{"adoption": {"forks": 699, "observed_at": "2026-08-28T04:10:00.153309+00:00", "stars": 7472}, "canonical_url": "https://ross.abutalabs.com/products/tabula", "card": {"archived": false, "artifact_type": "application", "description": "Tabula is a tool for liberating data tables trapped inside PDF files", "domain": ["pdf", "data-science", "files", "developer-tools"], "enriched": true, "function": ["pdf", "web-scraping", "data-science", "ocr"], "health_score": 27, "homepage": "http://tabula.technology", "language": "CSS", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["tabulapdf/tabula", "tabulapdf/tabula-java"], "name": "Tabula", "platform": ["windows", "cross-platform", "jvm"], "pushed_at": "2025-03-14T14:04:33+00:00", "repo": "tabulapdf/tabula", "stars": 7472, "tags": ["pdf-table-extraction", "csv-export", "excel-export", "local-web-interface", "tabula-java", "macos", "linux"], "topics": ["pdf", "csv", "excel", "tables", "scraping"], "urls": [{"kind": "homepage", "url": "http://tabula.technology"}], "use_cases": ["extract tables from pdf to csv", "convert pdf tables to excel spreadsheet", "scrape tabular data from pdf reports", "liberate data trapped in pdf files", "turn pdf financial reports into analyzable data", "extract tables from text-based pdfs for research"], "what_it_is": "Tabula is a local web application for extracting data tables from text-based PDF files into CSV, Excel, or JSON. It is powered by the tabula-java library and runs entirely on the user's machine.", "when_to_avoid": ["your PDFs are scanned images requiring OCR", "you need an actively developed end-user application (the GUI app sees few updates)", "you need complex layout understanding beyond simple tables"], "when_to_choose": ["you need tables out of text-based (not scanned) PDFs", "you want a free, offline tool that keeps documents private", "you prefer a visual interface for selecting table regions", "you want a scriptable Java library via tabula-java"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/tabulapdf/tabula", "repo": "tabulapdf/tabula", "role": "main", "score": 28}, {"path": "/repos/tabulapdf/tabula-java", "repo": "tabulapdf/tabula-java", "role": "backend", "score": 28}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:00.153309+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:37:37.162588+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "91c7cbfbd3db477a942497c94e2ddb32853fe117060a07526cbea2c64adff54f", "fetched_at": "2026-08-28T04:10:00.153309+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tabulapdf/tabula"}, {"content_hash": "98129a7c8c0b32e5e5982a6c5a86abb43f463e6677e1b9d55aa5d4d8148a925c", "fetched_at": "2026-08-29T08:32:53.464137+00:00", "kind": "homepage", "missing": false, "url": "http://tabula.technology"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 11, "longevity": 100, "rhythm": 8}, "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": 4923, "days_push": 537, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 28, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}