Papercutter
Turn your PDF collection into a dataset you can actually use.
For researchers doing systematic reviews, meta-analyses, or literature surveys who have PDFs piling up but need structured data for analysis.
Requires Python 3.10+ and an OpenAI or Anthropic API key.
Installation
pip install papercutter[full]
Optional extras:
pip install papercutter[docling] # PDF processing only
pip install papercutter[llm] # LLM extraction only
pip install papercutter[report] # Report generation only
Usage
1. Ingest
Convert PDFs to Markdown and extract tables.
papercutter ingest ./pdfs/
Output: markdown/, tables/, figures/, inventory.json
2. Configure
Generate an extraction schema from paper abstracts.
papercutter configure
Output: columns.yaml
columns:
- key: sample_size
description: "Total observations (N)"
type: integer
- key: method
description: "Estimation strategy (DiD, RDD, OLS, etc.)"
type: string
- key: effect
description: "Main treatment coefficient"
type: float
3. Extract
Extract data from all papers using LLM.
papercutter extract
Output: extractions.json
4. Report
Generate analysis outputs.
papercutter report # matrix.csv + review.pdf
papercutter report --condensed # appendix format
Book Pipeline
Process books or handbooks with chapter-level summaries.
papercutter book index ./book.pdf # Detect chapters
papercutter book extract # Extract text
papercutter book summarize # Summarize chapters
papercutter book report # Generate PDF
Output: output/book_summary.pdf
Output Files
| File | Description |
|---|---|
inventory.json |
Processing status for each PDF |
columns.yaml |
Extraction schema definition |
extractions.json |
Extracted data per paper |
matrix.csv |
Flattened dataset for R/Stata/Python |
review.pdf |
LaTeX report with structured summaries |
License
MIT
Metadata
Release files for papercutter 3.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| papercutter-3.1.0.tar.gz | 258.8 kB | Without provenance | Details for papercutter-3.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| papercutter-3.1.0-py3-none-any.whl | Python 3 | none | any | Details for papercutter-3.1.0-py3-none-any.whl |
Total release size: 297.0 kB
Release files / papercutter-3.1.0.tar.gz
| Download URL | papercutter-3.1.0.tar.gz |
|---|---|
| Size | 258.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2ee877fa9ba6143ed6ff81bd774b8998d0c10127c7527140e631a302ef1f994a
|
|
BLAKE2b-256 checksum How to use checksums |
bed4144d65872f0d876bef68fc6db21133f8c7ea499476b3cd51e13fa9c9fc65
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.6
|
Release files / papercutter-3.1.0-py3-none-any.whl
| Download URL | papercutter-3.1.0-py3-none-any.whl |
|---|---|
| Size | 38.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
bdf0dc1d8fc17a13899d82290c674331a3e33ce2bce79a6990deca32646a97d8
|
|
BLAKE2b-256 checksum How to use checksums |
152853910dcf65426a9b2e9606d32a2fcc3bfac132cabb214c7e0df0ffc63390
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.6
|
Security for papercutter 3.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.