{"adoption": {"forks": 196, "observed_at": "2026-08-28T04:06:09.604936+00:00", "stars": 2052}, "canonical_url": "https://ross.abutalabs.com/products/gocrawl", "card": {"archived": false, "artifact_type": "library", "description": "Polite, slim and concurrent web crawler.", "domain": ["crawlers", "web-development", "developer-tools"], "enriched": true, "function": ["web-scraping", "http-client", "concurrency"], "health_score": 20, "homepage": null, "language": "Go", "license": "BSD-3-Clause", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["PuerkitoBio/gocrawl"], "name": "PuerkitoBio/gocrawl", "platform": ["go", "cross-platform"], "pushed_at": "2021-05-19T15:15:33+00:00", "repo": "PuerkitoBio/gocrawl", "stars": 2052, "tags": ["web-crawler", "robots-txt", "polite-crawling", "goquery"], "topics": ["crawler", "robots-txt"], "urls": [], "use_cases": ["crawl a website politely respecting robots.txt", "scrape pages from multiple hosts concurrently", "build a site indexer in Go", "extract data from web pages with per-host crawl delays", "harvest links from a domain with configurable user agent"], "what_it_is": "gocrawl is a polite, slim and concurrent web crawler library written in Go. It respects robots.txt rules, applies per-host crawl delays, and offers customizable hooks into the crawling logic via an Extender interface.", "when_to_avoid": ["you want a simpler, more idiomatic modern Go crawler (consider fetchbot)", "you need a full-featured scraping framework with JavaScript rendering", "you need a actively developed project with recent releases"], "when_to_choose": ["you need a Go crawler that obeys robots.txt and rate-limits per host", "you want fine-grained control over which URLs are visited via hooks", "you need concurrent crawling with goroutines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/gocrawl", "repo": "PuerkitoBio/gocrawl", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:09.604936+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:57:21.003955+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6f97adf5d7c019216655302504ae7912fa1dd0e55a8fb728efb076ca53a14c25", "fetched_at": "2026-08-28T04:06:09.604936+00:00", "kind": "readme", "missing": false, "url": "https://github.com/PuerkitoBio/gocrawl"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 5097, "days_push": 1932, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}