{"adoption": {"forks": 158, "observed_at": "2026-08-28T04:05:52.992087+00:00", "stars": 1909}, "canonical_url": "https://ross.abutalabs.com/products/article-extractor", "card": {"archived": false, "artifact_type": "library", "description": "To extract article from given URL", "domain": ["web-development", "crawlers"], "enriched": true, "function": ["web-scraping", "parser", "nlp"], "health_score": 99, "homepage": "https://extractus.pwshub.com/article", "language": "TypeScript", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["extractus/article-extractor"], "name": "extractus/article-extractor", "platform": ["bun", "cross-platform"], "pushed_at": "2026-08-20T08:55:35+00:00", "repo": "extractus/article-extractor", "stars": 1909, "tags": ["article-extraction", "readability", "content-extraction", "metadata", "typescript", "natural-language-processing", "nodejs", "deno"], "topics": ["article-parser", "readability", "article-extractor", "content-extraction", "data-extraction", "data-scraping", "javascript", "typescript"], "urls": [], "use_cases": ["extract article content from a url", "parse news articles to get title and main image", "get article metadata like author and publish date", "extract readable text from html pages", "build a read-it-later or rss reader app", "scrape blog post content for indexing"], "what_it_is": "A TypeScript library that extracts the main article content, title, image, and metadata from a given URL or raw HTML string. It supports custom transformations for specific sites and runs on Node.js, Deno, and Bun.", "when_to_avoid": ["you need a hosted extraction API with guaranteed uptime rather than a library", "you need to scrape non-article pages like product listings or dynamic apps", "your stack is not JavaScript/TypeScript"], "when_to_choose": ["you need to turn messy web pages into clean article data in JavaScript or TypeScript", "you want a lightweight, MIT-licensed extractor that works across Node.js, Deno, and Bun", "you need per-site transformations and content sanitization options"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/article-extractor", "repo": "extractus/article-extractor", "role": "main", "score": 98}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:52.992087+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:11:06.460016+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5df54f4679915a0790491c5b01bd90f655b8267b451d7c124e5eeea97eb1070d", "fetched_at": "2026-08-28T04:05:52.992087+00:00", "kind": "readme", "missing": false, "url": "https://github.com/extractus/article-extractor"}, {"content_hash": "ad28a8ce36167a2b657c571b92147bdb14e5f6ce32ee935643052471c935e4f0", "fetched_at": "2026-08-29T10:50:27.744458+00:00", "kind": "homepage", "missing": false, "url": "https://extractus.pwshub.com/article"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 100, "rhythm": 98}, "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": 3930, "days_push": 13, "days_rel": 13, "gap_med": 13.5, "n_releases_24m": 13}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}