, formatted text, tables, images, metadata, hyperlinks and annotations from PDF, Word, Excel, PowerPoint, email, eBook, archive and image files, 65+ formats, on Windows, Linux, and macOS. No Microsoft Office or OpenOffice required....Markup (HTML, XHTML, MHTML, XML, MD) Images (JPG, JPEG, PNG, BMP...Integration The package ships an AGENTS.md reference for AI coding assistants...