{ "openapi": "3.0.1", "info": { "title": "SEO/GEO - Schema Markup Scraper", "description": "This actor to fetches JSON-LD/Schema Markup from Multiple URLs & checks whether the page contains markups for the following types: AggregateRating, Article, Event, FAQPage, LocalBusiness, Organization, Person, Product, & Review. Schema Markup helps search and generative engines find & read webpages.", "version": "0.0", "x-build-id": "qQg5htAWaihIR9qDs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/wisteria_banjo~schema-markup-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-wisteria_banjo-schema-markup-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/wisteria_banjo~schema-markup-scraper/runs": { "post": { "operationId": "runs-sync-wisteria_banjo-schema-markup-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/wisteria_banjo~schema-markup-scraper/run-sync": { "post": { "operationId": "run-sync-wisteria_banjo-schema-markup-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "URLs", "type": "array", "description": "One or more URLs of the pages where the crawler will start. Note that the Actor will additionally only crawl sub-pages of these URLs. For example, for the start URL `https://www.example.com/blog`, it will crawl pages like `https://example.com/blog/article-1`, but will skip `https://example.com/docs/something-else`.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "crawlerType": { "title": "Crawler type", "enum": [ "playwright:chrome", "cheerio", "jsdom" ], "type": "string", "description": "Select the crawling engine:\n- **Headless web browser** (default) - Useful for modern websites with anti-scraping protections and JavaScript rendering. It recognizes common blocking patterns like CAPTCHAs and automatically retries blocked requests through new sessions. However, running web browsers is more expensive as it requires more computing resources and is slower. It is recommended to use at least 8 GB of RAM.\n- **Raw HTTP client** - High-performance crawling mode that uses raw HTTP requests to fetch the pages. It is faster and cheaper, but it might not work on all websites.", "default": "playwright:chrome" }, "maxCrawlDepth": { "title": "Max crawling depth", "minimum": 0, "type": "integer", "description": "The maximum number of links starting from the start URL that the crawler will recursively descend. The start URLs have a depth of 0, the pages linked directly from the start URLs have a depth of 1, and so on.\n\nThis setting is useful to prevent accidental crawler runaway. By setting it to 0, the Actor will only crawl start URLs.", "default": 20 }, "maxCrawlPages": { "title": "Max pages", "minimum": 0, "type": "integer", "description": "The maximum number pages to crawl. It includes the start URLs, pagination pages, pages with no content, etc. The crawler will automatically finish after reaching this number. This setting is useful to prevent accidental crawler runaway.", "default": 9999999 } } }, "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 } } } } } } } } } }