{"adoption": {"forks": 1279, "observed_at": "2026-08-28T04:07:53.493121+00:00", "stars": 3277}, "canonical_url": "https://ross.abutalabs.com/products/nutch", "card": {"archived": false, "artifact_type": "application", "description": "Apache Nutch is an extensible and scalable web crawler", "domain": ["crawlers", "big-data", "developer-tools"], "enriched": true, "function": ["web-scraping", "parser", "search-engine", "etl", "plugin-system"], "health_score": 80, "homepage": "https://nutch.apache.org/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["apache/nutch"], "name": "apache/nutch", "platform": ["jvm", "self-hosted"], "pushed_at": "2026-08-25T05:08:32+00:00", "repo": "apache/nutch", "stars": 3277, "tags": ["web-crawler", "hadoop", "apache", "batch-crawling", "tika", "solr", "elasticsearch", "search", "linux", "docker"], "topics": ["java", "nutch", "web-crawler", "crawling", "hadoop", "apache"], "urls": [], "use_cases": ["crawl large portions of the web for a search engine index", "batch-scrape millions of pages into Hadoop", "collect and parse web content for downstream data pipelines", "build a custom crawler with pluggable parsing and indexing", "feed documents into Solr or Elasticsearch from web sources"], "what_it_is": "Apache Nutch is a highly extensible and scalable open-source web crawler built on Apache Hadoop data structures. It supports batch crawling of large web volumes with a pluggable architecture for parsing (Tika) and indexing (Solr, Elasticsearch).", "when_to_avoid": ["you need a lightweight single-machine crawler for a few sites", "you need real-time or low-latency crawling", "you want a crawler with built-in authentication for its REST API (the legacy service has none)"], "when_to_choose": ["you need large-scale, Hadoop-based batch crawling", "you want a mature, production-ready crawler with plugin extensibility", "you need fine-grained control over parsing, filtering, scoring, and indexing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/nutch", "repo": "apache/nutch", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:53.493121+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:43:21.586570+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ab4abfe52a6e8c312c80c26a7989cb5554ee5d1d9491fcfcaff410e16cd9809d", "fetched_at": "2026-08-28T04:07:53.493121+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/nutch"}, {"content_hash": "3b433f1c896f6f13ade076a3026957f52a9ac1732cab443e06e64c4ff1e8b0c7", "fetched_at": "2026-08-29T09:36:10.169886+00:00", "kind": "homepage", "missing": false, "url": "https://nutch.apache.org/"}, {"content_hash": "f3d35b2f185f3e81365b867989c1e66a09f6718d6735cc876d1e342922fb868a", "fetched_at": "2026-08-29T09:36:10.180924+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation/security"}, {"content_hash": "b6909a976ae228808bda9b67c9d543febed8f147540633d9a8af7b539aa03e80", "fetched_at": "2026-08-29T09:36:10.182886+00:00", "kind": "site_page", "missing": false, "url": "https://nutch.apache.org/documentation"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "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": 6314, "days_push": 8, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}