{"adoption": {"forks": 303, "observed_at": "2026-08-28T04:06:36.790630+00:00", "stars": 2315}, "canonical_url": "https://ross.abutalabs.com/products/tabula-py", "card": {"archived": false, "artifact_type": "library", "description": "Simple wrapper of tabula-java: extract table from PDF into pandas DataFrame", "domain": ["pdf", "data-science", "files", "developer-tools"], "enriched": true, "function": ["pdf", "parser", "data-science", "ocr"], "health_score": 29, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["chezou/tabula-py"], "name": "chezou/tabula-py", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2024-12-05T16:14:56+00:00", "repo": "chezou/tabula-py", "stars": 2315, "tags": ["pdf-table-extraction", "pandas", "tabula-java", "csv-conversion", "wrapper", "macos", "linux"], "topics": ["python", "pandas", "pdf", "tabula-java", "tabula"], "urls": [], "use_cases": ["extract tables from pdf into pandas dataframe", "convert pdf tables to csv", "scrape tabular data from pdf reports", "batch convert many pdfs to csv or", "read remote pdf files and parse their tables", "pull financial or research tables out of pdf documents"], "what_it_is": "tabula-py is a Python wrapper around tabula-java that extracts tables from PDF files into pandas DataFrames. It can also convert PDFs directly into CSV, TSV, or JSON files, including batch conversion of whole directories.", "when_to_avoid": ["you need to extract tables from scanned PDFs requiring OCR", "you cannot install or rely on a Java runtime", "you need pure-Python PDF parsing or deep control over PDF internals"], "when_to_choose": ["you need structured table data from text-based PDFs in a Python/pandas workflow", "you want simple PDF-to-CSV/TSV/JSON conversion with minimal code", "you're okay with a Java runtime dependency in exchange for tabula-java's mature extraction engine"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/tabula-py", "repo": "chezou/tabula-py", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:36.790630+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:39:25.158947+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8013d0be4e09b0f4beb4c5077eb671abbeca9040b9b2cd79b95be5c4746e3fde", "fetched_at": "2026-08-28T04:06:36.790630+00:00", "kind": "readme", "missing": false, "url": "https://github.com/chezou/tabula-py"}, {"content_hash": "1ad12dd858c55d07d72317236b17ff324b8604ca29ca8b6776fe7974377b6c9b", "fetched_at": "2026-08-29T10:19:18.665773+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/tabula-py/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3644, "days_push": 636, "days_rel": 685, "gap_med": null, "n_releases_24m": 1}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}