Structured Web Scraper
Pricing
Pay per usage
Go to Apify Store
Structured Web Scraper
Extract articles, products, headings, images and links from any website in clean structured JSON format. Supports multiple URLs per run.
Structured Web Scraper
Pricing
Pay per usage
Extract articles, products, headings, images and links from any website in clean structured JSON format. Supports multiple URLs per run.
You can access the Structured 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 Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "gGmInHyc3oyNGoAEr" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scalloped_scotspine~structured-web-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scalloped_scotspine-structured-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scalloped_scotspine~structured-web-scraper/runs": { "post": { "operationId": "runs-sync-scalloped_scotspine-structured-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scalloped_scotspine~structured-web-scraper/run-sync": { "post": { "operationId": "run-sync-scalloped_scotspine-structured-web-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "URLs to scrape", "type": "array", "description": "List of URLs to scrape. Supports any website.", "items": { "type": "string" } }, "contentType": { "title": "Content type to extract", "enum": [ "article", "product", "search-results", "all" ], "type": "string", "description": "Type of content to prioritize during extraction.", "default": "article" }, "extractImages": { "title": "Extract images", "type": "boolean", "description": "Include image URLs and alt text in the output.", "default": true }, "extractLinks": { "title": "Extract outbound links", "type": "boolean", "description": "Include all outbound links found on the page.", "default": false }, "maxItems": { "title": "Max items per page", "type": "integer", "description": "Maximum number of items to extract per page before filtering.", "default": 30 }, "useAiFilter": { "title": "Use AI filter", "type": "boolean", "description": "Enable AI-powered content filtering. Each article is validated before inclusion.", "default": false }, "aiProvider": { "title": "AI provider", "enum": [ "openai", "ollama" ], "type": "string", "description": "Which LLM to use for filtering.", "default": "openai" }, "openaiApiKey": { "title": "OpenAI API key", "type": "string", "description": "Your OpenAI API key. Get one at platform.openai.com" }, "ollamaUrl": { "title": "Ollama server URL", "type": "string", "description": "URL of your Ollama server (e.g. http://your-server:11434). Must be reachable from Apify cloud.", "default": "http://localhost:11434" }, "aiModel": { "title": "AI model", "type": "string", "description": "Model to use. OpenAI: gpt-4o-mini, gpt-4o. Ollama: llama3, mistral, etc.", "default": "gpt-4o-mini" }, "filterGoal": { "title": "Filter goal", "type": "string", "description": "Instruction to the AI for what to keep. E.g. 'only tech/programming articles', 'no political content', 'prioritize in-depth technical posts'.", "default": "Only keep high-quality, substantive articles. Reject clickbait, ads, and low-effort content." } } }, "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 Structured 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: