{"adoption": {"forks": 249, "observed_at": "2026-08-28T04:09:02.280117+00:00", "stars": 4910}, "canonical_url": "https://ross.abutalabs.com/products/scraperr", "card": {"archived": true, "artifact_type": "application", "description": "Self-hosted webscraper.", "domain": ["web-development", "crawlers", "self-hosted"], "enriched": true, "function": ["web-scraping", "self-hosted", "gui", "data-visualization", "scheduling"], "health_score": 10, "homepage": "https://scraperr-docs.pages.dev/", "language": "TypeScript", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["jaypyles/Scraperr"], "name": "jaypyles/Scraperr", "platform": ["self-hosted", "python"], "pushed_at": "2025-10-12T16:55:31+00:00", "repo": "jaypyles/Scraperr", "stars": 4910, "tags": ["xpath", "playwright", "fastapi", "nextjs", "no-code-scraping", "helm", "data-export", "automation", "data-engineering", "docker", "kubernetes", "web-server"], "topics": ["opensource", "self-hosted", "webscraper", "docker", "helm", "kubernetes", "playwright", "python", "scraping", "web-scraper", "web-scrapers", "web-scraping", "webscraping"], "urls": [], "use_cases": ["scrape websites without writing code", "extract data from web pages using xpath", "crawl all pages within a domain", "download images and videos from scraped pages", "export scraped data to csv or markdown", "manage a queue of scraping jobs", "self-host a web scraper with docker"], "what_it_is": "Scraperr is a self-hosted web scraping application with a web UI that lets users scrape websites without writing code, using XPath-based extraction, job queues, and domain spidering. It is built with FastAPI, Playwright, and Next.js, and deploys via Docker or Helm.", "when_to_avoid": ["you need a programmatic scraping library to embed in your own code", "you require large-scale distributed crawling beyond a single self-hosted instance", "you need scraping of sites requiring complex authentication or heavy JavaScript interaction beyond Playwright defaults"], "when_to_choose": ["you want a no-code, self-hosted scraping tool with a UI", "you need XPath-based extraction and domain-wide spidering", "you want job queues, notifications, and CSV/markdown export out of the box", "you deploy with Docker or Kubernetes/Helm"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scraperr", "repo": "jaypyles/Scraperr", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:02.280117+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:18:04.550726+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "390f513825a1245eb64918e67181b17154e5f5a791052bb355476afcc02c6ab3", "fetched_at": "2026-08-28T04:09:02.280117+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jaypyles/Scraperr"}, {"content_hash": "a78105121c6a8cd601b53a0cc6629eb43eedad8d49e0a1916c95e5ad052f5e46", "fetched_at": "2026-08-29T09:00:28.422406+00:00", "kind": "homepage", "missing": false, "url": "https://scraperr-docs.pages.dev/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 46, "longevity": 56, "rhythm": 40}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 788, "days_push": 325, "days_rel": 416, "gap_med": 2, "n_releases_24m": 20}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}