hancom-office
Read, fill, and edit Korean HWP (Hancom Office) documents in Python. Extract text for LLM / RAG pipelines, fill government & university forms programmatically, and rewrite the binary without corrupting it.
한컴오피스 문서를 위한 오픈소스 Python 파서 및 변환기 (hwp, hwpx, cell, and show). Extract HWPX to Markdown, JSON, and plain text for RAG, NLP, and document search.