{"adoption": {"forks": 260, "observed_at": "2026-08-28T04:06:21.815973+00:00", "stars": 2171}, "canonical_url": "https://ross.abutalabs.com/products/tesserocr", "card": {"archived": false, "artifact_type": "library", "description": "A Python wrapper for the tesseract-ocr API", "domain": ["computer-vision", "image-processing", "files"], "enriched": true, "function": ["ocr", "image-processing"], "health_score": 98, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["sirfz/tesserocr"], "name": "sirfz/tesserocr", "platform": ["windows", "python"], "pushed_at": "2026-08-04T12:28:33+00:00", "repo": "sirfz/tesserocr", "stars": 2171, "tags": ["tesseract", "cython", "pillow", "text-extraction", "linux", "macos"], "topics": ["optical-character-recognition", "ocr", "tesseract", "python-library", "cython"], "urls": [], "use_cases": ["extract text from images in python", "run ocr on scanned pdf pages", "recognize text in pillow images", "perform multithreaded ocr in python", "wrap tesseract without shelling out to the CLI"], "what_it_is": "A Python wrapper around the tesseract-ocr C++ API built with Cython for optical character recognition. It is Pillow-friendly, works with image files, and releases the GIL during processing to enable real concurrency with Python threads.", "when_to_avoid": ["you cannot install native libtesseract/libleptonica dependencies", "you need a pure-Python OCR solution", "you need OCR engines beyond tesseract"], "when_to_choose": ["you want fast, direct API access to tesseract from Python instead of subprocess calls", "you need concurrent OCR with real parallelism via threading", "your images are already loaded as Pillow Image objects"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tesserocr", "repo": "sirfz/tesserocr", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:21.815973+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:49:15.941817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e8a0e11814543c36aee59beda6680356b237bf80921b93b12615b46925a639d0", "fetched_at": "2026-08-28T04:06:21.815973+00:00", "kind": "readme", "missing": false, "url": "https://github.com/sirfz/tesserocr"}, {"content_hash": "2efeb463eb8c1107262069c106ddf3e4c287dc427bee41b978d4bf5ea6ee7422", "fetched_at": "2026-08-29T10:29:21.517604+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tesserocr/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 84}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3912, "days_push": 29, "days_rel": 29, "gap_med": 68, "n_releases_24m": 6}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}