{"adoption": {"forks": 1427, "observed_at": "2026-08-28T04:07:41.997015+00:00", "stars": 3083}, "canonical_url": "https://ross.abutalabs.com/products/webcollector", "card": {"archived": false, "artifact_type": "framework", "description": "WebCollector is an open source web crawler framework based on Java.It provides some simple interfaces for crawling the Web,you can setup a multi-threaded web crawler in less than 5 minutes.", "domain": ["crawlers", "web-development"], "enriched": true, "function": ["web-scraping", "http-client", "parser"], "health_score": 60, "homepage": "https://github.com/CrawlScript/WebCollector", "language": "Java", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "maintenance", "member_repos": ["CrawlScript/WebCollector"], "name": "CrawlScript/WebCollector", "platform": ["jvm", "cross-platform"], "pushed_at": "2026-02-10T07:32:20+00:00", "repo": "CrawlScript/WebCollector", "stars": 3083, "tags": ["web-crawler", "multi-threaded", "selenium", "java-framework", "search-engine-crawling", "data-engineering"], "topics": [], "urls": [], "use_cases": ["crawl websites to collect pages", "build a multi-threaded web crawler in Java", "scrape news articles from the web", "crawl JavaScript-rendered pages with Selenium", "collect data for building a search index", "crawl sites through rotating proxies"], "what_it_is": "WebCollector is an open-source Java web crawler framework that provides simple interfaces for building multi-threaded web crawlers quickly. It supports features like cookies, POST requests, proxies, and Selenium-based JavaScript rendering.", "when_to_avoid": ["you need a distributed, large-scale crawling platform", "your stack is Python or Node.js rather than Java", "you need heavy-duty headless-browser automation beyond simple rendering"], "when_to_choose": ["you need a quick-to-setup crawler on the JVM", "you want a lightweight Java alternative to Scrapy-style crawling", "you need multi-threaded crawling with proxy and cookie support"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/webcollector", "repo": "CrawlScript/WebCollector", "role": "main", "score": 62}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:41.997015+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:27:41.456888+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "4be37c3fc3cb14413392fb41b7d23102ff7b5c26ee2aa527a50e46ce6f1f5f7e", "fetched_at": "2026-08-28T04:07:41.997015+00:00", "kind": "readme", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}, {"content_hash": "6f08d5e097919363f7593205c2fe2be5eab996ad538ade5fc782eef7c1a6f609", "fetched_at": "2026-08-29T09:42:50.922266+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/CrawlScript/WebCollector"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 66, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4435, "days_push": 204, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 62, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}