{"adoption": {"forks": 156, "observed_at": "2026-08-28T04:05:10.543299+00:00", "stars": 1607}, "canonical_url": "https://ross.abutalabs.com/products/grab-site", "card": {"archived": false, "artifact_type": "cli-tool", "description": "The archivist's web crawler: WARC output, dashboard for all crawls, dynamic ignore patterns", "domain": ["crawlers", "developer-tools", "self-hosted"], "enriched": true, "function": ["web-scraping", "cli", "monitoring", "analytics"], "health_score": 34, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["ArchiveTeam/grab-site"], "name": "ArchiveTeam/grab-site", "platform": ["windows", "python", "cli"], "pushed_at": "2025-05-23T09:57:06+00:00", "repo": "ArchiveTeam/grab-site", "stars": 1607, "tags": ["web-archiving", "warc", "crawler", "archiveteam", "backup", "dashboard", "linux", "macos"], "topics": ["archiving", "crawl", "spider", "crawler", "warc"], "urls": [], "use_cases": ["back up an entire website to WARC files", "crawl a site recursively for archiving", "monitor multiple crawls from a dashboard", "add ignore patterns to a running crawl to skip junk URLs", "archive large sites with millions of pages"], "what_it_is": "grab-site is a preconfigured web crawler for archiving websites, producing WARC files via a fork of wpull. It includes a dashboard for monitoring all crawls, dynamic ignore patterns, and duplicate page detection.", "when_to_avoid": ["you need a lightweight programmable scraping library rather than a full crawler", "you need a Python version other than 3.7/3.8 with pinned dependencies", "you need fine-grained custom crawl logic or API integration", "you only need to fetch a few pages rather than crawl a whole site"], "when_to_choose": ["you need WARC-standard web archives", "you want a preconfigured crawler with sensible defaults", "you need to adjust ignore rules mid-crawl", "you're doing web preservation or Archive Team-style archiving"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/grab-site", "repo": "ArchiveTeam/grab-site", "role": "main", "score": 43}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:10.543299+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:51:35.526991+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e0b209d3f11cb134fb5f2e85544826a3b38f309702819477cbf62ffe5ea8ca38", "fetched_at": "2026-08-28T04:05:10.543299+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ArchiveTeam/grab-site"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 23, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 4227, "days_push": 467, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 43, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}