{"adoption": {"forks": 916, "observed_at": "2026-08-28T04:10:43.802302+00:00", "stars": 10697}, "canonical_url": "https://ross.abutalabs.com/products/pdfplumber", "card": {"archived": false, "artifact_type": "library", "description": "Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.", "domain": ["pdf", "files", "data-science", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "data-science", "cli"], "health_score": 97, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["jsvine/pdfplumber"], "name": "jsvine/pdfplumber", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-08-06T00:46:50+00:00", "repo": "jsvine/pdfplumber", "stars": 10697, "tags": ["pdf-parsing", "table-extraction", "pdfminer", "text-extraction", "visual-debugging"], "topics": ["pdf", "pdf-parsing", "table-extraction"], "urls": [], "use_cases": ["extract tables from pdf files", "parse text out of a pdf in python", "get character and line positions from a pdf", "convert pdf pages to csv or json", "debug pdf layout visually", "extract form values from pdfs"], "what_it_is": "pdfplumber is a Python library for extracting detailed information from PDFs, including every character, line, rectangle, and table, built on pdfminer.six. It also provides a command-line interface and visual debugging tools for inspecting PDF structure.", "when_to_avoid": ["your PDFs are scanned images requiring OCR", "you only need simple full-document text extraction with no layout detail", "you need a non-Python solution"], "when_to_choose": ["you need fine-grained access to PDF objects like chars, rects, and lines", "you want to extract tables from machine-generated PDFs", "you prefer a Python library with a CLI and visual debugging"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdfplumber", "repo": "jsvine/pdfplumber", "role": "main", "score": 90}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.802302+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:17:58.152128+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "21c16ca6ef7a44a9ea8f9f683b76335bc053b1fb0b9a07e937d46cfd1fc325f1", "fetched_at": "2026-08-28T04:10:43.802302+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jsvine/pdfplumber"}, {"content_hash": "4f88dca7af1cc6602792ab35686275616f649224a2b9c34da49d4c5b9c24cfe3", "fetched_at": "2026-08-29T08:17:04.779543+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfplumber/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 77}, "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": 4027, "days_push": 28, "days_rel": 79, "gap_med": 85, "n_releases_24m": 6}, "score": 90, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}