Marker
介绍
Marker converts documents to markdown, JSON, chunks, and HTML quickly and accurately.
- Converts PDF, image, PPTX, DOCX, XLSX, HTML, EPUB files in all languages
- Formats tables, forms, equations, inline math, links, references, and code blocks
- Extracts and saves images
- Removes headers/footers/other artifacts
- Extensible with your own formatting and logic
- Does structured extraction, given a JSON schema (beta)
- Optionally boost accuracy with LLMs (and your own prompt)
- Works on GPU, CPU, or MPS
安装
You'll need python 3.10+ and PyTorch.
当前推荐使用 Python 3.12 (不用 3.14)
https://www.python.org/downloads/windows/
Install with:
pip install marker-pdf
If you want to use marker on documents other than PDFs, you will need to install additional dependencies with:
Get "Microsoft Visual C++ 14.0" or greater: https://learn.microsoft.com/en-us/cpp/windows/latest-supported-vc-redist?view=msvc-180#latest-supported-redistributable-version
Get "Microsoft C++ Build Tools": https://visualstudio.microsoft.com/visual-cpp-build-tools/
pip install marker-pdf[full]
单文件转换
marker_single /path/test_file.pdf
或
marker_single /path/test_file.docx
文件夹批量转换
marker /pathfolder
参考资料
https://github.com/datalab-to/marker