{"adoption": {"forks": 311, "observed_at": "2026-08-28T04:04:58.409648+00:00", "stars": 1526}, "canonical_url": "https://ross.abutalabs.com/products/gravitylabs-goose", "card": {"archived": true, "artifact_type": "library", "description": "Html Content / Article Extractor in Scala - open sourced from Gravity Labs ", "domain": ["web-development", "crawlers"], "enriched": true, "function": ["parser", "web-scraping", "nlp"], "health_score": 10, "homepage": "http://gravity.com", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["GravityLabs/goose"], "name": "GravityLabs/goose", "platform": ["jvm", "cli"], "pushed_at": "2017-04-18T08:29:34+00:00", "repo": "GravityLabs/goose", "stars": 1526, "tags": ["article-extraction", "html-parsing", "content-extraction", "metadata-extraction", "readability", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["extract main article text from a news page url", "get the main image from an article for a preview card", "pull meta description and publish date from web pages", "build a read-it-later or feed reader app that shows article snippets", "extract embedded youtube/vimeo videos from articles"], "what_it_is": "Goose is a Scala library (originally Java) that extracts the main body text, metadata, publish date, embedded videos, and top image from news article web pages. It was open sourced by Gravity.com in 2011 for powering article-snippet apps like Flipboard/Pulse.", "when_to_avoid": ["you need an actively maintained extractor - the last release was 2017", "you are not on the JVM ecosystem", "you need modern web page handling for heavily JavaScript-rendered sites"], "when_to_choose": []}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gravitylabs-goose", "repo": "GravityLabs/goose", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:58.409648+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:31:35.580038+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9b6e1701ae33a216e127f33d254e986468924d3ae32962e44df0081853005a5f", "fetched_at": "2026-08-28T04:04:58.409648+00:00", "kind": "readme", "missing": false, "url": "https://github.com/GravityLabs/goose"}, {"content_hash": "05f39b2c0595c9b611410fb3db2dbb29dcdcfdc94bfe5e905dc271cb22b8cd59", "fetched_at": "2026-08-29T11:34:07.635564+00:00", "kind": "homepage", "missing": false, "url": "http://gravity.com"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5739, "days_push": 3424, "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}}