news-aggregator-skill

Real-time news aggregation from multiple sources combines feeds from platforms like Hacker News, Weibo, and 36Kr into a unified feed. This Skill fetches and consolidates headlines across eight major sources for daily scans and tech briefs.

Filtering aggregated news feeds by keywords refines the unified feed to match specific topics. This Skill applies keyword filters to the fetched content, helping you isolate relevant financial updates or hot-topic deep-dives from the noise.

Multi-source news aggregation works directly with GitHub Trending and Product Hunt. It fetches real-time updates from both platforms alongside Tencent News and Wall Street CN, consolidating them into a single browsable feed.

Extracting full article text during a news aggregation scan uses deep crawling to download and parse the source page. This Skill offers optional content enrichment via deep crawling, extracting up to 3000 characters of body text.

You need beautifulsoup4 to perform deep crawling for news briefs because it parses the downloaded HTML to extract article text. The Skill relies on it alongside requests to fetch and process web content from the eight aggregated sources.

Limitations of real-time news aggregation for hot-topic deep-dives include a text extraction cap during deep crawling. The Skill truncates extracted article content to the first 3000 characters, which may omit details from lengthy analytical reports.