{"adoption": {"forks": 656, "observed_at": "2026-08-28T04:07:24.220921+00:00", "stars": 2827}, "canonical_url": "https://ross.abutalabs.com/products/anthelion", "card": {"archived": true, "artifact_type": "plugin", "description": "Anthelion is a plugin for Apache Nutch to crawl semantic annotations within HTML pages.", "domain": ["crawlers", "web-development"], "enriched": true, "function": ["web-scraping", "machine-learning", "parser", "search-engine", "nlp"], "health_score": 10, "homepage": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "abandoned", "member_repos": ["YahooArchive/anthelion"], "name": "YahooArchive/anthelion", "platform": ["jvm"], "pushed_at": "2015-12-17T07:21:20+00:00", "repo": "YahooArchive/anthelion", "stars": 2827, "tags": ["focused-crawling", "semantic-web", "apache-nutch", "microdata", "rdfa", "microformats", "online-learning", "structured-data-extraction", "search", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["crawl the web for pages with semantic annotations", "extract microdata and RDFa from HTML pages", "prioritize fetching structured-data-rich pages during a crawl", "build a search index of semantic triples", "run focused crawling with online learning feedback"], "what_it_is": "Anthelion is an Apache Nutch plugin for focused crawling of semantic data embedded in HTML pages. It uses an online learning classifier to prioritize data-rich pages and extracts Microdata, Microformats, and RDFa annotations via the any23 library.", "when_to_avoid": ["you need a maintained crawler or support for modern Nutch versions", "you want a standalone scraper without Nutch", "you need active community support - the project is archived and unmaintained"], "when_to_choose": ["you already run Apache Nutch 1.x and want to target semantic-data-rich pages", "you need to extract Microdata, Microformats, or RDFa during crawling"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/anthelion", "repo": "YahooArchive/anthelion", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.220921+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:38:12.649932+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "33a60028945955fc8cb6dab40b071707fab2a97dcb4251594a14cd1e13001607", "fetched_at": "2026-08-28T04:07:24.220921+00:00", "kind": "readme", "missing": false, "url": "https://github.com/YahooArchive/anthelion"}, {"content_hash": "017705c1b36a8363cf9e8f8fe01538e5cfcd57b289bd1b445795026020ccefba", "fetched_at": "2026-08-29T09:53:33.051979+00:00", "kind": "homepage", "missing": false, "url": "https://labs.yahoo.com/publications/6702/focused-crawling-structured-data"}, {"content_hash": "83c7a5ff14fa662c0415061ed09ca9db0e456eefdbbc6796233d8b4a9cfcfed0", "fetched_at": "2026-08-29T09:53:33.061225+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search/sln2244.html"}, {"content_hash": "13dfe80ed99318a16c3cfbbc09fe3d2c4316eecd89e375fdc1c460f4baa170a3", "fetched_at": "2026-08-29T09:53:33.063198+00:00", "kind": "site_page", "missing": false, "url": "https://help.yahoo.com/kb/search-for-desktop/SLN2206.html?impressions=true"}], "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": 3964, "days_push": 3912, "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}}