{"adoption": {"forks": 282, "observed_at": "2026-08-28T04:07:34.290088+00:00", "stars": 2987}, "canonical_url": "https://ross.abutalabs.com/products/newscatcher", "card": {"archived": false, "artifact_type": "library", "description": "Programmatically collect normalized news from (almost) any website.", "domain": ["data-science", "crawlers", "media", "developer-tools"], "enriched": true, "function": ["web-scraping", "parser", "nlp", "data-science"], "health_score": 20, "homepage": "https://newscatcherapi.com/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["kotartemiy/newscatcher"], "name": "kotartemiy/newscatcher", "platform": ["python", "cross-platform"], "pushed_at": "2020-10-30T19:09:31+00:00", "repo": "kotartemiy/newscatcher", "stars": 2987, "tags": ["news-aggregation", "rss", "news-media", "mvp-prototyping", "normalized-data", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["collect news articles from a specific website in python", "get latest headlines by topic like politics or tech", "find news sources by country and language", "build a news aggregation prototype", "scrape normalized news data for a data science project", "test an MVP that needs live news feeds"], "what_it_is": "A Python package that programmatically collects normalized news articles from thousands of news websites, filterable by topic, country, and language. It works out of the box without any API keys and is intended for prototyping and MVPs rather than production systems.", "when_to_avoid": ["you need a production-grade news pipeline with SLAs", "you need full-text search or NLP enrichment at scale - consider the vendor's commercial News API", "you need actively maintained software - the last release was in 2020"], "when_to_choose": ["you need quick, key-free access to news feeds in Python", "you are prototyping or validating assumptions with news data", "you want to filter news sources by topic, country, or language"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/newscatcher", "repo": "kotartemiy/newscatcher", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:34.290088+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:31:24.999053+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "ed7c45feb039c091c13e2c1dee43215f7390d0b97cb239f6d92f24bc50133bbf", "fetched_at": "2026-08-28T04:07:34.290088+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kotartemiy/newscatcher"}, {"content_hash": "a0b99020b04483b97187ba9655a311581e30413ba6cd3886a562a1dcafe12e1f", "fetched_at": "2026-08-29T09:46:34.005285+00:00", "kind": "homepage", "missing": false, "url": "https://newscatcherapi.com/"}, {"content_hash": "57c6e60fff09f1ead8e8e84d111b897cc92d4ec6a275044c3a1640a4e6f049c2", "fetched_at": "2026-08-29T09:46:34.014644+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/about-us"}, {"content_hash": "b29778b5fd170315b0e66a721b789cf14a1ddfc5aa630888ca9357eab9759ad3", "fetched_at": "2026-08-29T09:46:34.022264+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/docs/home"}, {"content_hash": "07a05c36911527a920ba35ae516649fb3315419145ba7ffcd9fe7749497964ca", "fetched_at": "2026-08-29T09:46:34.016842+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/company/roadmap"}, {"content_hash": "4795d3c8ca2a6ef57b0a94ff1a1011c2312c6567c7e1a7a90c8e7e8495b48740", "fetched_at": "2026-08-29T09:46:34.019730+00:00", "kind": "site_page", "missing": false, "url": "https://www.newscatcherapi.com/pricing"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2382, "days_push": 2133, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}