Stealth Scraper
Scrape bot-protected websites
On it. Running Stealth Scraper now and I'll bring the results straight back here.
Try asking
About
Stealth Scraper extracts data from bot-protected websites that block standard scraping tools. When you're getting 403 errors, CAPTCHA walls, or blocks from Cloudflare, Akamai, DataDome, or PerimeterX — this tool gets through using residential proxies and geo-targeted IPs.
It's the fallback for when normal web scraping fails. Use it on single pages or crawl entire protected sites. If a site loads fine in your browser but blocks automated requests, this is the tool for the job.
What you can do
- Scrape a single bot-protected page using residential proxies and extended rendering wait times
- Crawl an entire bot-protected site recursively
- Target geo-specific content using country-level proxy selection
- Match locale with language headers for localized content
- Control rendering wait time for heavy single-page applications
- Return content as markdown, HTML, or raw HTML
Who it's for
Developers and researchers who need data from sites that actively block scrapers. Data teams collecting pricing, product, or content data from protected sources. Anyone whose standard scraping workflow is hitting bot detection walls.
How to use it
- Try the regular Web Scraper tool first — use Stealth Scraper only when you get 403, 429, or CAPTCHA responses
- Use stealth_scrape for a single page — it automatically applies residential proxies and a 3-second render wait
- Set country to match the target site's region (e.g. "gb" for UK sites) for better proxy matching
- Increase waitFor for heavy SPAs that need extra time to render their content
- For long React/SPA pages or competitor research, set fullContent to true or increase maxPreviewChars so the model-facing response includes more than the compact preview
- Use stealth_crawl for recursive crawling of a protected site — note it's slower and async (~120s)
Getting started
No setup required — the tool uses a shared proxy pool by default, or connect your own account for dedicated proxies.
Scrape a single bot-protected web page using enhanced residential…
Recursively crawl a bot-protected website using enhanced proxies on…
Scrape a single bot-protected web page using enhanced residential proxies, geo-targeted IPs, and extended rendering wait times. Bypasses Cloudflare, Akamai, DataDome, and similar anti-bot systems.
Recursively crawl a bot-protected website using enhanced proxies on every page. Bypasses anti-bot systems across the entire crawl, with geo-targeted IPs and extended rendering.
- Concise responses now honor fullContent and maxPreviewChars, returning the requested page text without a second call
- Added fullContent and maxPreviewChars controls for long React/SPA pages and competitor research
- Initial release with stealth_scrape and stealth_crawl skills
Powered by
Related
Guides
- How to Scrape a Website in ChatGPTUse a read/fetch ToolRouter MCP app to scrape websites in ChatGPT Pro, Business or Enterprise/Edu web with structured output.
- How to Scrape a Website in GrokGrok browsing is not a structured scrape. Add the ToolRouter connector on grok.com, then pull structured fields from a URL in chat.
Questions
When should I use this instead of a normal scraper?
Use `stealth_scrape` when a site throws 403s, 429s, CAPTCHA pages, or bot protection from Cloudflare, Akamai, DataDome, or PerimeterX.
Can it scrape just one page or an entire site?
`stealth_scrape` handles a single protected page, while `stealth_crawl` recursively crawls a whole site with a page limit and depth cap.
Can I match the browser to the site region or language?
Yes. Set `country` for geo-targeted proxies and `languages` for locale headers. You can also use `mobile`, `waitFor`, and `onlyMainContent` when the site needs it.
What output formats can I get?
`stealth_scrape` can return formats like markdown, HTML, raw HTML, links, and screenshots, along with the extracted page metadata.