{ "openapi": "3.0.1", "info": { "title": "Dataset Change Monitor", "description": "Compare every scraper run with the previous one and get only new, changed and removed items, with field-level before/after diffs. Alerts via Telegram, Slack, webhook or email. Works with any Apify Actor, dataset, JSON or CSV.", "version": "1.0", "x-build-id": "86fGgUcesbCfyK3BS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/egra_van~dataset-change-monitor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-egra_van-dataset-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/egra_van~dataset-change-monitor/runs": { "post": { "operationId": "runs-sync-egra_van-dataset-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/egra_van~dataset-change-monitor/run-sync": { "post": { "operationId": "run-sync-egra_van-dataset-change-monitor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "datasetId": { "title": "Dataset ID", "type": "string", "description": "ID or name of the Apify dataset to check, e.g. the default dataset of your scraper's latest run. Leave empty when this Actor runs as an integration after another Actor: the finished run's dataset is used automatically." }, "actorRunId": { "title": "…or Actor run ID", "type": "string", "description": "ID of a finished Actor run. Its default dataset is compared." }, "datasetUrl": { "title": "…or JSON / CSV URL", "type": "string", "description": "Public link to a JSON array, JSON Lines or CSV file, e.g. an Apify dataset export link (https://api.apify.com/v2/datasets/…/items?format=json)." }, "items": { "title": "…or items (JSON)", "type": "array", "description": "Array of objects to compare. Handy for testing or when calling the Actor from Make, Zapier or n8n." }, "monitorName": { "title": "Monitor name", "type": "string", "description": "Each name keeps its own memory of the previous run. Use a different name for every scraper or search you track, e.g. \"amazon-laptops\". If empty, the name is taken from the source Actor or task (integration) or \"default\"." }, "idFields": { "title": "Unique key fields", "type": "array", "description": "Field(s) that identify the same item between runs, e.g. url, id or asin. Nested fields use dots (offer.id). If empty, the whole item is the key: items can then only be new or removed, never changed.", "items": { "type": "string" } }, "compareFields": { "title": "Fields to watch", "type": "array", "description": "Only these fields decide whether an item changed, e.g. price, stock, title. Leave empty to watch all fields except the ignored ones.", "items": { "type": "string" } }, "ignoreFields": { "title": "Fields to ignore", "type": "array", "description": "Fields that change on every run and are not real changes, e.g. scrapedAt, timestamp, position. Used when \"Fields to watch\" is empty.", "items": { "type": "string" } }, "reportNew": { "title": "Report new items", "type": "boolean", "description": "Items whose key did not exist in the previous run.", "default": true }, "reportChanged": { "title": "Report changed items", "type": "boolean", "description": "Items whose watched fields differ from the previous run.", "default": true }, "trackRemoved": { "title": "Report removed items", "type": "boolean", "description": "Items that were in the previous run but are missing now.", "default": true }, "reportAllOnFirstRun": { "title": "Report all items as new on the first run", "type": "boolean", "description": "By default the first run only saves a baseline and reports nothing.", "default": false }, "detailedDiff": { "title": "Show which fields changed (before → after)", "type": "boolean", "description": "Keeps a compact copy of each item between runs. Turn off for very large datasets to use less memory; changed items are still detected.", "default": true }, "maxChangesPerItem": { "title": "Max field changes listed per item", "minimum": 1, "maximum": 200, "type": "integer", "description": "Limits the size of the \"changes\" list for items with many modified fields.", "default": 20 }, "maxItems": { "title": "Max items to compare", "minimum": 0, "type": "integer", "description": "0 = no limit. When the limit is hit, removed items are not reported for that run.", "default": 0 }, "notifyMaxItems": { "title": "Changes listed in a message", "minimum": 0, "maximum": 100, "type": "integer", "description": "How many changes Telegram, Slack and email messages list before \"…and N more\".", "default": 10 }, "notifyOnNoChanges": { "title": "Also notify when nothing changed", "type": "boolean", "description": "Sends a short \"no changes\" message after every run, useful to know the monitor is alive.", "default": false }, "telegramBotToken": { "title": "Telegram bot token", "type": "string", "description": "Create a bot with @BotFather and paste its token." }, "telegramChatId": { "title": "Telegram chat ID", "type": "string", "description": "Your user, group or channel ID (e.g. 123456789 or -1001234567890). Add the bot to the group or channel first." }, "slackWebhookUrl": { "title": "Slack incoming webhook URL", "type": "string", "description": "https://hooks.slack.com/services/…" }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Receives a POST with a JSON summary and the first changes. Works with Make, Zapier, n8n or your own server." }, "webhookMaxItems": { "title": "Changes included in the webhook", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum number of change records included in the webhook JSON. The full list is always in the dataset.", "default": 100 }, "emailTo": { "title": "Email to", "type": "string", "description": "Sends a summary email through the apify/send-mail Actor (billed as a separate small run on your account). Several addresses: separate with commas." }, "emailSubject": { "title": "Email subject", "type": "string", "description": "Default: \": 3 new, 1 changed, 0 removed\"." }, "resetState": { "title": "Start over", "type": "boolean", "description": "Forget the previous snapshot of this monitor and create a new baseline.", "default": false }, "allowEmptySource": { "title": "Allow an empty source", "type": "boolean", "description": "By default an empty dataset is treated as a failed scrape: nothing is reported as removed and the snapshot is kept. Enable if an empty result can be real.", "default": false }, "stateStoreName": { "title": "State storage name", "type": "string", "description": "Named key-value store that keeps the snapshots between runs. Letters, digits and \"-\" only.", "default": "change-monitor-state" }, "payload": { "title": "Integration payload", "type": "object", "description": "Filled automatically when this Actor runs as an integration after another Actor. Leave empty." } } }, "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 } } } } } } } } } }