{"adoption": {"forks": 496, "observed_at": "2026-08-28T04:08:07.532402+00:00", "stars": 3502}, "canonical_url": "https://ross.abutalabs.com/products/pdf2docx", "card": {"archived": false, "artifact_type": "library", "description": "Open source Python library for converting PDF to DOCX.", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 86, "homepage": "https://pdf2docx.readthedocs.io", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["ArtifexSoftware/pdf2docx"], "name": "ArtifexSoftware/pdf2docx", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2026-05-01T10:53:52+00:00", "repo": "ArtifexSoftware/pdf2docx", "stars": 3502, "tags": ["pdf-to-docx", "docx", "table-extraction", "pymupdf", "document-conversion"], "topics": ["pdf-converter", "docx", "pdf-to-word", "extract-table", "pymupdf"], "urls": [], "use_cases": ["convert pdf to word docx", "extract tables from pdf", "batch convert pdfs to editable documents", "convert pdf layout to docx preserving formatting", "turn scanned pdf pages into word files", "pdf to docx from the command line"], "what_it_is": "A Python library and CLI for converting PDF files into editable DOCX (Word) documents, with layout, text, and table extraction built on PyMuPDF. It is no longer actively maintained by Artifex but remains available under the MIT license for community use and forking.", "when_to_avoid": ["you need ongoing bug fixes or support for new PDF features", "you need general-purpose PDF processing beyond DOCX conversion (use PyMuPDF)", "you require guaranteed compatibility with the latest Python versions", "you need high-fidelity conversion of complex or heavily scanned PDFs"], "when_to_choose": ["you need a free, MIT-licensed PDF-to-DOCX converter in Python", "you want to extract tables from PDFs into editable Word format", "you need a simple CLI or GUI for one-off PDF conversions", "you're okay maintaining a fork yourself since the project is unmaintained"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf2docx", "repo": "ArtifexSoftware/pdf2docx", "role": "main", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:07.532402+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:35:47.361247+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "53e6f5a6e648ae8934567047b387f927a0656444e86410703d0212eabe0e288a", "fetched_at": "2026-08-28T04:08:07.532402+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArtifexSoftware/pdf2docx"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 80, "longevity": 100, "rhythm": 81}, "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": 2631, "days_push": 124, "days_rel": 124, "gap_med": 9.5, "n_releases_24m": 5}, "score": 84, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}