{ "openapi": "3.0.1", "info": { "title": "Schema Extractor", "description": "Turn any URL(s) plus a JSON Schema into validated, typed records. Fetches each page, reduces it to its readable core, asks an LLM to fill in your schema, and validates the result - a fraction of the cost of a full AI web scraper.", "version": "0.1", "x-build-id": "LeQJ07wZaHhWUEBlT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/roseapps~schema-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-roseapps-schema-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/roseapps~schema-extractor/runs": { "post": { "operationId": "runs-sync-roseapps-schema-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/roseapps~schema-extractor/run-sync": { "post": { "operationId": "run-sync-roseapps-schema-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "schema" ], "properties": { "startUrls": { "title": "Start URLs", "type": "array", "description": "One or more pages to extract data from.", "default": [ { "url": "https://example.com" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "schema": { "title": "JSON Schema", "type": "object", "description": "A JSON Schema describing the record you want back from each page. Every field the LLM returns must validate against it.", "default": { "type": "object", "properties": { "title": { "type": "string" }, "price": { "type": "number" } } } }, "maxPages": { "title": "Max pages", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of pages to fetch and extract (including any pages discovered via followLinksMatching).", "default": 20 }, "followLinksMatching": { "title": "Follow links matching (regex)", "type": "string", "description": "Optional regular expression. When set, same-site links found on each fetched page that match it are crawled too (breadth-first), up to maxPages. Leave empty to only process startUrls." }, "llmProvider": { "title": "LLM provider", "enum": [ "anthropic", "openai", "bedrock", "none" ], "type": "string", "description": "Which LLM backend to use for extraction.", "default": "none" }, "model": { "title": "Model", "type": "string", "description": "Model name/ID to use. Defaults per provider: anthropic=claude-haiku-4-5, openai=gpt-4o-mini, bedrock=anthropic.claude-haiku-4-5-20251001-v1:0. Only honoured when you supply your own apiKey (BYOK) -- in bundled mode (no apiKey), the cheap default model is always used regardless of this field." }, "apiKey": { "title": "API key (bring your own)", "type": "string", "description": "Your own API key for the selected provider. If omitted, the Actor's bundled key is used (billed at the bundled price) where available." }, "awsRegion": { "title": "AWS region (Bedrock only)", "type": "string", "description": "AWS region for the Bedrock provider, e.g. us-east-1. Falls back to env var AWS_REGION." }, "awsAccessKeyId": { "title": "AWS access key ID (Bedrock only)", "type": "string", "description": "Falls back to env var AWS_ACCESS_KEY_ID." }, "awsSecretAccessKey": { "title": "AWS secret access key (Bedrock only)", "type": "string", "description": "Falls back to env var AWS_SECRET_ACCESS_KEY." }, "extractionInstructions": { "title": "Extraction instructions", "type": "string", "description": "Optional free-text guidance for the LLM, e.g. \"prices are in EUR\" or \"skip out-of-stock items\"." }, "multipleRecordsPerPage": { "title": "Multiple records per page", "type": "boolean", "description": "Turn on if a single page can contain several records matching the schema (e.g. a listing page). The LLM is asked for a JSON array and each element becomes its own output row.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 5, "type": "integer", "description": "Maximum number of pages fetched/extracted in parallel.", "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 } } }, "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 } } } } } } } } } }