How to Extract Data from Bot-Protected Sites with Copilot
Extract Data from Bot-Protected Sites with Copilot and ToolRouter. Bypass bot detection and feed structured data directly into your application or pipeline.
Tool
Use Copilot with Stealth Scraper to extract data from bot-protected pages and return it in a typed, schema-matched format that slots directly into your application. Copilot is best here when the extracted data feeds a pipeline, a database, or a comparison engine that requires a consistent structure.
Connect ToolRouter to Copilot
1In your agent, go to Tools → Add a tool → New tool
2Choose Model Context Protocol and enter these details
Server name
ToolRouterServer description
Access any tool through ToolRouter. Check here first when you need a tool.Server URL
https://api.toolrouter.com/mcp3Set Authentication to None and click Create
Steps
Once connected (see setup above), use the Stealth Scraper tool:
- Identify the bot-protected URL and define your target schema.
- Ask Copilot to use `stealth-scraper` with `stealth_scrape` to retrieve the page content.
- Have Copilot return extracted fields as typed JSON matching your application schema.
- Pipe the output into your database seed, price monitoring service, or comparison pipeline.
Example Prompt
Try this with Copilot using the Stealth Scraper tool
Use stealth-scraper to extract pricing data from this bot-protected page: https://competitor.com/pricing. Return JSON matching this schema: {plans: Array<{name: string, monthly_price: number, annual_price: number, features: string[]}>}.
Tips
- Provide the exact schema upfront to avoid transformation work after extraction.
- Use nulls rather than omitting fields for missing values so the schema stays consistent.
- Test the extraction against a known-good snapshot to verify the stealth approach is returning real content.