{ "openapi": "3.0.1", "info": { "title": "Schema Markup Validator - JSON-LD Structured Data Checker", "description": "Validate JSON-LD and Microdata schema markup on a URL list, a sitemap or a whole site against Google rich result rules (Product, FAQ, Recipe, Event, Job...), plus Open Graph. $2 per 1,000 pages.", "version": "0.1", "x-build-id": "JQpVq10a0hkeu0KJk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidytools~structured-data-validator/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidytools-structured-data-validator", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidytools~structured-data-validator/runs": { "post": { "operationId": "runs-sync-tidytools-structured-data-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/tidytools~structured-data-validator/run-sync": { "post": { "operationId": "run-sync-tidytools-structured-data-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", "properties": { "urls": { "title": "URLs or domains", "type": "array", "description": "Main input (fill this, or `startUrls`). Pages to validate (product, article, recipe, event pages...), one per line: full URLs or bare domains. Up to 10,000 per run. Each page is requested exactly as given (only a #fragment is dropped) and keeps your line in inputUrl. With \"Crawl the website\" on, the crawl starts from these pages. Invalid lines become a row with errorType \"invalid_input\" (not charged).", "items": { "type": "string" } }, "startUrls": { "title": "URL list files or request list (optional)", "type": "array", "description": "Older URL field, kept for existing API calls. Use it to upload or link a .txt/.csv file of page URLs. Full URLs only here: bare domains such as example.com go in \"URLs or domains\" above. Both fields are combined.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawl": { "title": "Crawl the website", "type": "boolean", "description": "Follow internal links and validate every page found, up to Max pages. Off: only the listed pages are checked.", "default": false }, "useSitemap": { "title": "Validate the pages in the sitemap", "type": "boolean", "description": "Read the site's XML sitemap (found automatically from robots.txt or /sitemap.xml) and validate every listed page, up to Max pages. Combine with Include URL patterns to check e.g. only /products/ pages.", "default": false }, "sitemapUrl": { "title": "Sitemap URL (optional)", "type": "string", "description": "Use this sitemap instead of finding one automatically. Setting it turns on sitemap validation." }, "maxPages": { "title": "Max pages (crawl or sitemap)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Stop after this many pages. Used when crawling or validating a sitemap.", "default": 100 }, "report": { "title": "Pages in the results", "enum": [ "all", "problems+missing", "problems" ], "type": "string", "description": "Which checked pages go to the dataset. Every page is still checked and charged, and the SUMMARY counts all of them (it also lists pages without structured data in pagesWithoutStructuredData). Values: all = All checked pages; problems+missing = Problems and pages without structured data; problems = Only pages with errors or warnings.", "default": "all" }, "onlyProblems": { "title": "Only report problems (old setting)", "type": "boolean", "description": "Kept for existing API calls: true is the same as \"Pages in the results\" = \"Problems and pages without structured data\" (pages with no structured data are listed too). Ignored when \"Pages in the results\" is set.", "default": false }, "includeJsonLd": { "title": "Include the raw JSON-LD", "type": "boolean", "description": "Add the extracted JSON-LD objects to each result, so you can also use this as a structured data extractor.", "default": true }, "validateMicrodata": { "title": "Also validate Microdata", "type": "boolean", "description": "Validate schema.org Microdata (itemscope/itemprop) with the same rules as JSON-LD. Its issues are marked format: \"microdata\". RDFa types are listed in rdfaTypes but not validated.", "default": true }, "mode": { "title": "Page fetching (HTTP or browser)", "enum": [ "auto", "fast", "browser" ], "type": "string", "description": "\"Auto\" reads the raw HTML (what search engines see first) and uses a real browser only when a site blocks plain requests. \"Browser\" always validates the JavaScript-rendered page, for markup injected by JavaScript (e.g. Google Tag Manager). Values: auto = Auto (recommended); fast = Raw HTML only; browser = Browser (rendered page).", "default": "auto" }, "includeUrlPatterns": { "title": "Include URL patterns (crawl or sitemap)", "type": "array", "description": "Optional glob patterns; only matching pages are validated when crawling or reading a sitemap, e.g. https://example.com/products/**", "items": { "type": "string" } }, "excludeUrlPatterns": { "title": "Exclude URL patterns (crawl or sitemap)", "type": "array", "description": "Optional glob patterns of pages to skip when crawling or reading a sitemap, e.g. **/tag/**", "items": { "type": "string" } }, "maxConcurrency": { "title": "Parallel pages", "minimum": 1, "maximum": 30, "type": "integer", "description": "How many pages are checked at the same time.", "default": 10 }, "httpVia": { "title": "Plain HTTP requests from", "enum": [ "auto", "backend", "direct", "vm" ], "type": "string", "description": "Some sites block requests from data centers. Auto retries from a second network before falling back to a real browser. If both are refused, Auto also tries our second server (Oracle, different IP) before a real browser.", "default": "auto" }, "pageTimeoutSecs": { "title": "Time limit per page (seconds)", "minimum": 0, "maximum": 900, "type": "integer", "description": "A page that takes longer to read (all retries and the browser fallback included) is reported with errorType \"timeout\" and not charged. 0 = no limit.", "default": 120 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Only used for requests sent from Apify's network. Apify proxy usage is billed to your Apify account." } } }, "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 } } } } } } } } } }