News Scraper
Configurable News Scraper — collects articles from any set of RSS/Atom feeds the user provides. Supports multiple sources with category tagging, deduplication, and date sorting. Includes a multi-language summary report (English, Portuguese, Spanish).
Configuration
Provide your sources as a JSON array in globalArguments.sources: json [ { "name": "BBC News", "feeds": [ { "url": "https://feeds.bbci.co.uk/news/rss.xml", "category": "general" }, { "url": "https://feeds.bbci.co.uk/news/technology/rss.xml", "category": "technology" } ] }, { "name": "Reuters", "feeds": [ { "url": "https://www.reutersagency.com/feed/", "category": "general" } ] } ]
Methods
- gather — Fetch all configured RSS/Atom feeds, parse articles, deduplicate by URL, sort by date, and write a consolidated brief.
Report
- @figura/news-summary — Formatted markdown briefing with top
headlines and per-source sections. Supports
en,pt-BR, andes.
Global Arguments
| Argument | Type | Description |
|---|---|---|
| sources | array | Array of news sources to scrape. Each source has a name and one or more RSS/Atom feed URLs. |
| articlesPerSource | number | Maximum number of articles to keep per source |
| language | string | Language hint for the report (e.g. 'en', 'pt-BR', 'es') |
Resources
News summary report — formatted briefing with top headlines from configured sources. Supports multiple languages.
- Has README or module doc2/2earned
- README has a code example1/1earned
- README is substantive1/1earned
- Most symbols documented1/1earned
- No slow types (deprecated)1/1earned
- Dependencies pass trust audit2/2earned
- Has description1/1earned
- Platform support declared (or universal)2/2earned
- License declared1/1earned
- Verified public repository2/2earned