Schema Markup Scraper & SEO Auditor
Pricing
from $3.00 / 1,000 results
Extract JSON-LD, Microdata, RDFa, Open Graph & Twitter Cards. Runs a 0-100 SEO audit β checks canonical, hreflang, headings, image alt, EEAT author signals. Detects 80+ schema.org types including LocalBusiness with NAP, geo coordinates, and Google Place IDs.
You can access the Schema Markup Scraper & SEO Auditor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, youβll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "Rb9UdDT4jejoYefLd" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/autofacts~metadata-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-autofacts-metadata-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/autofacts~metadata-scraper/runs": { "post": { "operationId": "runs-sync-autofacts-metadata-scraper", "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/autofacts~metadata-scraper/run-sync": { "post": { "operationId": "run-sync-autofacts-metadata-scraper", "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", "type": "array", "description": "URLs to start crawling from", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "followLinks": { "title": "Follow Links", "type": "boolean", "description": "Also crawl links found on the start pages, up to Max Depth. Off by default: without it the Actor fetches exactly the URLs you submit.", "default": false }, "maxDepth": { "title": "Max Depth", "minimum": 0, "type": "integer", "description": "How many link hops past a start URL to follow. Only applies when Follow Links is on. 0 means the start URLs only.", "default": 0 }, "maxRequestsPerCrawl": { "title": "Max Requests Per Crawl", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum number of pages that the scraper will open. The crawl will stop when this limit is reached.", "default": 100 }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of pages that will be processed in parallel.", "default": 10 }, "extractMetaTags": { "title": "Extract Meta Tags", "type": "boolean", "description": "Extract all meta tags from the page", "default": true }, "extractSeoAnalysis": { "title": "Extract SEO Analysis", "type": "boolean", "description": "Extract SEO signals: canonical URL, hreflang (with validation), robots meta, heading hierarchy, author/EEAT info, image alt audit, article metadata, breadcrumbs, Dublin Core, viewport, and charset", "default": true }, "extractGeoData": { "title": "Extract Geo/Local SEO Data", "type": "boolean", "description": "Extract geo meta tags, LocalBusiness schema, NAP (Name/Address/Phone), and Google Maps/Place ID references", "default": true }, "computeSeoScore": { "title": "Compute SEO Score", "type": "boolean", "description": "Run an SEO audit producing a 0-100 score and list of issues aligned with Google ranking signals", "default": true }, "extractRdfa": { "title": "Extract RDFa", "type": "boolean", "description": "Extract RDFa structured data (niche format, opt-in)", "default": false }, "extractHCard": { "title": "Extract hCard/vCard", "type": "boolean", "description": "Extract hCard/vCard microformat contact data (niche format, opt-in)", "default": false }, "proxy": { "title": "Proxy configuration", "type": "object", "description": "Select proxies to be used by your crawler." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Schema Markup Scraper & SEO Auditor from the options below:
If youβd like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: