Content Freshness Date Extractor
Pricing
from $4.90 / 1,000 content freshness date extractor page auditeds
Extract published, modified, updated, visible, sitemap, and HTTP date signals and flag freshness issues.
You can access the Content Freshness Date Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "aHFBPEXfl0Ij9FotV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~content-freshness-date-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-content-freshness-date-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/junipr~content-freshness-date-extractor/runs": { "post": { "operationId": "runs-sync-junipr-content-freshness-date-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/junipr~content-freshness-date-extractor/run-sync": { "post": { "operationId": "run-sync-junipr-content-freshness-date-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": { "startUrls": { "title": "Start Urls", "type": "array", "description": "Public page URLs to fetch and audit. Keep runs bounded with maxPages and allowedDomains.", "items": { "type": "string" }, "default": [] }, "sitemapUrls": { "title": "Sitemap Urls", "type": "array", "description": "XML sitemap URLs whose listed pages should be sampled for this audit.", "items": { "type": "string" }, "default": [] }, "htmlInputs": { "title": "Html Inputs", "type": "array", "description": "Inline HTML documents to audit without fetching live pages.", "items": { "type": "object" }, "default": [] }, "headerInputs": { "title": "Header Inputs", "type": "array", "description": "Supplied HTTP header records to audit alongside HTML inputs.", "items": { "type": "object" }, "default": [] }, "allowedDomains": { "title": "Allowed Domains", "type": "array", "description": "Optional hostname allowlist used to keep crawls constrained to approved domains.", "items": { "type": "string" }, "default": [] }, "maxPages": { "title": "Max Pages", "minimum": 1, "maximum": 500, "type": "integer", "description": "Maximum number of pages or records to process in one run.", "default": 25 }, "maxDepth": { "title": "Max Depth", "minimum": 0, "maximum": 5, "type": "integer", "description": "Maximum crawl depth from supplied start URLs.", "default": 1 }, "staleAfterDays": { "title": "Stale After Days", "minimum": 0, "type": "integer", "description": "Number of days after which detected content dates should be treated as stale.", "default": 0 }, "dateTypes": { "title": "Date Types", "type": "array", "description": "Date signal types to extract from visible text, metadata, structured data, or sitemaps.", "items": { "type": "string" }, "default": [] }, "includeVisibleDateExtraction": { "title": "Include Visible Date Extraction", "type": "boolean", "description": "Extract visible publication, modified, and review date text from page content.", "default": true }, "includeJsonLdDates": { "title": "Include Json Ld Dates", "type": "boolean", "description": "Extract datePublished and dateModified values from JSON-LD when present.", "default": true }, "includeSitemapLastmod": { "title": "Include Sitemap Lastmod", "type": "boolean", "description": "Include sitemap lastmod values as freshness evidence when available.", "default": true }, "timeoutMs": { "title": "Timeout Ms", "minimum": 500, "maximum": 30000, "type": "integer", "description": "Per-request timeout in milliseconds for live fetches.", "default": 15000 }, "maxChargeUsd": { "title": "Maximum charge (USD)", "minimum": 0, "maximum": 1000, "type": "number", "description": "Stop before paid output would exceed this fixed-inclusive PPE limit.", "default": 10 } } }, "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 } } } } } } } } }}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 Content Freshness Date Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: