ocr-and-documents

PyMuPDF extracts text from text-based PDFs, while marker-pdf handles OCR-enabled extraction from scanned documents. The skill applies these dependencies to capture text, tables, and layout structure, converting the output into structured Markdown.

Yes, the tool provides optional python-docx support for handling DOCX files alongside its primary PDF extraction capabilities. It applies OCR-enabled extraction and table capture to automate document processing workflows across multiple formats.

Yes, marker-pdf is required specifically for OCR-enabled extraction from scanned documents. The tool uses it to detect and capture document structure, extracting text and tables into Markdown output for automated document processing workflows.

Table detection works by capturing table structures during extraction and converting them directly into Markdown format. This enables easy integration of extracted tabular PDF data into dashboards and reports without manual data capture.

Yes, pymupdf is required to extract text and structure from text-based PDFs. For scanned documents requiring OCR, the skill additionally uses marker-pdf to ensure accurate text and table capture during markdown conversion.