{"adoption": {"forks": 367, "observed_at": "2026-08-28T04:07:24.296702+00:00", "stars": 2829}, "canonical_url": "https://ross.abutalabs.com/products/crawler", "card": {"archived": false, "artifact_type": "library", "description": "https://spatie.be/docs/crawler", "domain": ["crawlers", "web-development", "developer-tools"], "enriched": true, "function": ["web-scraping", "http-client", "concurrency"], "health_score": 98, "homepage": "https://freek.dev/308-building-a-crawler-in-php", "language": "PHP", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["spatie/crawler"], "name": "spatie/crawler", "platform": ["php", "cli"], "pushed_at": "2026-08-07T07:21:29+00:00", "repo": "spatie/crawler", "stars": 2829, "tags": ["crawler", "guzzle", "link-checking", "javascript-rendering", "puppeteer"], "topics": ["php", "crawler", "guzzle", "concurrency"], "urls": [], "use_cases": ["crawl all links on a website", "check for broken links on my site", "collect all internal URLs from a domain", "crawl JavaScript-rendered single-page apps", "scrape website pages concurrently in PHP"], "what_it_is": "A PHP library by Spatie for crawling links on websites, built on Guzzle promises for concurrent requests. It can execute JavaScript via Chrome and Puppeteer to crawl JavaScript-rendered sites.", "when_to_avoid": ["you need a full-scale distributed scraping system", "your stack is not PHP", "you only need a one-off CLI site audit without writing code"], "when_to_choose": ["you need a programmable web crawler in a PHP project", "you want concurrent crawling with configurable depth and crawl profiles", "you need to crawl sites that render content with JavaScript"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/crawler", "repo": "spatie/crawler", "role": "main", "score": 97}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:24.296702+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:38:11.759345+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "43361ac669e9e85346a2ec1980461e4a3e4c1ad1ef02742e465ce3df19db8b7d", "fetched_at": "2026-08-28T04:07:24.296702+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spatie/crawler"}, {"content_hash": "e89fc461fc36a0f449d7b7ee217eea3e12eab475a6bb90d9759bdbba950c7252", "fetched_at": "2026-08-29T09:53:21.915347+00:00", "kind": "homepage", "missing": false, "url": "https://freek.dev/308-building-a-crawler-in-php"}, {"content_hash": "e0ef9dccbb05c2ca499f33e17a37b8d295834eb41f7a6997f032841524bf0976", "fetched_at": "2026-08-29T09:53:21.925164+00:00", "kind": "site_page", "missing": false, "url": "https://freek.dev/about"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 96}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3957, "days_push": 26, "days_rel": 26, "gap_med": 16.5, "n_releases_24m": 21}, "score": 97, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}