Skip to main content

​
Input Formats

PyMuPDF4LLM can open and extract content from the following document types:
FormatExtensionsNotes
PDF.pdfAll versions, including encrypted and scanned
XPS.xpsMicrosoft XML Paper Specification
eBooks.epub, .mobi, .fb2Reflowable content is linearised per chapter
Comic Books.cbzImage-based pages; OCR recommended
Office Documents.doc, .docx, .ppt, .pptx, .xls, .xlsx, .hwp, .hwpxPyMuPDF Pro only — see below
Standard PyMuPDF4LLM supports PDF, XPS, eBooks, and CBZ out of the box. Office format support requires a PyMuPDF Pro licence.

​
Office Documents (Pro Only)

Processing Office files requires PyMuPDF Pro, which converts documents to PDF internally before extraction. This means all standard extraction options — layout analysis, OCR, page chunks — work identically on Office files. 
import pymupdf4llm

# Requires PyMuPDF Pro licence
md_text = pymupdf4llm.to_markdown("report.doc")

PyMuPDF Pro

Learn how to install and activate PyMuPDF Pro for Office document support.

​
Output Formats

PyMuPDF4LLM can produce output in four formats depending on your use case:
FormatFunctionBest For
Markdownto_markdown()LLM ingestion, RAG pipelines, readable docs
JSONto_json()Custom pipelines needing bounding boxes and layout data
Plain Textto_text()Simple text extraction, search indexing
Imagesto_markdown(write_images=True)Preserving figures, charts, and diagrams

​
Markdown

The default and most commonly used output format. Text is extracted in reading order with headings, lists, tables, and inline formatting preserved where detectable. 
md_text = pymupdf4llm.to_markdown("document.pdf")

​
JSON

Returns structured data including bounding boxes, font information, and layout metadata for every block on the page. Useful for building custom post-processing pipelines. 
json_output = pymupdf4llm.to_json("document.pdf")

​
Plain Text

Strips all formatting and returns raw text content. Ideal when downstream tools do not need Markdown syntax. 
text = pymupdf4llm.to_text("document.pdf")

​
Images

When write_images=True is passed to to_markdown(), embedded images and graphics are extracted and saved to disk. Image paths are referenced inline in the Markdown output. 
md_text = pymupdf4llm.to_markdown("document.pdf", write_images=True, image_path="images/")

​
Next Steps

Extract Markdown

Full walkthrough of to_markdown() with common options.

Images & Graphics

Controlling image extraction, DPI, and output path.

PyMuPDF Pro

Unlock Office document support with PyMuPDF Pro.