Skip to main content New gottem — one API for every web scraping vendor.
AI Studio

Extract web data with natural language.

Describe what you need in plain English. Spider's AI endpoints crawl, scrape, search, and automate the web — structured JSON back, ready for your application.

5AI endpointsJSONStructured outputREST+ Python, Node, Go
01 · How it works

Prompt in. JSON out.

01

Send a prompt

Pass a URL and describe what you want to extract in plain English. No selectors, no XPath, no parsers.

02

AI extracts

Spider renders the page in a real browser, then runs your prompt against the DOM to find matching data.

03

Get JSON

Receive clean structured output, ready for your database, API, or AI pipeline.

02 · Endpoints

Five ways to ask.

Each endpoint targets one extraction pattern. All five share the same prompt-driven request shape and your existing API key.

AI Crawl

POST /ai/crawl

Crawl a site with a natural-language goal. The crawler follows links toward whatever you described, not whatever a sitemap says.

NL goalsSmart link pickingContent filteringStructured output
Prompt
"Find all product pages and extract pricing information"
View documentation

AI Scrape

POST /ai/scrape

Hand the page a prompt instead of selectors. Spider renders it, runs your prompt over the DOM, and returns the fields you asked for as JSON.

Plain-English fieldsAuto schemaMulti-formatContext-aware
Prompt
"Extract all article titles, authors, and publish dates"
View documentation

AI Search

POST /ai/search

Search the web with an intent, not a keyword. Results are ranked by relevance to the question, not just lexical match.

Semantic queriesIntent rankingStructured results
Prompt
"Find recent news about AI startups in healthcare"
View documentation

AI Browser

POST /ai/browser

Drive a real browser with English instructions. Spider figures out the clicks, fills, and waits without you writing selectors.

NL automationSmart elementsAction sequencingDynamic pages
Prompt
"Click the login button, fill the email field, and submit"
View documentation

AI Links

POST /ai/links

Pull only the links you want — product pages, docs, articles — by describing them, not by writing a CSS selector.

NL filteringCategory detectionRelevance rankingDeep discovery
Prompt
"Find all links to product pages and documentation"
View documentation
03 · Integration

One field, structured results.

Add a prompt field to any AI request. Works with every Spider SDK and the same API key you already issued.

Request
$ curl -X POST \
  https://api.spider.cloud/ai/scrape \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "url": "https://example.com",
    "prompt": "Extract product names and prices"
  }'
Response200 OK
[
  { "name": "Widget Pro",  "price": "$49.99" },
  { "name": "Gadget Plus", "price": "$29.99" },
  { "name": "Tool Max",    "price": "$79.99" }
]
Python · Node · Go SDKsUses existing API keyPay-per-use pricing
04 · Why this AI surface

Built for the people writing the code.

01

No selectors needed

Drop XPath, CSS selectors, and brittle scraper scripts. Describe your data in English and let the model do the parsing.

02

Works with any site

JavaScript-rendered pages, SPAs, dynamic content. Spider drives a real browser before AI extraction runs.

03

Schema-shaped output

Get JSON with the exact fields you asked for. Pin a schema, or let the model infer the shape from the prompt.

04

Scales on demand

From a single page to a million. Same API, built-in concurrency, rate limiting, and retries.

Start extracting

Ship your first prompt in minutes.

Sign up, grab an API key, and send your first AI extraction request. No selectors to maintain, no infrastructure to run.