Skip to main content
Alongside the parsed JSON, every response can carry the scraped page’s HTML — proof of what the AI provider actually displayed — and its answer as text or markdown for LLM pipelines.

​
HTML: proof of scraped page

When you request HTML from any endpoint using include.html: true, the response includes a URL to the full scraped page stored on our CDN. This is the page the AI provider actually displayed, so you can present it to your clients as proof of what was scraped. result.html is a single URL string on most endpoints. On Google Search and Google News it is an array of URLs — one per scraped page — so handle both shapes if you call several endpoints from the same code path. The raw HTML includes browser chrome (headers, footers, sidebars, cookie banners, and scripts). To render a clean version, fetch the HTML from the CDN URL and parse it with the @cloro-dev/response-parser npm package: it auto-detects the AI provider, strips scripts and chrome, and returns sanitized HTML you can render in any framework (React, Vue, Svelte, vanilla JS). See the response-parser README for installation, API reference, framework examples, and supported options.
The HTML URL expires after 24 hours — download and store the HTML if you need long-term access. Including HTML costs no extra credits.

​
Text and markdown: LLM analysis

For text analysis or LLM pipelines, use result.text or result.markdown (with include.markdown: true) directly. You don’t need the response-parser for this. But special objects are embedded as text in these fields: when the AI provider displays shopping cards, places, ads, inline products, entities, or map entries, their content appears in result.text and result.markdown. Sources and footers are not included. The structured fields (result.shoppingCards, result.places, result.ads, result.inlineProducts, result.entities, result.mapEntries) hold the same data in clean form. Use them to know exactly what to strip out of the text before sending it to an LLM, and to read object-specific data such as prices, ratings, and URLs.
If you pass result.text or result.markdown directly to an LLM without removing special object content, the model may treat product cards, ads, or place listings as part of the AI’s natural language response.

​
Common questions

​
Why do I see errors when opening the HTML file in my browser?

The scraped HTML may include JavaScript from the original AI provider page. When opened directly in a browser, this JavaScript executes and can cause errors, broken layouts, or unexpected behavior. To view the HTML correctly, disable JavaScript in your browser before opening the file: in Chrome, open DevTools (Cmd/Ctrl+Shift+I), press Cmd/Ctrl+Shift+P, and run “Disable JavaScript”. Alternatively, use the @cloro-dev/response-parser library which automatically strips all scripts during parsing.