{ "openapi": "3.0.1", "info": { "title": "Metascraper Metadata Extractor", "description": "Extract normalized page metadata with Metascraper rule bundles, raw meta-tag provenance, Open Graph, Twitter cards, JSON-LD, canonicals, and content hints.", "version": "0.1", "x-build-id": "BYRM1viQvfWVgtIDi" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/khadinakbar~metascraper-metadata-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-khadinakbar-metascraper-metadata-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/khadinakbar~metascraper-metadata-extractor/runs": { "post": { "operationId": "runs-sync-khadinakbar-metascraper-metadata-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/khadinakbar~metascraper-metadata-extractor/run-sync": { "post": { "operationId": "run-sync-khadinakbar-metascraper-metadata-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Page URLs", "uniqueItems": true, "type": "array", "description": "Public HTTP or HTTPS page URLs to inspect, such as 'https://example.com/article'. Provide a plain list when calling from an agent or API. Up to 100 distinct URLs are accepted and duplicates are removed. This is not a sitemap or domain crawler; use startUrls only as an equivalent Apify-style input.", "items": { "type": "string" }, "default": [] }, "startUrls": { "title": "Page URLs (Apify format)", "type": "array", "description": "Alternative Apify request-list input using objects like {\"url\":\"https://example.com\"}. It is merged with the urls list and is useful in the Console. Up to 100 distinct URLs are accepted after merging. This does not discover or crawl links beyond the supplied pages.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxResults": { "title": "Maximum pages to process", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum number of distinct supplied pages to fetch, from 1 to 100. The default is 25 so an agent has a predictable cost cap. URLs after this limit are skipped and reported in the run summary. This is not a pagination setting because the Actor does not follow page links.", "default": 25 }, "includeRawMetaTags": { "title": "Include raw meta tags", "type": "boolean", "description": "Include page-authored head metadata grouped by its name, property, or http-equiv key. The default true preserves provenance for audits and debugging. Set false for a smaller response that contains only normalized Metascraper fields. This does not return page text, cookies, scripts, or form data.", "default": true }, "includeJsonLd": { "title": "Include JSON-LD blocks", "type": "boolean", "description": "Include valid JSON-LD values from application/ld+json script blocks, capped at 20 blocks per page. The default true is useful for structured-data checks. Invalid JSON-LD is counted in warnings rather than evaluated or repaired. This is not schema validation or rich-result eligibility testing.", "default": true }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 60, "type": "integer", "description": "Maximum time allowed for one page request, from 5 to 60 seconds. The default 30 seconds covers ordinary public pages while preventing stuck runs. Raise it only for known slow pages. This does not control the overall Actor run timeout.", "default": 30 }, "maxConcurrency": { "title": "Maximum concurrent requests", "minimum": 1, "maximum": 10, "type": "integer", "description": "Number of supplied pages to fetch in parallel, from 1 to 10. The default 5 is conservative for sites that rate limit metadata reads. Lower it for a single domain or fragile target. This is not a request rate guarantee because response times vary.", "default": 5 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Route public page requests through Apify Proxy when enabled. The default false uses the Actor container network and avoids proxy usage costs. Enable only for targets that need an allowed geography or routinely rate-limit direct requests. This setting does not bypass logins, paywalls, or access controls.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional Apify Proxy configuration, such as a group or country code, used only when Use Apify Proxy is enabled. Leave the default empty object for direct requests. This setting is advanced and never exposes a proxy password in output. It is not a generic arbitrary proxy URL field.", "default": {} } } }, "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 } } } } } } } } } }