AI Web Data Extractor – Any URL to JSON with Your Schema
Pricing
from $1.00 / 1,000 page-extracteds
Go to Apify Store
AI Web Data Extractor – Any URL to JSON with Your Schema
Pricing
from $1.00 / 1,000 page-extracteds
You can access the AI Web Data Extractor – Any URL to JSON with Your Schema programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "O1l7oHKieOFg4YUlT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/filexy634~ai-structured-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-filexy634-ai-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/filexy634~ai-structured-extractor/runs": { "post": { "operationId": "runs-sync-filexy634-ai-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/filexy634~ai-structured-extractor/run-sync": { "post": { "operationId": "run-sync-filexy634-ai-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", "schema", "llmApiKey" ], "properties": { "urls": { "title": "URLs", "type": "array", "description": "Web pages to extract data from, one per line.", "items": { "type": "string" } }, "schema": { "title": "Fields to extract", "type": "object", "description": "Either a JSON Schema object (type: object with properties), or a simple map of field name to a plain-English description, e.g. {\"title\": \"Book title\", \"price\": \"Price as a number\"}." }, "instructions": { "title": "Extra instructions", "type": "string", "description": "Optional guidance for the model, e.g. \"Prices are in euros\" or \"Only extract products from the main listing\"." }, "multiple": { "title": "Extract a list of items per page", "type": "boolean", "description": "Turn on for listing pages. The result becomes an array with one entry per matching item, each following your schema.", "default": false }, "llmProvider": { "title": "LLM provider", "enum": [ "anthropic", "openai" ], "type": "string", "description": "Which API your key belongs to. Anthropic uses the Messages API; OpenAI also covers any OpenAI-compatible endpoint via the base URL field.", "default": "anthropic" }, "llmApiKey": { "title": "LLM API key", "type": "string", "description": "Your own API key. It is stored encrypted, used only for this run's model calls and never written to the dataset. LLM usage is billed by your provider, not by this Actor." }, "model": { "title": "Model", "type": "string", "description": "Model name. Leave empty for a cheap, fast default (Anthropic: claude-haiku-5-5, OpenAI: gpt-4o-mini)." }, "llmBaseUrl": { "title": "API base URL", "pattern": "^https?://.+", "type": "string", "description": "Optional. Override for OpenAI-compatible providers such as OpenRouter, e.g. https://openrouter.ai/api/v1." }, "maxContentChars": { "title": "Max page characters sent to the model", "minimum": 2000, "maximum": 200000, "type": "integer", "description": "Pages are cleaned to text and cut at this length to control model cost. Raise it for very long pages.", "default": 30000 }, "cacheTtlHours": { "title": "Cache results (hours)", "minimum": 0, "maximum": 720, "type": "integer", "description": "Reuse a previous result when the same page content, schema, instructions and model are seen again within this time. 0 disables the cache.", "default": 24 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages are processed in parallel. Lower it if your LLM provider rate-limits you.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Only needed for sites that block data-center traffic." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for AI Web Data Extractor – Any URL to JSON with Your Schema from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: