{"adoption": {"forks": 118, "observed_at": "2026-08-28T04:03:29.474765+00:00", "stars": 1076}, "canonical_url": "https://ross.abutalabs.com/products/metachris-pdfx", "card": {"archived": true, "artifact_type": "cli-tool", "description": "Extract text, metadata and references (pdf, url, doi, arxiv) from PDF. Optionally download all referenced PDFs.", "domain": ["pdf", "files", "developer-tools"], "enriched": true, "function": ["pdf", "parser", "web-scraping", "cli"], "health_score": 10, "homepage": "http://www.metachris.com/pdfx", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["metachris/pdfx"], "name": "metachris/pdfx", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2023-06-15T04:37:39+00:00", "repo": "metachris/pdfx", "stars": 1076, "tags": ["pdf-metadata", "reference-extraction", "doi", "arxiv", "link-checking", "command-line"], "topics": [], "urls": [], "use_cases": ["extract references from a research paper pdf", "download all cited pdfs from a paper", "extract metadata from a pdf file", "find broken links in a pdf document", "extract plain text from a pdf", "get doi and arxiv references from academic papers"], "what_it_is": "PDFx is a Python command-line tool and library that extracts metadata, text, and references (PDFs, URLs, DOIs, arXiv IDs) from PDF documents. It can also download all referenced PDFs in parallel and check for broken hyperlinks.", "when_to_avoid": ["you need OCR for scanned PDFs", "you need full-featured PDF manipulation like editing or form filling", "you need actively maintained software with recent updates"], "when_to_choose": ["you need to extract citations or hyperlinks from academic PDFs", "you want a simple CLI or Python API for PDF metadata and reference extraction", "you want to bulk-download papers referenced by a PDF"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/metachris-pdfx", "repo": "metachris/pdfx", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:29.474765+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:53:23.286472+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25088abc638b28efbd4f5f73dea72e6f9a74703601381939eba79b1cd70526f3", "fetched_at": "2026-08-28T04:03:29.474765+00:00", "kind": "readme", "missing": false, "url": "https://github.com/metachris/pdfx"}, {"content_hash": "ae3f2cfd180f4b524a1ceb85b814a8e993dc9e14f1c71d628d7a4700aec29f67", "fetched_at": "2026-08-29T12:55:08.701311+00:00", "kind": "homepage", "missing": false, "url": "http://www.metachris.com/pdfx"}, {"content_hash": "772897236c481b05512e2627787157dd4e56a060e5c74a6c51e072946a529dad", "fetched_at": "2026-08-29T12:55:08.704089+00:00", "kind": "site_page", "missing": false, "url": "https://www.metachris.dev/about"}, {"content_hash": "2db6566cc32e132d71e0f60ffb7b5a19bfa6cff3bd5a9faa953c4e6f1e1ba3bb", "fetched_at": "2026-08-29T12:55:08.705808+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/pdfx/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3975, "days_push": 1175, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}