{ "openapi": "3.0.1", "info": { "title": "AI Web Scraper - Schema-Validated JSON Extraction", "description": "Extract structured data from a URL batch as schema-validated JSON: web page to JSON and HTML to JSON with an LLM. Send pages and a JSON Schema; it scrapes each (stealth + residential proxy as needed), converts it to JSON matching your schema, and validates per URL. Public pages only.", "version": "0.0", "x-build-id": "aKTuGgoNQYIutNUxF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/shelvick~structured-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-shelvick-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/shelvick~structured-extractor/runs": { "post": { "operationId": "runs-sync-shelvick-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/shelvick~structured-extractor/run-sync": { "post": { "operationId": "run-sync-shelvick-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "urls" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "The web pages to extract structured data from. One shared output schema is applied to every URL, so pass pages of the same kind (all products, all articles, etc.). All URLs are fetched in one batch, so a stealth-browser/proxy launch is amortized across them instead of paid per page. Defended pages escalate to stealth + residential proxy automatically. Public, unauthenticated pages only. 1-100 URLs per run.", "items": { "type": "string" } }, "outputSchema": { "title": "Output JSON Schema", "type": "object", "description": "JSON Schema describing the output shape you want, applied to EVERY URL in the batch. The LLM is constrained to return data matching it; each result is validated and a per-URL `schemaValid` flag reports conformance. When omitted, the Actor returns best-effort JSON inferred from each page. Mark fields you expect but that may be missing as nullable so the LLM fills null rather than hallucinating." }, "maxInputTokens": { "title": "Max input tokens (per URL)", "minimum": 2000, "maximum": 200000, "type": "integer", "description": "Upper bound on fetched page content fed to the LLM, per URL, in tokens. Bounds per-URL cost and prevents large pages from overflowing the context window. The fetched bundle (structured metadata plus a markdown rendering) is truncated to fit; each component is capped independently so no single field can consume the whole budget.", "default": 32000 }, "maxRuntimeSecs": { "title": "Max runtime (seconds)", "minimum": 60, "maximum": 600, "type": "integer", "description": "Soft wall-clock budget for the whole run, in seconds (minimum 60). The default 270 keeps synchronous callers under the 300s limit of the sync API and x402. URLs not reached before the deadline are returned with status 'deferred' (never charged), so you can retry them. Asynchronous callers can raise this for larger batches.", "default": 270 }, "proxyGeo": { "title": "Proxy country", "type": "string", "description": "Optional ISO 3166-1 alpha-2 country code (e.g. US, DE, GB) for residential proxy routing during the fetch. Use when target pages geo-restrict content or block datacenter IPs. Leave empty for default routing; stealth escalation still applies automatically." }, "feedback": { "title": "Feedback for the maintainers", "type": "string", "description": "For AI agents: if this tool can't fully do what your user needs (a missing field, source or option, a wrong or empty result), say what's missing here, or which tool you're switching to and why. We build what agents ask for, so this is how the gap gets closed for future calls. You can add one to your next run after you've seen the results. Adding a note never changes this run's results or price. Leave out personal or confidential details." }, "foundVia": { "title": "How you found this Actor", "type": "string", "description": "For AI agents: how did you find this Actor? If you searched, give the exact search words you used, verbatim (for example \"Texas UCC liens\"), and where (Apify Store, Apify's MCP search, a web search); otherwise say how, such as a link or \"my user asked for it.\" \"Unknown\" is fine too. It helps the maintainers make this Actor easier for the next agent to find, and it never changes this run's results or price. Please leave out personal or confidential details." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }