document-processor - Extract text from PDF and DOCX files
Extract text from PDFs and DOCX files with OCR and page splitting
Tags
Updated: 2026-05-11Capabilities
Typical Inputs
Typical Outputs
What this skill does
- extract PDF content
- extract DOCX content
- perform OCR on scanned documents
- split large documents
- convert DOCX to markdown
- extract document metadata
- extract embedded images
Inputs
- PDF file
- DOCX file
- image-based PDF
Outputs
- extracted text
- markdown file
- JSON output
- extracted images
- document metadata
Requirements
- Python environment
- pypdf
- python-docx
- tesseract for OCR
- poppler for pdftotext