{ "openapi": "3.0.1", "info": { "title": "AI Data Extraction: Any Web Page to JSON Schema", "description": "Extract structured data from a list of URLs with an LLM. Give a JSON Schema or a list of fields and get one JSON record per page, validated against the schema and retried once on failure. Uses your Anthropic, OpenAI or OpenRouter key, with a key-free demo. About $0.01 per page plus your LLM cost.", "version": "0.1", "x-build-id": "DugyUjLT0qYUsgCqE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fernandosord~ai-structured-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fernandosord-ai-structured-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fernandosord~ai-structured-extractor/runs": { "post": { "operationId": "runs-sync-fernandosord-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/fernandosord~ai-structured-extractor/run-sync": { "post": { "operationId": "run-sync-fernandosord-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": [ "startUrls" ], "properties": { "startUrls": { "title": "URLs", "type": "array", "description": "Public web pages to extract from. Each URL becomes one row in the dataset. Duplicates are removed.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "fields": { "title": "Fields (plain language)", "type": "array", "description": "One field per line, optionally followed by a colon and a description, e.g. `price: listed price including currency`. Ignored when a JSON Schema is given.", "items": { "type": "string" } }, "pageType": { "title": "Page type (for plain-language fields)", "enum": [ "single", "list" ], "type": "string", "description": "`single`: one object per page, e.g. a product page. `list`: an array with one object per item, e.g. a search result or category page. With a JSON Schema, use a root of type `array` instead.", "default": "single" }, "jsonSchema": { "title": "JSON Schema", "type": "object", "description": "A JSON Schema for the result of each page. When set, it is used instead of the plain-language fields. Results that do not validate are retried once and then saved with status `validation_failed`." }, "instructions": { "title": "Extra instructions", "type": "string", "description": "Optional notes for the model, e.g. `Prices are in EUR; return numbers without the currency sign.`" }, "llmProvider": { "title": "LLM provider", "enum": [ "anthropic", "openai", "openrouter" ], "type": "string", "description": "Which API your key belongs to.", "default": "anthropic" }, "llmApiKey": { "title": "LLM API key", "type": "string", "description": "Your API key for the chosen provider. Stored encrypted by Apify and never logged or written to the dataset. Leave empty to run the key-free demo." }, "llmModel": { "title": "Model", "type": "string", "description": "Model ID. Leave empty for the default: `claude-haiku-5-5` (Anthropic), `gpt-5.4-mini` (OpenAI), `anthropic/claude-haiku-5.5` (OpenRouter)." }, "maxContentChars": { "title": "Max page characters sent to the LLM", "minimum": 1000, "maximum": 400000, "type": "integer", "description": "The page is converted to markdown first. Longer pages are cut at this length and the row is marked `truncated: true`. Lower it to cut LLM cost.", "default": 60000 }, "contentCssSelector": { "title": "Content CSS selector", "type": "string", "description": "Optional. Only send the matching part of the page to the LLM, e.g. `main` or `#product`. Falls back to the whole body if nothing matches." }, "removeCssSelector": { "title": "Remove CSS selector", "type": "string", "description": "Optional. Elements to drop before extraction, e.g. `nav, footer, .cookie-banner`." }, "useBrowserFallback": { "title": "Render JavaScript pages in a browser when needed", "type": "boolean", "description": "Pages are fetched with plain HTTP first. If the response is an empty JavaScript shell, the page is loaded once more in headless Chromium.", "default": true }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after this many URLs.", "default": 100 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many pages are processed at the same time. Lower it if your LLM account hits rate limits.", "default": 5 }, "extraBlockedDomains": { "title": "Extra domains to skip", "type": "array", "description": "Hostnames to skip in addition to the built-in list (subdomains included), e.g. `example.org`.", "items": { "type": "string" } } } }, "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 } } } } } } } } } }