{"adoption": {"forks": 101, "observed_at": "2026-08-28T04:04:13.373443+00:00", "stars": 1278}, "canonical_url": "https://ross.abutalabs.com/products/doc2text", "card": {"archived": false, "artifact_type": "library", "description": "Detect text blocks and OCR poorly scanned PDFs in bulk. Python module available via pip.", "domain": ["pdf", "computer-vision", "files"], "enriched": true, "function": ["ocr", "image-processing", "pdf", "parser", "computer-vision"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "experimental", "member_repos": ["jlsutherland/doc2text"], "name": "jlsutherland/doc2text", "platform": ["python", "cli"], "pushed_at": "2020-12-01T22:56:27+00:00", "repo": "jlsutherland/doc2text", "stars": 1278, "tags": ["ocr-preprocessing", "scanned-documents", "text-extraction", "bulk-processing", "tesseract", "natural-language-processing", "linux"], "topics": [], "urls": [], "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"], "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.", "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"], "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"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/doc2text", "repo": "jlsutherland/doc2text", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:13.373443+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:02:45.953645+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "475447980e1ad402cac986dc5701b1b64585e20a5445ad97b5ce0a9addf62811", "fetched_at": "2026-08-28T04:04:13.373443+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jlsutherland/doc2text"}, {"content_hash": "46580e577bef0e930bc51a309f8f58975b536cff76a059edf00e318f52c22a97", "fetched_at": "2026-08-29T12:13:30.980761+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/doc2text/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3657, "days_push": 2101, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}