{ "openapi": "3.0.1", "info": { "title": "Website Change Tracker | Page Change Detection, RAG Sync", "description": "Extract website changes for RAG sync: only pages added, changed or deleted since your last run, as Markdown chunks with stable IDs to upsert and chunk IDs to delete, not line or section diffs. $1.50 per 1,000 changed pages + $0.50 per 1,000 checked.", "version": "0.1", "x-build-id": "8d2HPafKnqkJ2mqBQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aurelix~website-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aurelix-website-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/aurelix~website-change-monitor/runs": { "post": { "operationId": "runs-sync-aurelix-website-change-monitor", "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/aurelix~website-change-monitor/run-sync": { "post": { "operationId": "run-sync-aurelix-website-change-monitor", "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", "corpusId" ], "properties": { "startUrls": { "title": "Start URLs or sitemaps", "type": "array", "description": "Pages to start from, e.g. ['https://docs.apify.com/academy'], or sitemap URLs ending in .xml, e.g. ['https://example.com/sitemap.xml']. Links are followed within the chosen scope. A URL without http(s):// gets https://.", "items": { "type": "string" } }, "corpusId": { "title": "Corpus ID", "type": "string", "description": "Name of the tracked corpus, e.g. 'apify-academy'. Runs with the same corpus ID compare against each other; a new ID starts a new baseline. 1-60 letters, digits, '-' or '_'. Stored in your account's key-value store 'aurelix-website-change-tracker'.", "default": "default" }, "maxPages": { "title": "Max pages checked per run", "minimum": 1, "maximum": 20000, "type": "integer", "description": "Stop after this many pages are checked (and charged), e.g. 500. Set it above the size of the site so every known page is re-checked each run; known pages not reached are kept, not deleted. Pages blocked by robots.txt, errors and duplicates do not count.", "default": 500 }, "scope": { "title": "Crawl scope", "enum": [ "path", "domain" ], "type": "string", "description": "'path' = only URLs under the start URL's folder (start https://example.com/docs/ tracks /docs/...), 'domain' = the whole site of each start URL (www. and the bare domain count as one site).", "default": "path" }, "includeGlobs": { "title": "Include URL globs", "type": "array", "description": "Track only links whose full URL matches one of these patterns, e.g. ['https://docs.apify.com/academy/**']. '**' matches anything, '*' anything except '/'. Empty = every in-scope URL.", "default": [], "items": { "type": "string" } }, "excludeGlobs": { "title": "Exclude URL globs", "type": "array", "description": "Never follow links whose full URL matches one of these patterns, e.g. ['**/changelog/**', '**?page=*'].", "default": [], "items": { "type": "string" } }, "useSitemaps": { "title": "Also use the sites' sitemaps", "type": "boolean", "description": "Also seed the crawl with in-scope URLs from each start site's sitemap (robots.txt Sitemap lines or /sitemap.xml), so pages that no other page links to are tracked too.", "default": false }, "returnBaseline": { "title": "Return the baseline", "type": "boolean", "description": "On the first run of a corpus, return every page as 'added' with all its chunks (charged per page) to fill your vector database. Off = record the baseline silently and pay only per page checked; later runs return changes either way.", "default": true }, "chunkSize": { "title": "Max chunk size (characters)", "minimum": 300, "maximum": 8000, "type": "integer", "description": "Largest chunk in characters, e.g. 1500 (about 350 tokens). Chunks follow headings and paragraph boundaries. Fixed per corpus at its first run, so chunk IDs stay stable; use a new corpus ID to re-chunk.", "default": 1500 }, "webhookUrl": { "title": "Webhook URL for the delta", "type": "string", "description": "Optional. The changes are also POSTed here as JSON in batches of 25 ({corpus_id, run_id, batch, final, changes}); the last batch has final=true and the run summary. A failing webhook never fails the run." } } }, "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 } } } } } } } } } }