使用 PyMuPDF 准备代理就绪的 PDF 和文档提取
Use PyMuPDF to extract text, layout metadata, tables, images, Markdown, or JSON from PDFs and documents before an agent ingests or reviews them.
Prerequisites
Python 3.10+, PyMuPDF, source PDFs or supported document files, and optional pymupdf4llm or Tesseract OCR for LLM-ready Markdown or scanned pages.
Installation
Use the upstream install or setup path that matches your environment:
- pip install pymupdf
- pip install pymupdf-fonts
- pip install pymupdf4llm
- pip install pymupdfpro
Requirements and caveats from upstream:
-
-
- [](https://demo.pymupdf.io?utm_source=github&utm_medium=referral&utm_campaign=pymupdf_github&utm_content=badges&utm_t...
Basic usage or getting-started notes:
- | Package | Purpose |
- |---|---|
- | pymupdf-fonts | Extended font collection for text output |
- Source: https://github.com/1991513ccie-png/skills
- Extracted from upstream docs: https://raw.githubusercontent.com/pymupdf/PyMuPDF/HEAD/README.md
Documentation
- https://pymupdf.readthedocs.io/