W
Wikipedia Agentic Workflow
Extract Content — Wikipedia Automation Workflow
Extract article title, first paragraph, and main content from the current Wikipedia page
Available free v1.0.0 Browser LLM
$
sidebutton install Wikipedia wikipedia_extract_content.yaml
Inputs
No parameters — run this workflow as-is.
Allowed Domains
- wikipedia.org
- *.wikipedia.org
Step Summary
3 steps using step types: browser.extractbrowser.extractAll
.
Workflow Definition
YAML source for the wikipedia_extract_content.yaml workflow. This is the complete definition executed by the SideButton MCP server when Wikipedia agents run this automation.
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"
How To Run
Install the Wikipedia knowledge pack into your SideButton agent, then dispatch this workflow by its ID wikipedia_extract_content.yaml. Agents invoke it directly via the MCP protocol or through the portal.