{ "openapi": "3.0.1", "info": { "title": "AI Web Scraper — Structured Data From Any URL", "description": "Extract structured data from any website using an LLM and your own field schema — no CSS selectors. Give it URLs and the fields you want; get clean JSON rows back. Works on blogs, job boards, product pages, listings, and more.", "version": "1.0", "x-build-id": "SnzdAntHYgc5ef1qx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/muhammadafzal~ai-web-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-muhammadafzal-ai-web-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/muhammadafzal~ai-web-extractor/runs": { "post": { "operationId": "runs-sync-muhammadafzal-ai-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/muhammadafzal~ai-web-extractor/run-sync": { "post": { "operationId": "run-sync-muhammadafzal-ai-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "The page URLs to extract data from. Use this when the user provides specific pages (article, product, listing, profile). Each URL is fetched and passed to the LLM for extraction.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "fields": { "title": "Fields to Extract", "type": "array", "description": "The data points to pull from each page. Each field has a name and a short description telling the model what to capture. Example: [{\"name\":\"title\",\"description\":\"the product title\"},{\"name\":\"price\",\"description\":\"price in USD as a number\",\"type\":\"number\"}].", "default": [ { "name": "text", "description": "the full quote text" }, { "name": "author", "description": "name of the person who said the quote" }, { "name": "tags", "description": "list of tag labels on the quote", "type": "array" } ] }, "listMode": { "title": "Extract a List of Items per Page", "type": "boolean", "description": "Turn ON when each page contains MANY repeating items (e.g., a product grid, search results, a list of quotes) — the actor returns one row per item. Turn OFF when each page is a single record (e.g., one product detail page).", "default": true }, "model": { "title": "Extraction Model", "type": "string", "description": "Internal: OpenRouter model used for extraction. Managed by the actor; not user-editable.", "default": "openai/gpt-4o-mini" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of output rows to produce across all pages (cost control).", "default": 100 }, "maxCrawlPages": { "title": "Max Pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to fetch and send to the LLM (cost control).", "default": 20 }, "maxContentChars": { "title": "Max Content Characters per Page", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "How much page text to send to the model (controls token cost). Longer = more complete but more expensive.", "default": 12000 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy settings for fetching pages. Datacenter proxy is enabled by default; switch to residential for sites that block datacenter IPs.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }