{"adoption": {"forks": 1041, "observed_at": "2026-08-28T04:09:53.429108+00:00", "stars": 7018}, "canonical_url": "https://ross.abutalabs.com/products/pdfminersix", "card": {"archived": false, "artifact_type": "library", "description": "Community maintained fork of pdfminer - we fathom PDF", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "developer-tools"], "health_score": 80, "homepage": "https://pdfminersix.readthedocs.io", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["pdfminer/pdfminer.six"], "name": "pdfminer/pdfminer.six", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-03-13T13:46:54+00:00", "repo": "pdfminer/pdfminer.six", "stars": 7018, "tags": ["text-extraction", "layout-analysis", "pdf-parsing", "text-mining", "cjk-support", "natural-language-processing"], "topics": ["pdf", "parser", "python"], "urls": [], "use_cases": ["extract text from pdf files in python", "parse resumes from pdfs", "get font and position information of pdf text", "convert pdf documents to html or hocr", "extract embedded images from pdfs", "handle cjk and vertical writing text in pdfs", "extract text from encrypted pdfs"], "what_it_is": "pdfminer.six is a community-maintained Python library for parsing and analyzing PDF documents, focused on extracting and analyzing text data including layout, fonts, and colors. It is written entirely in Python and offers both a Python API and a command-line tool (pdf2txt.py) for converting PDFs to text, HTML, or hOCR.", "when_to_avoid": ["you need to create or edit PDFs rather than read them", "you need fast OCR of scanned documents (it parses text, not images)", "you need high-performance processing of very large PDF volumes", "you need a maintained-by-vendor solution with guaranteed support"], "when_to_choose": ["you need detailed text and layout analysis of PDFs in pure Python", "you need font, color, or exact position metadata for extracted text", "you need CJK/vertical writing or various font type support", "you want a modular parser you can extend with custom interpreters"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdfminersix", "repo": "pdfminer/pdfminer.six", "role": "main", "score": 75}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:53.429108+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:40:38.628582+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "90b4ac4d2adc4a85d4e42ad76a02bc5b7cb658cc55a032a8ed235d9a9348d2bd", "fetched_at": "2026-08-28T04:09:53.429108+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pdfminer/pdfminer.six"}, {"content_hash": "404a37c3dbd18639e4cbf267480b46400f3954aab002f590b3cb8ad0d11c920e", "fetched_at": "2026-08-29T08:37:02.520888+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfminer.six/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 72, "longevity": 100, "rhythm": 65}, "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": 4387, "days_push": 173, "days_rel": 238, "gap_med": 7, "n_releases_24m": 10}, "score": 75, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}