{ "openapi": "3.0.1", "info": { "title": "Dataset Change Tracker", "description": "Compare two runs of your scraper and get only the new, changed and removed items. Ignores fields you choose, shows which fields changed and their old values, and can remember the last run by storing only hashes of the items.", "version": "0.1", "x-build-id": "5kyhLcx7trjipZ6fp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/quietworkslab~dataset-change-tracker/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-quietworkslab-dataset-change-tracker", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/quietworkslab~dataset-change-tracker/runs": { "post": { "operationId": "runs-sync-quietworkslab-dataset-change-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/quietworkslab~dataset-change-tracker/run-sync": { "post": { "operationId": "run-sync-quietworkslab-dataset-change-tracker", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetId": { "title": "Current dataset", "type": "string", "description": "The dataset to check, usually the newest run of your scraper. Leave it empty to try the Actor on built-in sample data. When this Actor runs after your scraper from the scraper's Integrations tab, set it to {{resource.defaultDatasetId}}. Hidden fields (names starting with #) are not compared." }, "previousDatasetId": { "title": "Previous dataset", "type": "string", "description": "The older dataset to compare with. You can leave it empty if you set \"Remember the last run in this store\" below: the Actor then compares with the fingerprint saved by its previous run." }, "stateStoreName": { "title": "Remember the last run in this store", "pattern": "^[a-zA-Z0-9]([a-zA-Z0-9-]*[a-zA-Z0-9])?$", "type": "string", "description": "Optional. Name of a key-value store in your account, for example my-shop-tracker (not \"default\"). After each complete run the Actor saves a fingerprint there: 64-bit hashes of each item's key and content, not the items themselves. Note that a key that is easy to guess, such as a URL pattern or a sequential ID, can be confirmed by hashing guesses. The next run compares with the fingerprint, so you don't have to pick the previous dataset. The first run with a new name reports every item as added. Do not use the same name in two runs at the same time. Letters, digits and hyphens only." }, "keyFields": { "title": "Key fields", "type": "array", "description": "Fields that identify the same item in both datasets, for example url, id or sku. Use dots for nested fields (product.id). With several fields, the combination is the key. If fewer than half of the first 100 items have a value in the key fields, the run stops before charging and lists the fields it found. If empty, whole items are compared and only added and removed items are reported.", "items": { "type": "string" } }, "ignoreFields": { "title": "Fields to ignore", "type": "array", "description": "Fields that change on every run and should not count as a change, for example scrapedAt or a session ID. Use dots for nested fields (meta.loadedAt); a nested path also applies to every element of a list (offers.seenAt).", "items": { "type": "string" } }, "changeTypes": { "title": "Change types to output", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Which changes to write to the dataset. All of them are still counted in the summary (OUTPUT).", "items": { "type": "string", "enum": [ "added", "changed", "removed" ], "enumTitles": [ "Added items", "Changed items", "Removed items" ] }, "default": [ "added", "changed", "removed" ] }, "ignoreArrayOrder": { "title": "Ignore the order of items in lists", "type": "boolean", "description": "If checked, a list with the same elements in a different order (for example tags or image URLs) does not count as a change.", "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 }, "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 } } } } } } } } } }