Smart AI Web Scraper
Pricing
Pay per usage
Go to Apify Store
Smart AI Web Scraper
Unlock the power of Smart AI Web Scraper! Efficiently scrape dynamic content, simulate browser behavior, and extract targeted data.
Smart AI Web Scraper
Pricing
Pay per usage
Unlock the power of Smart AI Web Scraper! Efficiently scrape dynamic content, simulate browser behavior, and extract targeted data.
You can access the Smart AI Web Scraper 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": "1.0", "x-build-id": "to2YJz4NH3N6v1noH" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cockroachapi~smart-ai-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cockroachapi-smart-ai-web-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cockroachapi~smart-ai-web-scraper/runs": { "post": { "operationId": "runs-sync-cockroachapi-smart-ai-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cockroachapi~smart-ai-web-scraper/run-sync": { "post": { "operationId": "run-sync-cockroachapi-smart-ai-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrl", "fields" ], "properties": { "startUrl": { "title": "Start URL", "type": "string", "description": "URL for the scraper to visit" }, "actions": { "title": "Actions (Pre-extraction)", "type": "array", "description": "Define a sequence of actions to perform on the page before extracting data.", "items": { "type": "object", "properties": { "waitBeforeAction": { "title": "Wait for Timeout (in seconds) before the action", "type": "number", "description": "Number of seconds to wait before performing this action. Defaults to 0.5 seconds.", "prefill": 0.5, "minimum": 0, "maximum": 300 }, "action": { "title": "Action (Natural Language)", "type": "string", "description": "Describe the action to perform in natural language (e.g., 'Click the \"Load More\" button', 'Scroll to the bottom of the page', 'Hover over the product image').", "editor": "textfield" }, "waitAfterAction": { "title": "Wait for Timeout (in seconds) after the action", "type": "number", "description": "Number of seconds to wait after performing this action. Defaults to 0.5 seconds.", "prefill": 0.5, "minimum": 0, "maximum": 300 } }, "required": [ "action" ] } }, "fields": { "title": "Fields to Extract", "type": "array", "description": "Define the fields you want to extract with their data types", "items": { "type": "object", "properties": { "fieldName": { "title": "Field Name", "type": "string", "description": "Name of the field to extract", "editor": "textfield" }, "dataType": { "title": "Data Type", "type": "string", "description": "Type of data for this field", "editor": "select", "enum": [ "text", "number", "array", "boolean" ], "enumTitles": [ "Text", "Number", "Array", "Boolean" ], "default": "text", "prefill": "text" } }, "required": [ "fieldName", "dataType" ] } }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings to avoid blocking. Defaults to US Residential proxies." } } }, "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 } } }, "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 } } } } } } } } }}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 Smart AI Web Scraper 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: