{"adoption": {"forks": 112, "observed_at": "2026-08-28T04:03:26.780589+00:00", "stars": 1065}, "canonical_url": "https://ross.abutalabs.com/products/pdftotext", "card": {"archived": true, "artifact_type": "library", "description": null, "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 10, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["jalan/pdftotext"], "name": "jalan/pdftotext", "platform": ["python", "windows", "cross-platform"], "pushed_at": "2026-06-28T00:00:42+00:00", "repo": "jalan/pdftotext", "stars": 1065, "tags": ["pdf-text-extraction", "poppler", "python-binding", "linux", "macos"], "topics": [], "urls": [], "use_cases": ["extract text from pdf files in python", "parse pdf documents into plain text", "read individual pages from a pdf", "extract text from password-protected pdfs", "convert pdf content to strings for indexing"], "what_it_is": "pdftotext is a Python library for simple PDF text extraction, built as a binding around the Poppler C++ library. It supports reading text page-by-page or as a whole, including password-protected PDFs.", "when_to_avoid": ["you need layout-aware or structured PDF parsing", "you cannot install native C++ dependencies like poppler-cpp", "you need a project actively developed on GitHub (it has moved to SourceHut)"], "when_to_choose": ["you need fast, simple PDF text extraction in Python", "you can install native Poppler dependencies", "you want a minimal API for page-wise text access"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdftotext", "repo": "jalan/pdftotext", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:26.780589+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:55:30.091199+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "bdde0596b4af212f77cfc3c6912df1a0baf084b22a800eaf83998e91138bfd89", "fetched_at": "2026-08-28T04:03:26.780589+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jalan/pdftotext"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 89, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3421, "days_push": 67, "days_rel": 635, "gap_med": null, "n_releases_24m": 1}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}