# jlsutherland/doc2text

Detect text blocks and OCR poorly scanned PDFs in bulk. Python module available via pip.

Repository: https://github.com/jlsutherland/doc2text
Canonical: https://ross.abutalabs.com/products/doc2text
Language: Python
License: MIT
License Family: permissive
Last push: 2020-12-01T22:56:27+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3657, "days_push": 2101, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1278, forks 101 (observed 2026-08-28T04:04:13.373443+00:00)

## What it is
doc2text is a Python library that extracts high-quality text from poorly scanned PDFs by correcting resolution, cropping, and skew before OCR. It uses OpenCV and tesseract to detect text blocks and process documents in bulk.

## Use cases
- extract text from poorly scanned pdfs
- ocr scanned documents in bulk
- fix skew and resolution before ocr
- build text corpora from pdf files
- detect text blocks in scanned images
- preprocess scans for tesseract

## When to choose
- you need to OCR low-quality or skewed scanned PDFs on Linux
- you want to build research text corpora from scanned documents
- you want automatic scan correction (crop, deskew, resolution) before OCR

## When to avoid
- you need multi-column or table extraction support
- you need cross-platform support beyond Ubuntu Linux
- you need a stable, actively maintained library
- you only need OCR of clean, high-quality PDFs

## Facets
- artifact type: library
- maturity: experimental
- function: ocr, image-processing, pdf, parser, computer-vision
- domain: pdf, computer-vision, files
- platform: python, cli
- tags: ocr-preprocessing, scanned-documents, text-extraction, bulk-processing, tesseract, natural-language-processing, linux

## Member repositories
- jlsutherland/doc2text (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:13.373443+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T05:02:45.953645+00:00, confidence not recorded.
  - readme: https://github.com/jlsutherland/doc2text (fetched 2026-08-28T04:04:13.373443+00:00, sha 475447980e1a)
  - registry_pypi: https://pypi.org/pypi/doc2text/json (fetched 2026-08-29T12:13:30.980761+00:00, sha 46580e577bef)
- Data as of 2026-08-30T08:39:29.467469+00:00.