{"adoption": {"forks": 108, "observed_at": "2026-08-28T04:05:09.280420+00:00", "stars": 1597}, "canonical_url": "https://ross.abutalabs.com/products/upton", "card": {"archived": false, "artifact_type": "framework", "description": "A batteries-included framework for easy web-scraping. Just add CSS! (Or do more.)", "domain": ["crawlers"], "enriched": true, "function": ["web-scraping", "parser"], "health_score": 20, "homepage": null, "language": "HTML", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["propublica/upton"], "name": "propublica/upton", "platform": ["ruby"], "pushed_at": "2018-12-26T02:48:38+00:00", "repo": "propublica/upton", "stars": 1597, "tags": ["scraping-framework", "nokogiri", "csv-export", "rate-limiting", "debug-stash", "data-engineering", "automation"], "topics": [], "urls": [], "use_cases": ["scrape a list of links from a website into a CSV", "extract structured data from paginated search result pages", "scrape tables or lists from news articles", "build a scraper that caches pages during development", "scrape a site politely with delays between requests", "scrape data from an API by overriding index fetching"], "what_it_is": "Upton is a Ruby framework that handles the repetitive parts of writing web scrapers, letting developers focus on site-specific CSS selectors or XPath expressions. It includes a debug stash mode that caches responses to avoid hammering target servers, plus built-in pagination and CSV export.", "when_to_avoid": ["you need a JavaScript-rendered (SPA) scraping solution", "you're not working in Ruby", "you need a maintained project - the last release was in 2018"], "when_to_choose": ["you're writing a Ruby scraper and want pagination, throttling, and caching handled for you", "you need to scrape index pages that link to instance pages", "you want a quick CSV output from a scraping project"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/upton", "repo": "propublica/upton", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:09.280420+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:54:00.662544+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "946347607d6f74357cae094dd4b3ff5b3792975a24ea0bed46d04c9dcef02604", "fetched_at": "2026-08-28T04:05:09.280420+00:00", "kind": "readme", "missing": false, "url": "https://github.com/propublica/upton"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "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": 4844, "days_push": 2807, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}