{"adoption": {"forks": 4106, "observed_at": "2026-08-28T04:10:49.431069+00:00", "stars": 11678}, "canonical_url": "https://ross.abutalabs.com/products/webmagic", "card": {"archived": false, "artifact_type": "framework", "description": "A scalable web crawler framework for Java.", "domain": ["crawlers", "web-development", "developer-tools"], "enriched": true, "function": ["web-scraping", "parser", "http-client", "etl"], "health_score": 66, "homepage": "http://webmagic.io/", "language": "Java", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["code4craft/webmagic"], "name": "code4craft/webmagic", "platform": ["jvm", "cross-platform"], "pushed_at": "2025-12-20T14:01:57+00:00", "repo": "code4craft/webmagic", "stars": 11678, "tags": ["crawler", "scraping", "xpath", "distributed-crawling", "annotation-driven", "data-engineering"], "topics": ["crawler", "java", "scraping", "framework"], "urls": [], "use_cases": ["scrape product prices from e-commerce sites", "crawl github repository metadata", "extract structured data from html pages", "build a distributed crawler with redis", "collect news articles into a database", "parse web pages with xpath and css selectors"], "what_it_is": "WebMagic is a scalable web crawler framework for Java covering the full crawl lifecycle: downloading, URL management, content extraction (XPath/CSS/regex/JsonPath), and persistence. It offers a simple chainable API plus annotation-driven POJO crawlers, with multi-threading and Redis-based distributed support.", "when_to_avoid": ["you need a headless browser for JavaScript-heavy sites", "your stack is Python (Scrapy) or Node.js", "you only need a one-off simple HTTP fetch", "you need a maintained GUI scraping tool"], "when_to_choose": ["you need a JVM-based crawler with a simple, extensible API", "you want annotation-driven extraction into POJOs", "you need multi-threaded or Redis-distributed crawling", "you want pluggable pipelines to console, file, MySQL, or Redis"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/webmagic", "repo": "code4craft/webmagic", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:49.431069+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:15:24.734981+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ba1f792648052c42b05eaf964e913e2546545052be03446cc5bc55cf92756a45", "fetched_at": "2026-08-28T04:10:49.431069+00:00", "kind": "readme", "missing": false, "url": "https://github.com/code4craft/webmagic"}, {"content_hash": "4494c3c4d1dce79d381cddff2bde787cc85ea1b22dd162dd28e7a371286271a4", "fetched_at": "2026-08-29T08:13:42.752642+00:00", "kind": "homepage", "missing": false, "url": "http://webmagic.io/"}, {"content_hash": "256c6ea19934efd936e928be9973b1144a609399a7fe0a8160388f8ea5ac70a9", "fetched_at": "2026-08-29T08:13:42.766661+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/en/index.html"}, {"content_hash": "d13e3138b44eb3b987d70350b2e392786d6a4d9e578e2934ba0051c5ad7f8395", "fetched_at": "2026-08-29T08:13:42.761999+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/apidocs/index.html"}, {"content_hash": "064d5208ee6bcd704d81a55c22ba0dbb917cb23adbc44c8526a8d84785b54fd5", "fetched_at": "2026-08-29T08:13:42.764405+00:00", "kind": "site_page", "missing": false, "url": "http://webmagic.io/archive/docs/0.6.1/zh/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 58, "longevity": 100, "rhythm": 40}, "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": 4880, "days_push": 256, "days_rel": 569, "gap_med": 0.0, "n_releases_24m": 7}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}