{"adoption": {"forks": 779, "observed_at": "2026-08-28T04:08:35.660266+00:00", "stars": 4106}, "canonical_url": "https://ross.abutalabs.com/products/python-goose", "card": {"archived": false, "artifact_type": "library", "description": "Html Content / Article Extractor, web scrapping lib in Python", "domain": ["web-development", "crawlers"], "enriched": true, "function": ["web-scraping", "parser", "nlp"], "health_score": 63, "homepage": null, "language": "HTML", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["grangier/python-goose"], "name": "grangier/python-goose", "platform": ["python", "cross-platform"], "pushed_at": "2026-03-10T10:24:55+00:00", "repo": "grangier/python-goose", "stars": 4106, "tags": ["article-extraction", "html-parsing", "content-extraction", "readability", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["extract main article text from news pages", "get the top image from an article url", "scrape meta description and meta tags", "extract embedded youtube or vimeo videos from articles", "parse articles in multiple languages", "build a readability-style clean reader view"], "what_it_is": "Python-Goose is a Python library that extracts the main body text, metadata, top image, and embedded videos from news article web pages. It is a rewrite of the Java/Scala Goose article extractor with language-aware parsing.", "when_to_avoid": ["you need general-purpose web crawling or scraping of non-article pages", "you need a actively developed modern extractor with ongoing updates"], "when_to_choose": ["you need to extract clean article content and metadata from news-style pages in Python", "you want automatic main-image detection from articles"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/python-goose", "repo": "grangier/python-goose", "role": "main", "score": 64}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:35.660266+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:23:13.652931+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "64a6d29809b78c546eb8335432b84e872b5b688548d28a0a03ddb652e6716208", "fetched_at": "2026-08-28T04:08:35.660266+00:00", "kind": "readme", "missing": false, "url": "https://github.com/grangier/python-goose"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 71, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5351, "days_push": 176, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 64, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}