{ "openapi": "3.0.1", "info": { "title": "AI Web Data Extractor", "description": "Extract structured data from any website by saying what you want in plain English. Products, prices, jobs, leads, news, tables or direct answers, as clean JSON, CSV or Excel. No selectors, no code. Works with AI agents via MCP. Pay per page; failed pages are free.", "version": "1.1", "x-build-id": "Rtjh4C5ecvKuAXzsm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datacortex~ai-web-data-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datacortex-ai-web-data-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datacortex~ai-web-data-extractor/runs": { "post": { "operationId": "runs-sync-datacortex-ai-web-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datacortex~ai-web-data-extractor/run-sync": { "post": { "operationId": "run-sync-datacortex-ai-web-data-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "ask" ], "properties": { "urls": { "title": "URLs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "Public web pages to read, one per line. A list page (search results, a category, a directory) returns one row per item and follows its next pages.", "items": { "type": "string" } }, "ask": { "title": "What do you want?", "minLength": 1, "maxLength": 4000, "type": "string", "description": "Plain English. Name the fields for a list ('title, price and rating of every book'), describe one record ('product name, price, SKU and stock status'), or ask a question ('how many books are in the Travel category?'). The same request runs on every URL." }, "outputType": { "title": "Output type", "enum": [ "auto", "rows", "record", "reply" ], "type": "string", "description": "Auto reads it from your wording. Rows: one row per item on a list page, following next pages. Record: one row for the page itself. Reply: a direct answer to a question, reading linked pages if needed.", "default": "auto" }, "followLinks": { "title": "Follow links (open each item's page)", "maxLength": 500, "type": "string", "description": "Optional. Say which links to open on each URL, for example 'every product link' or 'every job posting'. Each page found is then asked What do you want? on its own, one row per page, with foundOn saying where it was found. Leave empty to read only the URLs above." }, "maxItems": { "title": "Max item pages", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Most item pages Follow links opens in this run, across all URLs. Each item page is usually one billed page.", "default": 100 }, "maxPagesPerUrl": { "title": "Max pages per URL", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Most pages one URL may read. Leave empty for the defaults: 10 for rows, 5 for a reply, 1 for a record. With Follow links, this is how many list pages to read for links (default 1); each item page reads 1. Each page fetched is one billed page; failed pages are free." }, "residentialNetwork": { "title": "Residential network", "type": "boolean", "description": "Fetch through home-broadband IP addresses, for sites that turn data-centre visitors away. Same price per page.", "default": false }, "country": { "title": "Country", "maxLength": 2, "type": "string", "description": "Two-letter country code to browse from on the residential network, for example US, GB or DE. Used for rows only." }, "maxConcurrency": { "title": "URLs at once", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many URLs to work on at the same time (1–10).", "default": 3 } } }, "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 } } } } } } } } } }