{"adoption": {"forks": 132, "observed_at": "2026-08-28T04:03:17.567107+00:00", "stars": 1029}, "canonical_url": "https://ross.abutalabs.com/products/pdf-to-text", "card": {"archived": false, "artifact_type": "library", "description": "Extract text from a pdf", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["pdf", "parser", "ocr"], "health_score": 87, "homepage": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf", "language": "PHP", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["spatie/pdf-to-text"], "name": "spatie/pdf-to-text", "platform": ["php", "windows", "cli"], "pushed_at": "2026-06-02T07:08:44+00:00", "repo": "spatie/pdf-to-text", "stars": 1029, "tags": ["pdftotext-wrapper", "text-extraction", "poppler", "spatie", "linux", "macos"], "topics": ["php", "text", "pdf", "pdf-converter"], "urls": [], "use_cases": ["extract text from pdf files in php", "parse pdf content into plain text", "convert pdf documents to text", "read text from pdfs in a laravel app", "index pdf documents for search", "pull text out of pdf invoices"], "what_it_is": "A PHP library that wraps the pdftotext binary to extract plain text from PDF files with a simple, fluent API. It requires the poppler-utils pdftotext executable to be installed on the system.", "when_to_avoid": ["you cannot install system-level binaries on your host", "you need layout, image, or table extraction rather than plain text", "you need OCR for scanned PDFs without a text layer"], "when_to_choose": ["you need simple text extraction from PDFs in PHP", "you can install system binaries like poppler-utils", "you want a minimal, well-maintained wrapper around pdftotext"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pdf-to-text", "repo": "spatie/pdf-to-text", "role": "main", "score": 67}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:17.567107+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:07:41.151329+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "04dd4a5388d34f2fbaaa78162e8d6f4ac0c0231617fc93622608dce8ec57451b", "fetched_at": "2026-08-28T04:03:17.567107+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/pdf-to-text"}, {"content_hash": "f4255c1afe6edeb9d54401782447ee97c04efe9d2499aae415440d46680edf44", "fetched_at": "2026-08-29T13:07:24.077692+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/348-a-package-to-extract-text-from-a-pdf"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T13:07:24.080284+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 85, "longevity": 100, "rhythm": 26}, "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": 3898, "days_push": 92, "days_rel": 282, "gap_med": 201.0, "n_releases_24m": 3}, "score": 67, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}