Automate Wikipedia Data Extraction & Summarization with n8n & Google Gemini

What This Automation Does

This workflow takes a Wikipedia article URL as input and returns a short, easy-to-read summary.
It solves the problem of manual data gathering from large web pages, saving time and mistakes.
You get human-written text summaries fast for research or business use.

The workflow uses Bright Data’s proxy service to get the full page HTML without blocking.
Then it uses Google Gemini AI to clean and format that data into plain text.
Next, another Google Gemini AI step creates a short summary of the content.
Finally, the summary is sent automatically to a webhook URL for alerting or storage.

Who Should Use This Workflow

Users who need quick, reliable summaries of Wikipedia pages without manual copying.
Ideal for marketers, researchers, and knowledge workers with limited time or technical skills.

This avoids hiring experts or spending hours on data cleanup.
Anyone with access to n8n and required API accounts can run the workflow easily.

Tools and Services Used

• Bright Data Web Unlocker Zone: Scrapes full HTML pages reliably without blocks.
• Google Gemini (PaLM API): Used twice – once for cleaning HTML to text and once for summarizing.
• n8n Workflow Automation Platform: Hosts and runs the steps.
• External HTTP Webhook: Receives final summary for notifications or logging.

Inputs, Processing, and Output

Inputs

• Wikipedia article URL, e.g., https://en.wikipedia.org/wiki/Cloud_computing?product=unlocker&method=api
• Configured Bright Data zone name for scraping.
• Valid API keys for Bright Data and Google Gemini services.

Processing Steps

1. Use Bright Data API to retrieve the raw HTML of the article.
2. Send raw HTML to Google Gemini AI to extract clean, human-readable text.
3. Pass clean text to another Google Gemini AI process to create a concise summary.
4. POST the summary to an external webhook URL for downstream use.

Output

A brief, human-friendly summary text sent to the webhook as JSON.

Beginner Step-by-Step: How to Use This Workflow in n8n

Import Workflow

1. Inside the n8n editor, click the Download button on this page to get the workflow file.
2. Use the “Import from File” option in n8n to load the workflow.

Configure Credentials and Inputs

1. Add your Bright Data HTTP Header Auth credentials in the Wikipedia Web Request node.
2. Add your Google Gemini (PaLM API) credentials to both LLM nodes.
3. In the Set node, update the url field to the desired Wikipedia page URL if needed.
4. Update the zone field with your Bright Data zone name if different.
5. In the final HTTP Request node, update the webhook URL to your chosen endpoint.

Test and Activate

1. Click the Manual Trigger node’s “Execute Workflow” button once to test.
2. Check that data flows smoothly and the final summary arrives at your webhook.
3. When ready, toggle the workflow to “Active” to allow production use on demand.

Customizations

• Change article by updating the URL in the Set node.
• Use OpenAI or other AI providers by swapping Google Gemini credentials and models in LLM nodes.
• Adapt the summarization prompt in the summarization node to create longer or shorter summaries.
• Switch webhook URL to send summaries to Slack, email, or custom APIs.

Troubleshooting

• Authentication failed in Wikipedia Web Request node.
  Cause: Bright Data API keys missing or wrong.
  Fix: Re-enter valid Bright Data HTTP Header Auth credentials.
• LLM Data Extractor outputs empty or poor text.
  Cause: Incorrect input reference or prompt issues.
  Fix: Make sure input uses {{$json.data}} and prompt is clear, simple.
• Summary webhook receives empty data.
  Cause: “Send Body” not enabled or wrong field reference.
  Fix: Enable “Send Body” and confirm body uses {{$json.response.text}}.

Pre-Production Checklist

• Check validity of Bright Data credentials and zone name configured.
• Confirm Google Gemini (PaLM API) keys work for both AI nodes.
• Run a manual test to see full data flow without errors.
• Ensure the final summary is correct and received via webhook.
• Back up API keys and workflow settings securely.

Deployment Guide

Turn on the workflow’s toggle switch in n8n editor to activate.
Since this uses manual trigger, run when you want fresh summaries.

Watch the workflow run log for successful executions.
Consider using self-host n8n for stable operation if running on your own server.

Summary and Final Result

✓ This workflow saves hours of manual Wikipedia research.
✓ You get clean, human-readable summaries fast.
✓ It handles web scraping blocks using Bright Data proxies.
✓ Google Gemini AI cleans and summarizes content precisely.
✓ The result can trigger alerts or feed other tools via webhooks.