{"adoption": {"forks": 540, "observed_at": "2026-08-28T04:08:18.667129+00:00", "stars": 3788}, "canonical_url": "https://ross.abutalabs.com/products/generalnewsextractor", "card": {"archived": false, "artifact_type": "library", "description": " 新闻网页正文通用抽取器 Beta 版.", "domain": ["web-development", "crawlers"], "enriched": true, "function": ["parser", "web-scraping", "nlp"], "health_score": 85, "homepage": "http://gne.kingname.info/", "language": "Python", "license": "GPL-3.0", "license_family": "copyleft", "maturity": "active", "member_repos": ["kingname/GeneralNewsExtractor"], "name": "kingname/GeneralNewsExtractor", "platform": ["python", "cross-platform"], "pushed_at": "2026-04-21T23:03:46+00:00", "repo": "kingname/GeneralNewsExtractor", "stars": 3788, "tags": ["news-extraction", "html-parsing", "text-density", "content-extraction", "metadata-extraction", "natural-language-processing"], "topics": ["python3", "webcrawler", "webspider"], "urls": [], "use_cases": ["extract article body text from news pages", "scrape news articles without site-specific rules", "get title author and publish time from html", "extract article listings from an index page", "clean noise like comments and ads out of article html", "build a news aggregator pipeline"], "what_it_is": "GNE (GeneralNewsExtractor) is a Python library that extracts article title, author, publish time, body text, and images from news page HTML using a text and symbol density algorithm. It takes already-fetched HTML as input and returns a structured dictionary, deliberately excluding any crawling/request functionality.", "when_to_avoid": ["you need a full crawler that fetches pages from websites", "you need extraction of non-news page types like e-commerce or forums", "you require JavaScript rendering - you must fetch and render HTML yourself first"], "when_to_choose": ["you already have rendered HTML and need structured article data", "you want a lightweight extractor with no heavy dependencies", "you target Chinese news sites or general news layouts without writing per-site selectors"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/generalnewsextractor", "repo": "kingname/GeneralNewsExtractor", "role": "main", "score": 81}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:18.667129+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:27:28.030584+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "47f88965b8c71208c6d52e71518f4462b0572df2afd4fa0f9b883f35d35f344f", "fetched_at": "2026-08-28T04:08:18.667129+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kingname/GeneralNewsExtractor"}, {"content_hash": "501a159e32c6d9e695218b04f7ed813b583ff68e6160557b37f9b72477e37948", "fetched_at": "2026-08-29T09:22:11.796676+00:00", "kind": "homepage", "missing": false, "url": "http://gne.kingname.info/"}, {"content_hash": "369874815e1bd4a35ff50584e50153681532ed2f8750539ed69b7cdd125501b4", "fetched_at": "2026-08-29T09:22:11.805515+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/generalnewsextractor/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "longevity": 100, "rhythm": 74}, "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": 2551, "days_push": 134, "days_rel": 179, "gap_med": 0, "n_releases_24m": 2}, "score": 81, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}