{"adoption": {"forks": 847, "observed_at": "2026-08-28T04:07:18.652787+00:00", "stars": 2766}, "canonical_url": "https://ross.abutalabs.com/products/webporter", "card": {"archived": false, "artifact_type": "application", "description": "基于 webmagic 的 Java 爬虫应用", "domain": ["crawlers", "data-science", "developer-tools"], "enriched": true, "function": ["web-scraping", "search-engine", "data-visualization", "etl"], "health_score": 20, "homepage": null, "language": "Java", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["brianway/webporter"], "name": "brianway/webporter", "platform": ["jvm", "cli"], "pushed_at": "2022-01-08T13:14:10+00:00", "repo": "brianway/webporter", "stars": 2766, "tags": ["zhihu", "webmagic", "elasticsearch", "kibana", "crawler-example", "json-config", "multi-threaded", "search", "docker"], "topics": ["elasticsearch", "kibana", "zhihu"], "urls": [], "use_cases": ["scrape zhihu user profiles into elasticsearch", "learn how to build a java crawler with webmagic", "bulk import crawled json data into elasticsearch", "visualize scraped data with kibana aggregations", "example of a full crawl-store-analyze pipeline", "configure a crawler without changing source code"], "what_it_is": "webporter is a Java crawler application built on the webmagic framework that demonstrates a complete pipeline of data crawling, persistence, and visualization. It ships a Zhihu user-data collector example with modules for core logic, Elasticsearch bulk import, and site-specific collection configured via JSON.", "when_to_avoid": ["you need a production-grade crawler - use webmagic or scrapy instead", "you need a general-purpose scraping framework rather than a sample application", "you need an actively maintained project with a clear license"], "when_to_choose": ["you want a worked Java example of crawling plus Elasticsearch ingestion", "you need to collect Zhihu user data for analysis or learning", "you prefer JSON configuration over code changes"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/webporter", "repo": "brianway/webporter", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:18.652787+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:16:45.192968+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5ff238f39b2adea186349ecbf97a80e6a50cb18529eb9cefca285944a607e13a", "fetched_at": "2026-08-28T04:07:18.652787+00:00", "kind": "readme", "missing": false, "url": "https://github.com/brianway/webporter"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3569, "days_push": 1698, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}