{"adoption": {"forks": 1159, "observed_at": "2026-08-28T04:11:17.103903+00:00", "stars": 16751}, "canonical_url": "https://ross.abutalabs.com/products/pdf-inspector", "card": {"archived": false, "artifact_type": "library", "description": "Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["parser", "pdf", "ocr", "markdown", "nlp"], "health_score": 99, "homepage": "https://firecrawl.github.io/pdf-inspector/", "language": "Rust", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["firecrawl/pdf-inspector"], "name": "firecrawl/pdf-inspector", "platform": ["rust", "python", "cli", "wasm", "browser", "cross-platform"], "pushed_at": "2026-08-21T23:46:04+00:00", "repo": "firecrawl/pdf-inspector", "stars": 16751, "tags": ["pdf-classification", "text-extraction", "ocr-routing", "pdf-to-markdown", "scanned-pdf-detection", "table-detection", "multi-column-layout", "firecrawl", "natural-language-processing", "nodejs"], "topics": ["markdown", "nodejs", "pdf", "pdf-extraction", "pdf-parser", "python", "rust", "text-extraction", "ocr-routing", "pdf-classification"], "urls": [], "use_cases": ["convert pdfs to markdown", "detect scanned vs text-based pdfs", "extract text from pdf files", "route pdfs to ocr only when needed", "extract tables from pdf documents", "parse multi-column pdf layouts", "run pdf parsing in the browser"], "what_it_is": "A fast Rust library for PDF inspection, classification, and text extraction that detects whether PDFs are text-based or scanned to enable smart OCR routing. It converts native-text PDFs to clean Markdown with position-aware extraction, table detection, and multi-column layout support, with bindings for Python, Node.js, CLI, and browser WebAssembly.", "when_to_avoid": ["your PDFs are primarily scanned images requiring full-document OCR", "you need model-based PDF parsing or visual layout understanding beyond heuristics", "you need form field extraction or PDF editing/manipulation"], "when_to_choose": ["you need fast classification and extraction of native-text PDFs without OCR overhead", "you want Markdown output with tables, headings, and reading-order reconstruction", "you need bindings across Rust, Python, Node.js, CLI, and WebAssembly", "you want to skip expensive OCR services for text-based PDFs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf-inspector", "repo": "firecrawl/pdf-inspector", "role": "main", "score": 81}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:17.103903+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:04:45.971295+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3249b79029e4f14952004a01b393ed39cfd3416a1db9c139f63100360053658f", "fetched_at": "2026-08-28T04:11:17.103903+00:00", "kind": "readme", "missing": false, "url": "https://github.com/firecrawl/pdf-inspector"}, {"content_hash": "71398f560c050072019f3852b8391ebb16bcd261af7bb11d10f4eb25d0132bd5", "fetched_at": "2026-08-29T08:01:53.563798+00:00", "kind": "homepage", "missing": false, "url": "https://firecrawl.github.io/pdf-inspector/"}, {"content_hash": "77107c3648f42e38b3da80f158f87191ad878514880be8ede387459fba892204", "fetched_at": "2026-08-29T08:01:53.566550+00:00", "kind": "registry_crates", "missing": false, "url": "https://crates.io/api/v1/crates/pdf-inspector"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 14, "rhythm": 98}, "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": 208, "days_push": 12, "days_rel": 16, "gap_med": 2.5, "n_releases_24m": 3}, "score": 81, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}