{ "openapi": "3.0.1", "info": { "title": "Structured Web Extractor - JSON Schema with Evidence", "description": "Turn public web pages into records that match your JSON Schema. Every value carries its evidence: the JSON-LD path or the exact quote it came from. Values without evidence are rejected, and required facts that are missing leave the record partial.", "version": "0.0", "x-build-id": "oUXyMithYO8PTafiT" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/leadproof~structured-web-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-leadproof-structured-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/leadproof~structured-web-extractor/runs": { "post": { "operationId": "runs-sync-leadproof-structured-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/leadproof~structured-web-extractor/run-sync": { "post": { "operationId": "run-sync-leadproof-structured-web-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "sourceMode": { "title": "Source", "enum": [ "urls", "records", "dataset" ], "type": "string", "description": "Where the page content comes from. Only the selected source is used.", "default": "urls" }, "urls": { "title": "Page URLs", "type": "array", "description": "Public http(s) pages, one request each (static HTML, no browser). robots.txt is respected by default. Private, local and cloud-metadata addresses are refused, including after redirects.", "items": { "type": "string" } }, "records": { "title": "Page records or text", "type": "array", "description": "Objects with url (absolute, used as the evidence source) and at least one of text, markdown, html (up to 2 MB) or structuredData; optional inputId and title. PageRecord v1 objects are accepted as they are." }, "datasetId": { "title": "Dataset ID", "type": "string", "description": "Dataset of PageRecord v1 items, for example a page reader run's output. Declared as a dataset resource with READ permission, so a limited-permission run can read the dataset you select." }, "datasetOffset": { "title": "Dataset offset", "minimum": 0, "type": "integer", "description": "Skip this many dataset items first.", "default": 0 }, "schemaPreset": { "title": "Schema preset", "enum": [ "product", "local-business", "custom" ], "type": "string", "description": "Built-in schemas with deterministic bindings. Choose custom to use your own schema." }, "extractionSchema": { "title": "Extraction schema (custom)", "type": "object", "description": "JSON Schema subset: object root; types string, number, integer, boolean, object, array, and [type, \"null\"]; keywords properties, required, items, enum, format (email, uri, date, date-time), minimum, maximum, minLength, maxLength, minItems, maxItems, title, description, x-extract. Refused: $ref, anyOf/oneOf/allOf, pattern, default, const, examples, open objects. Limits: 16 KB, depth 5, 80 properties, 60 fields. See README." }, "mode": { "title": "Extraction mode", "enum": [ "deterministic", "llm", "auto" ], "type": "string", "description": "Deterministic never calls a model. LLM and auto call the selected model, bounded by the LLM budget. Every AI value must quote the page or it is rejected.", "default": "deterministic" }, "llmProvider": { "title": "AI provider", "enum": [ "apify-openrouter", "openrouter" ], "type": "string", "description": "The Apify proxy uses this run's own Apify token and bills token usage to the account that runs the Actor. With openrouter, your key is sent only to openrouter.ai.", "default": "apify-openrouter" }, "llmModel": { "title": "Model", "type": "string", "description": "OpenRouter model ID with structured output support and a fixed token price. Checked against the provider catalog before any call.", "default": "openai/gpt-4.1-mini" }, "llmApiKey": { "title": "OpenRouter API key", "type": "string", "description": "Only for provider openrouter. Stored encrypted by Apify." }, "maxLlmCostUsd": { "title": "LLM budget per run (USD)", "minimum": 0.01, "maximum": 20, "type": "number", "description": "Each model call reserves its worst-case price first; calls that would exceed this budget are not sent and their records are skipped. This budget is separate from the Actor's maximum charge per run.", "default": 0.25 }, "maxInputChars": { "title": "Page characters sent to the model", "minimum": 1000, "maximum": 60000, "type": "integer", "description": "Longer pages are cut at a line boundary and flagged content_truncated.", "default": 20000 }, "maxOutputTokens": { "title": "Max output tokens per call", "minimum": 200, "maximum": 4000, "type": "integer", "description": "Output that hits this limit is reported as model_output_truncated, never repaired.", "default": 1500 }, "interpretedValues": { "title": "Interpreted values", "enum": [ "separate", "include" ], "type": "string", "description": "A boolean such as inStock, or an enum value the page words differently, is the model's reading of a quote, not text found on the page. It is checked (the quote must be about the field and must not contradict the value) but never proven.", "default": "separate" }, "recordTimeoutSecs": { "title": "Time limit per record (seconds)", "minimum": 20, "maximum": 600, "type": "integer", "description": "Reading plus extraction of one record, including model retries. A record over the limit fails with record_timeout; the run continues.", "default": 120 }, "maxRecords": { "title": "Maximum records", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Hard limit for the selected source, API and Console alike.", "default": 50 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Pages processed at once. Requests to one host are spaced at least 1 second apart.", "default": 4 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Per page request, including redirects.", "default": 30 }, "maxPageBytes": { "title": "Maximum page size (bytes)", "minimum": 50000, "maximum": 5000000, "type": "integer", "description": "Larger responses fail with response_too_large.", "default": 2000000 }, "respectRobotsTxt": { "title": "Respect robots.txt", "type": "boolean", "description": "Skip URLs that the site's robots.txt disallows.", "default": true }, "saveSourceRecords": { "title": "Save source page records", "type": "boolean", "description": "Store each source PageRecord as PAGE- in the key-value store, so every recordPath in the evidence can be audited. Adds storage use.", "default": false }, "readerActorId": { "title": "Page reader Actor (optional)", "type": "string", "description": "Read URLs through a PageRecord v1 reader Actor instead of the built-in fetcher. It runs as a separate run on your account." }, "readerUrlsField": { "title": "Reader URL field", "type": "string", "description": "Input field name the reader Actor expects for its URL list.", "default": "urls" }, "readerMaxTotalChargeUsd": { "title": "Reader Actor budget per run (USD)", "minimum": 0, "maximum": 100, "type": "number", "description": "Maximum this run lets the reader Actor charge. It is a separate run with its own price, so this run's maximum charge does not cover it. 0 means the reader may not charge at all.", "default": 1 } } }, "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 } } } } } } } } } }