papercutter 1.2.0

Extract and map content from academic papers for LLM processing

Papercutter

Extract knowledge from academic papers. A CLI-first Python package for researchers.

Installation

pip install papercutter

With LLM features (summarization, reports, study aids):

pip install papercutter[llm]

With fast PDF processing (PyMuPDF):

pip install papercutter[fast]

All optional dependencies:

pip install papercutter[all]

Development Installation

git clone https://github.com/rawatpranjal/papercutter.git
cd papercutter
pip install -e ".[dev]"

Quick Start

Fetch Papers

Download papers from various academic sources:

# From arXiv
papercutter fetch arxiv 2301.00001

# From DOI
papercutter fetch doi 10.1257/aer.20180779

# From SSRN
papercutter fetch ssrn 4123456

# From NBER
papercutter fetch nber w29000

# From direct URL
papercutter fetch url "https://example.com/paper.pdf" --name smith_2024

Extract Text

Extract clean text from PDFs:

# Full text to stdout
papercutter extract text paper.pdf

# Save to file
papercutter extract text paper.pdf --output paper.txt

# Chunk for LLM processing
papercutter extract text paper.pdf --chunk-size 4000 --overlap 200

# Extract specific pages
papercutter extract text paper.pdf --pages "1-10,15"

Extract Tables

Extract tables from PDFs as CSV or JSON:

# All tables to stdout as JSON
papercutter extract tables paper.pdf

# Save as CSV files
papercutter extract tables paper.pdf --output ./tables/ --format csv

# Extract from specific pages
papercutter extract tables paper.pdf --pages "5-10" --format json

Extract References

Extract bibliography as BibTeX:

# BibTeX to stdout
papercutter extract refs paper.pdf

# Save to file
papercutter extract refs paper.pdf --output refs.bib

# As JSON
papercutter extract refs paper.pdf --format json

Configuration

Papercutter stores configuration in ~/.papercutter/config.yaml:

output:
  directory: ~/papers

extraction:
  backend: pdfplumber
  text:
    chunk_size: null
    chunk_overlap: 200
  tables:
    format: csv

# LLM settings (v0.2)
llm:
  default_provider: anthropic
  default_model: claude-sonnet-4-20250514

Environment variables override config:

export PAPERCUTTER_ANTHROPIC_API_KEY=sk-ant-...
export PAPERCUTTER_OPENAI_API_KEY=sk-...

Migration from Papercut

Papercutter is a direct rename of the original Papercut project. To upgrade an existing installation:

1. Reinstall the package: pip uninstall papercut && pip install papercutter.
2. Update scripts and shell aliases to call papercutter instead of papercut.
3. Rename your config directory if you have custom settings: mv ~/.papercut ~/.papercutter.
4. (Optional) Rename the cache directory to retain cached artifacts: mv ~/.cache/papercut ~/.cache/papercutter.
5. Update any PAPERCUT_* environment variables to the new PAPERCUTTER_* prefix.

Development

Run tests:

pytest tests/

Run linting:

ruff check src/
mypy src/

License

MIT License - see LICENSE for details.