{"adoption": {"forks": 282, "observed_at": "2026-08-28T04:03:41.514790+00:00", "stars": 1127}, "canonical_url": "https://ross.abutalabs.com/products/boilerpipe", "card": {"archived": false, "artifact_type": "library", "description": "Work in progress transmit from Google Code", "domain": ["web-development", "crawlers"], "enriched": true, "function": ["nlp", "parser", "web-scraping"], "health_score": 20, "homepage": "https://code.google.com/p/boilerpipe/", "language": "Java", "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["kohlschutter/boilerpipe"], "name": "kohlschutter/boilerpipe", "platform": ["jvm", "cross-platform"], "pushed_at": "2018-01-03T21:47:34+00:00", "repo": "kohlschutter/boilerpipe", "stars": 1127, "tags": ["html-extraction", "boilerplate-removal", "content-extraction", "text-extraction", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["extract article text from html pages", "remove boilerplate from web pages", "get main content of a news article", "clean html for text mining", "extract fulltext from web documents for nlp"], "what_it_is": "boilerpipe is a Java library for removing boilerplate (ads, navigation, headers) from HTML pages and extracting the main full text content. It implements heuristic algorithms for article extraction from web pages.", "when_to_avoid": ["you need actively maintained software with recent fixes", "you need a non-JVM language without bindings", "you need modern JavaScript-rendered page extraction"], "when_to_choose": ["you need proven, fast boilerplate removal in a JVM application", "you are extracting article text from many web pages for analysis or indexing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/boilerpipe", "repo": "kohlschutter/boilerpipe", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:41.514790+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:38:48.229459+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "fa2fa2e41772c2e267ac148bc5dacc3651a38366d2fb5ebc55d685389472e3d0", "fetched_at": "2026-08-28T04:03:41.514790+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kohlschutter/boilerpipe"}, {"content_hash": "0a91afed6eaaeb655d51b1e2056e4cda57fd1b01464e8759bf5d285fd3ef6407", "fetched_at": "2026-08-29T12:43:19.168275+00:00", "kind": "homepage", "missing": false, "url": "https://code.google.com/p/boilerpipe/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4294, "days_push": 3164, "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}}