Orphan Page Finder
Pricing
from $4.90 / 1,000 page auditeds
Go to Apify Store
Orphan Page Finder
Find orphan pages by comparing sitemap URLs, crawl-discovered URLs, and internal link graph relationships.
Orphan Page Finder
Pricing
from $4.90 / 1,000 page auditeds
Find orphan pages by comparing sitemap URLs, crawl-discovered URLs, and internal link graph relationships.
You can access the Orphan Page Finder programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "Gxok1MsrIyNGHbxKq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/junipr~orphan-page-finder/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-junipr-orphan-page-finder", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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~orphan-page-finder/runs": { "post": { "operationId": "runs-sync-junipr-orphan-page-finder", "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~orphan-page-finder/run-sync": { "post": { "operationId": "run-sync-junipr-orphan-page-finder", "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": { "records": { "title": "Records To Check", "type": "array", "description": "Records, snapshots, or source observations to process. Defaults to a tiny deterministic fixture.", "items": { "type": "object" }, "default": [ { "sourceId": "linked-page", "sourceUrl": "https://example.com/services", "title": "Linked service page", "description": "Page is present in sitemap and has three incoming internal links.", "category": "crawl graph", "keywords": [], "metadata": { "url": "https://example.com/services", "inSitemap": true, "incomingLinks": 3, "discovered": true } }, { "sourceId": "orphan-page", "sourceUrl": "https://example.com/old-offer", "title": "Sitemap only orphan page", "description": "orphan sitemap only page with incomingLinks:0.", "category": "crawl graph", "keywords": [ "orphan", "sitemap only" ], "metadata": { "url": "https://example.com/old-offer", "inSitemap": true, "incomingLinks": 0, "discovered": false } } ] }, "urls": { "title": "Crawl Start URLs", "type": "array", "description": "Entry pages for the capped internal-link crawl.", "items": { "type": "string" }, "default": [] }, "sitemapUrls": { "title": "Sitemap URLs", "type": "array", "description": "XML sitemap or sitemap-index URLs to compare with the internal crawl graph.", "items": { "type": "string" }, "default": [] }, "fetchUrls": { "title": "Run Sitemap Crawl", "type": "boolean", "description": "Fetch sitemaps and crawl internal links. Default is false for deterministic fixture runs.", "default": false }, "fetchTimeoutMs": { "title": "Request Timeout (ms)", "minimum": 1000, "maximum": 30000, "type": "integer", "description": "Timeout for each sitemap or page request.", "default": 12000 }, "maxPages": { "title": "Max Crawl Pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum internal pages fetched while building the link graph.", "default": 10 }, "watchTerms": { "title": "Watch Terms", "type": "array", "description": "Keywords or topics used to flag relevant records.", "items": { "type": "string" }, "default": [ "orphan", "sitemap only", "unlinked" ] }, "includeReport": { "title": "Include Report Artifacts", "type": "boolean", "description": "Write JSON and Markdown report artifacts to the key-value store.", "default": true }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum records to process in one run.", "default": 2 }, "maxTextBytes": { "title": "Max Text Bytes", "minimum": 100, "maximum": 2000000, "type": "integer", "description": "Maximum searchable text bytes per record.", "default": 500000 }, "dryRun": { "title": "Dry Run", "type": "boolean", "description": "Validate input and write a dry-run summary without PPE charges or dataset output.", "default": false }, "debug": { "title": "Debug Logs", "type": "boolean", "description": "Enable debug logging.", "default": false } } }, "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 Orphan Page Finder 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: