{"adoption": {"forks": 2119, "observed_at": "2026-08-28T04:11:09.279844+00:00", "stars": 15144}, "canonical_url": "https://ross.abutalabs.com/products/newspaper", "card": {"archived": false, "artifact_type": "library", "description": "newspaper3k is a news, full-text, and article metadata extraction in Python 3. Advanced docs:", "domain": ["web-development", "crawlers", "data-science"], "enriched": true, "function": ["web-scraping", "parser", "nlp"], "health_score": 78, "homepage": "https://goo.gl/VX41yK", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["codelucas/newspaper"], "name": "codelucas/newspaper", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-09T07:55:32+00:00", "repo": "codelucas/newspaper", "stars": 15144, "tags": ["article-extraction", "news-scraping", "metadata-extraction", "newspaper3k", "html-parsing", "natural-language-processing"], "topics": ["python", "news", "crawler", "crawling", "scraper", "news-aggregator"], "urls": [], "use_cases": ["extract full text from news article urls", "scrape article metadata like authors and publish date", "crawl a news site to discover article links", "summarize articles and extract keywords with nlp", "build a news aggregator in python", "parse html into clean readable article text"], "what_it_is": "newspaper3k is a Python 3 library for discovering, downloading, and parsing news articles from websites. It extracts full text, authors, publish dates, images, keywords, and summaries, and can crawl entire news sites for article URLs.", "when_to_avoid": ["you need a general-purpose web scraper for arbitrary sites or JS-rendered pages", "you need actively maintained software with recent fixes", "you need structured data extraction beyond news articles"], "when_to_choose": ["you need turnkey news article extraction with metadata in Python", "you want to crawl news sites for article discovery", "you need keyword extraction and summarization built in"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/newspaper", "repo": "codelucas/newspaper", "role": "main", "score": 66}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:11:09.279844+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:06:35.959376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "8c6447b0094df338cf99430c88af402157172da1c465d400736953b8da1c2e1f", "fetched_at": "2026-08-28T04:11:09.279844+00:00", "kind": "readme", "missing": false, "url": "https://github.com/codelucas/newspaper"}, {"content_hash": "cf6989ef27ae59ede44ad7822de93df918a700cfb9cc45a9d9d91cc4e30db63b", "fetched_at": "2026-08-29T08:04:36.809551+00:00", "kind": "homepage", "missing": false, "url": "https://goo.gl/VX41yK"}, {"content_hash": "37fe9b56f324a34eb43c98b979e13083c2d8a3835e1321760deab5e12c952ff4", "fetched_at": "2026-08-29T08:04:36.818867+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/newspaper/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 8}, "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": 4664, "days_push": 24, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 66, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}