{"adoption": {"forks": 1643, "observed_at": "2026-08-28T04:11:38.215786+00:00", "stars": 25516}, "canonical_url": "https://ross.abutalabs.com/products/crawlee", "card": {"archived": false, "artifact_type": "library", "description": "Crawlee—A web scraping and browser automation library for Node.js to build reliable crawlers. In JavaScript and TypeScript. Extract data for AI, LLMs, RAG, or GPTs. Download HTML, PDF, JPG, PNG, and other files from websites. Works with Puppeteer, Playwright, Cheerio, JSDOM, and raw HTTP. Both headful and headless mode. With proxy rotation.", "domain": ["crawlers", "web-development", "developer-tools", "artificial-intelligence"], "enriched": true, "function": ["web-scraping", "http-client", "browser-extension", "proxy", "file-upload"], "health_score": 100, "homepage": "https://crawlee.dev", "language": "TypeScript", "license": "Apache-2.0", "license_family": "permissive", "maturity": "stable", "member_repos": ["apify/crawlee", "apify/crawlee-python"], "name": "Crawlee", "platform": ["cross-platform"], "pushed_at": "2026-08-26T20:43:47+00:00", "repo": "apify/crawlee", "stars": 25516, "tags": ["puppeteer", "playwright", "cheerio", "headless-browser", "proxy-rotation", "typescript", "crawler", "data-extraction", "llm-data", "automation", "nodejs", "docker"], "topics": ["web-scraping", "web-crawling", "npm", "headless-chrome", "puppeteer", "automation", "apify", "scraping", "crawling", "crawler", "headless", "scraper", "web-crawler", "javascript", "nodejs", "playwright", "typescript"], "urls": [{"kind": "homepage", "url": "https://crawlee.dev"}, {"kind": "site_page", "url": "https://crawlee.dev/js/docs/guides"}, {"kind": "site_page", "url": "https://crawlee.dev/js/docs/examples"}, {"kind": "site_page", "url": "https://crawlee.dev/js/api/core/changelog"}], "use_cases": ["scrape product prices from e-commerce sites", "crawl a website and extract all links", "download HTML, PDF, and images from web pages", "collect training data for LLMs and RAG pipelines", "scrape pages that require JavaScript rendering", "avoid getting blocked while scraping at scale", "export scraped data to CSV or JSON"], "what_it_is": "Crawlee is a web scraping and browser automation library for Node.js/TypeScript (with a Python port) for building reliable crawlers. It integrates with Puppeteer, Playwright, Cheerio, and JSDOM, handling proxies, sessions, retries, and anti-blocking out of the box.", "when_to_avoid": ["you only need a one-off simple HTTP fetch without crawling logic", "you work in a language other than JavaScript/TypeScript or Python", "you need a distributed scraping service rather than an embedded library"], "when_to_choose": ["you need a full-featured scraping framework with proxy rotation and session management", "you want to scrape JavaScript-heavy sites with headless browsers", "you need reliable, scalable crawlers with retries and queueing", "you want TypeScript support and active maintenance"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/apify/crawlee", "repo": "apify/crawlee", "role": "main", "score": 98}, {"path": "/repos/apify/crawlee-python", "repo": "apify/crawlee-python", "role": "sdk", "score": 89}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:38.215786+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T16:56:02.543013+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ca1321af15c2611a04c5861912aaec84d0d6314472f334b0542a7593bf6354fe", "fetched_at": "2026-08-28T04:11:38.215786+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apify/crawlee"}, {"content_hash": "fc7acc1ea74133da7d3c6b11dd131448132645df7973fb698b0183f91e875ab0", "fetched_at": "2026-08-29T07:53:16.889473+00:00", "kind": "homepage", "missing": false, "url": "https://crawlee.dev"}, {"content_hash": "b58b16270a4f2357a851694446dee0248c46909bf8f29f95e6b8e27659c6845b", "fetched_at": "2026-08-29T07:53:16.898552+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/guides"}, {"content_hash": "30b7067a80a4c62b7f90e26170069932a1e9da43a8585236db84701afbf649f6", "fetched_at": "2026-08-29T07:53:16.900368+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/docs/examples"}, {"content_hash": "4319e57ca3883267b73b72f55c9471ce94a436039e3582e5ef121c6d59c5c3d7", "fetched_at": "2026-08-29T07:53:16.902350+00:00", "kind": "site_page", "missing": false, "url": "https://crawlee.dev/js/api/core/changelog"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 97}, "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": 3659, "days_push": 7, "days_rel": 21, "gap_med": 17.0, "n_releases_24m": 27}, "score": 98, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}