{"adoption": {"forks": 864, "observed_at": "2026-08-28T04:09:48.684612+00:00", "stars": 6799}, "canonical_url": "https://ross.abutalabs.com/products/node-crawler", "card": {"archived": false, "artifact_type": "library", "description": "Web Crawler/Spider for NodeJS + server-side jQuery ;-)", "domain": ["crawlers", "web-development", "developer-tools"], "enriched": true, "function": ["web-scraping", "parser", "http-client", "caching"], "health_score": 92, "homepage": null, "language": "TypeScript", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["bda-research/node-crawler"], "name": "bda-research/node-crawler", "platform": ["cli"], "pushed_at": "2026-06-18T15:50:22+00:00", "repo": "bda-research/node-crawler", "stars": 6799, "tags": ["cheerio", "jquery-server-side", "rate-limiting", "priority-queue", "crawler", "spider", "esm", "typescript", "nodejs"], "topics": ["crawler", "javascript", "spider", "extract-data", "cheerio", "jquery", "nodejs"], "urls": [], "use_cases": ["scrape product prices from e-commerce sites", "crawl a website and extract links", "parse html pages with jquery-like selectors in node", "build a polite crawler with rate limiting and retries", "extract data from web pages into structured output", "queue large-scale crawling jobs with priority"], "what_it_is": "node-crawler is a TypeScript web crawler/spider library for Node.js that fetches pages and provides server-side DOM parsing with automatic jQuery-style manipulation via Cheerio. It offers a configurable request pool, retries, rate limiting, priority queues, and charset detection.", "when_to_avoid": ["you need to render JavaScript-heavy SPA pages (use Puppeteer/Playwright instead)", "you want a simple one-off HTTP fetch without crawling features", "you're on an older Node.js version below 22"], "when_to_choose": ["you need server-side DOM traversal with Cheerio/jQuery syntax", "you want built-in rate limiting, retries, and a priority queue", "you're on Node.js 22+ and comfortable with ESM", "you need charset detection and conversion handled automatically"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/node-crawler", "repo": "bda-research/node-crawler", "role": "main", "score": 91}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:48.684612+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:42:05.835482+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "32be71f762badc85379d1e6d6f120715dc8a350305a75aff80f6ef42158d0ed1", "fetched_at": "2026-08-28T04:09:48.684612+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bda-research/node-crawler"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 88, "longevity": 100, "rhythm": 89}, "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": 5760, "days_push": 76, "days_rel": 78, "gap_med": 11, "n_releases_24m": 2}, "score": 91, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}