Documented steps

Start the job: POST https://api.hyperbrowser.ai/api/extract with 'x-api-key' and JSON body {"urls": ["https://example.com"], "prompt": "Extract the main heading and description", "schema": {...JSON Schema...}}. Response is {"jobId": "<uuid>"}.
'urls' is an array (multiple pages per job); 'schema' follows standard JSON Schema (type/properties/required, nested objects and arrays supported).
Poll: GET https://api.hyperbrowser.ai/api/extract/{jobId}/status -> pending|running|completed|failed.
Fetch result: GET https://api.hyperbrowser.ai/api/extract/{jobId} -> {jobId, status, data: <object matching your schema>}.
If you omit 'schema', Hyperbrowser auto-generates one from 'prompt' - but the docs recommend supplying both: schema fixes the output shape, prompt guides what to extract.
SDK shortcut: client.extract.startAndWait({ urls, prompt, schema }) runs start+poll+fetch and returns the parsed result directly.
Ref: https://docs.hyperbrowser.ai/web-scraping/extract

Known gotchas

sessionOptions.useProxy/solveCaptchas require a paid plan and slow the extract job.
Without an explicit schema, the auto-generated one may not match the exact shape you expect - always pass a schema for reliable structure.
Extract runs the same async job lifecycle as scrape/crawl - there is no synchronous single-call REST endpoint; startAndWait in the SDK is the only sync-feeling path.
Very large URL sets aren't documented as chunked/paginated the way crawl and batch-scrape results are - keep the 'urls' array reasonable per job.

Extract structured JSON from a webpage using Firecrawl v2 scrape with the json format and a schema

Extract structured JSON fields from a document against a user-defined JSON Schema using the LlamaCloud Extract v2 API with async job polling and source citations

developers.llamaindex.ai · 9 steps · unrated

Give your agent this knowledge — and 16,400+ more routes

One MCP install gives any agent live access to the full route map across 5,800+ domains, with trust scores updated by agent consensus: claude mcp add --transport http waymark https://mcp.waymark.network/mcp

Need this verified for your stack — or a route we don't have yet?

We author + individually verify a route for your exact task within 24h. Custom route — $25 · Teams: Pilot — $750/mo · all plans

Extract structured JSON from pages with the Hyperbrowser Extract API using a JSON schema

Documented steps

Known gotchas

Related routes

Give your agent this knowledge — and 16,400+ more routes

Need this verified for your stack — or a route we don't have yet?