Magic-PDF is a tool designed to convert PDF documents into Markdown format, capable of processing files stored locally or on object storage supporting S3 protocol.

Key features include:

Support for multiple front-end model inputs
Removal of headers, footers, footnotes, and page numbers
Human-readable layout formatting
Retains the original document's structure and formatting, including headings, paragraphs, lists, and more
Extraction and display of images and tables within markdown
Conversion of equations into LaTeX format
Automatic detection and conversion of garbled PDFs
Compatibility with CPU and GPU environments
Available for Windows, Linux, and macOS platforms

Project Panorama

Flowchart

Submodule Repositories

Getting Started

Requirements

Python 3.9 or newer

Usage Instructions

1. Install Magic-PDF

pip install magic-pdf

2. Usage via Command Line

simple

cp magic-pdf.template.json to ~/magic-pdf.json
magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"

magic-pdf --help

3. Usage via Api

Local

image_writer = DiskReaderWriter(local_image_dir)
image_dir = str(os.path.basename(local_image_dir))
jso_useful_key = {"_pdf_type": "", "model_list": model_json}
pipe = UNIPipe(pdf_bytes, jso_useful_key, image_writer)
pipe.pipe_classify()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")

Object Storage

s3pdf_cli = S3ReaderWriter(pdf_ak, pdf_sk, pdf_endpoint)
image_dir = "s3://img_bucket/"
s3image_cli = S3ReaderWriter(img_ak, img_sk, img_endpoint, parent_path=image_dir)
pdf_bytes = s3pdf_cli.read(s3_pdf_path, mode=s3pdf_cli.MODE_BIN)
jso_useful_key = {"_pdf_type": "", "model_list": model_json}
pipe = UNIPipe(pdf_bytes, jso_useful_key, s3image_cli)
pipe.pipe_classify()
pipe.pipe_parse()
md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")

Demo can be referred to demo.py

All Thanks To Our Contributors

License Information

See LICENSE.md for details.

README.md

Magic-PDF

Introduction