{ "openapi": "3.0.1", "info": { "title": "Schema.org Extractor & Validator", "description": "Extract and validate Schema.org JSON-LD, Microdata, and RDFa from HTML pages.", "version": "1.0", "x-build-id": "DRDPYcrn497s04645" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ib4ngz~schema-org-extractor-validator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ib4ngz-schema-org-extractor-validator", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ib4ngz~schema-org-extractor-validator/runs": { "post": { "operationId": "runs-sync-ib4ngz-schema-org-extractor-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ib4ngz~schema-org-extractor-validator/run-sync": { "post": { "operationId": "run-sync-ib4ngz-schema-org-extractor-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Start URLs", "minItems": 1, "type": "array", "description": "One or more HTTP(S) pages to analyze.", "default": [ { "url": "https://apify.com" } ], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxRequestsPerCrawl": { "title": "Maximum requests", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum total pages processed during one run. All supplied Start URLs are always processed, even when their count is higher.", "default": 100 }, "maxCrawlDepth": { "title": "Maximum crawl depth", "minimum": 0, "maximum": 10, "type": "integer", "description": "0 analyzes only supplied URLs; higher values follow links by that many levels.", "default": 0 }, "sameDomainOnly": { "title": "Stay on originating hostname", "type": "boolean", "description": "When following links, only enqueue URLs on the hostname of the originating start URL.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Configure Apify Proxy or provide custom proxy URLs. Apify Proxy access depends on your plan.", "default": { "useApifyProxy": false } }, "includeJsonLd": { "title": "Extract JSON-LD", "type": "boolean", "description": "Extract application/ld+json blocks.", "default": true }, "includeMicrodata": { "title": "Extract Microdata", "type": "boolean", "description": "Extract Schema.org itemscope/itemprop markup.", "default": true }, "includeRdfa": { "title": "Extract RDFa", "type": "boolean", "description": "Extract common Schema.org RDFa markup.", "default": true }, "includeRaw": { "title": "Include raw source", "type": "boolean", "description": "Include bounded raw structured-data fragments. Full page HTML is never emitted.", "default": false }, "validate": { "title": "Validate vocabulary", "type": "boolean", "description": "Validate types, properties, inheritance, and conservative range hints.", "default": true }, "includeWarnings": { "title": "Include warning details", "type": "boolean", "description": "Emit detailed warning arrays. Summary counts always include generated warnings.", "default": true }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Maximum time allowed for one HTTP request.", "default": 30 } } }, "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 } } } } } } } } } }