Wikipedia Knowledge Pack Files

schema_version: 1
version: "1.0.0"
last_verified: "2025-12-21"
id: wikipedia_extract_content
title: "Extract Content"
description: "Extract article title, first paragraph, and main content from the current Wikipedia page"
category:
  level: task
  domain: research
  reusable: true
policies:
  allowed_domains:
    - wikipedia.org
    - "*.wikipedia.org"
steps:
  # Extract article title
  - type: browser.extract
    selector: "#firstHeading"
    as: title

  # Extract first paragraph (the lead/summary)
  - type: browser.extract
    selector: "#mw-content-text .mw-parser-output > p:not([class])"
    as: first_paragraph

  # Extract main content (multiple paragraphs)
  - type: browser.extractAll
    selector: "#mw-content-text .mw-parser-output > p:not([class])"
    as: content
    separator: "\n\n"