extractor.sh
All guides

News search guide / 2026

AI News Search API for Current Research in 2026

News workflows need recency controls and provenance. A concise article feed helps an agent identify current coverage without treating a headline or summary as the full story.

Quick answer

Use a timeframe when recency is part of the question.

Set language, country, and a timeframe when an agent needs a particular market or window, then read original publisher links for full context.

curl --get 'https://extractor.sh/api/extract' \
  --data-urlencode 'url=https://example.com/' \
  --data-urlencode 'format=json'

Available data

What you can extract

  • Up to 50 article candidates
  • Publisher, title, date, summary, and source link
  • Language and country controls
  • Recent-timeframe cutoffs

AI workflows

Where normalized data helps

  • Current-events chat
  • Policy and company monitoring
  • News briefing agents
  • Publisher discovery

AI-ready output

Markdown for models. JSON for systems.

Raw HTML consumes tokens on navigation, scripts, styling, and interface labels. Clean Markdown keeps the readable hierarchy for LLM prompts and RAG chunks. Normalized JSON is better when your application needs an explicit semantic type, source, author, publication date, media, attributes, and collection items.

Always retain the canonical URL from the response. AI-generated summaries should remain traceable to the public source, especially when the underlying page can change.

Boundaries

Public data only

  • Results are article metadata, not full publisher bodies.
  • Undated articles are excluded when a timeframe is selected.
  • Ranking changes over time.

extractor.sh does not bypass CAPTCHAs, login walls, paywalls, access controls, or regional restrictions. Review the source’s terms and applicable law before collecting or reusing data.