文档文字识别 · Doc-OCR

Turn PDFs, scans and photos into editable text with local macOS Vision OCR — nothing is uploaded.

PDF / 扫描件 / 图片 → 可编辑文字。有文字层的 PDF 直接抽取，扫描件走 macOS Vision 自带 OCR（中英文），文件不出本机。

Install

# 1) Agent Skills CLI (works with 50+ agent hosts)
npx skills add jiawood2006/doc-ocr

# 2) Claude Code / any host that reads ~/.claude/skills
git clone https://github.com/jiawood2006/doc-ocr.git ~/.claude/skills/doc-ocr

# 3) Hermes Agent
git clone https://github.com/jiawood2006/doc-ocr.git ~/.hermes/skills/utilities/doc-ocr

No build step, no account, no telemetry.

Usage

python3 scripts/dococr.py 合同.pdf                 # single file → text
python3 scripts/dococr.py 发票.jpg                 # image / scan
python3 scripts/dococr.py 书.pdf --md              # Markdown output
python3 scripts/dococr.py ./扫描件/ -o 全部.txt     # batch a folder

Ask your agent: "把这份扫描合同转成文字" and it runs the OCR for you.

Requirements

macOS (Vision framework) + Python 3.9+

pip3 install pymupdf pyobjc-framework-Vision

Notes

Text-layer PDFs are extracted directly (fast, exact); only scanned pages go through OCR. Chinese and English are handled out of the box.

License

MIT — see LICENSE. Issues and PRs welcome. Part of the hermes-skills collection.