{"adoption": {"forks": 198, "observed_at": "2026-08-28T04:05:23.558149+00:00", "stars": 1694}, "canonical_url": "https://ross.abutalabs.com/products/dbashford-textract", "card": {"archived": false, "artifact_type": "library", "description": "node.js module for extracting text from html, pdf, doc, docx, xls, xlsx, csv, pptx, png, jpg, gif, rtf and more!", "domain": ["files", "pdf", "developer-tools"], "enriched": true, "function": ["ocr", "parser", "pdf", "nlp"], "health_score": 54, "homepage": null, "language": "HTML", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["dbashford/textract"], "name": "dbashford/textract", "platform": ["cross-platform"], "pushed_at": "2025-12-15T16:37:00+00:00", "repo": "dbashford/textract", "stars": 1694, "tags": ["text-extraction", "document-parsing", "mime-type", "office-documents", "tesseract", "natural-language-processing", "nodejs"], "topics": ["extract-text", "extraction", "nodejs"], "urls": [], "use_cases": ["extract text from pdf files in node", "parse text out of word documents", "convert docx to plain text", "ocr text from images png jpg", "extract text from excel spreadsheets", "index document contents for search", "pull text from pptx presentations"], "what_it_is": "A Node.js library that extracts plain text from many document formats including HTML, PDF, DOC/DOCX, XLS/XLSX, CSV, PPTX, RTF, EPUB, and images via OCR. It dispatches based on MIME type and shells out to external tools like pdftotext, antiword, and tesseract for some formats.", "when_to_avoid": ["you need structured data (tables, layout) rather than raw text", "you cannot install system-level external dependencies", "you need pure-JavaScript extraction with no native tool dependencies"], "when_to_choose": ["you need a single Node.js API for many document formats", "you are okay installing external binaries like pdftotext or tesseract", "you want simple text extraction rather than structured parsing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dbashford-textract", "repo": "dbashford/textract", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:23.558149+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:37:59.259201+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4273a397ad7191797ba0ba064a88857c6ca90924cbe163797b834e29569f8c7f", "fetched_at": "2026-08-28T04:05:23.558149+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dbashford/textract"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 57, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4880, "days_push": 261, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}