{ "openapi": "3.0.1", "info": { "title": "Merge & Dedup Datasets, CSV, JSON & Excel Files", "description": "Merge Apify datasets, CSV, JSON, JSON Lines and Excel files into one clean dataset. Remove duplicates on any fields, ignoring case, spaces and URL variants; keep the first, last or most complete row; filter, pick and rename fields. No code. Duplicates and filtered rows are free.", "version": "0.1", "x-build-id": "T9Gn5fJt2sb8NQC1n" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/wrentools~dataset-merge-dedup/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-wrentools-dataset-merge-dedup", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/wrentools~dataset-merge-dedup/runs": { "post": { "operationId": "runs-sync-wrentools-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/wrentools~dataset-merge-dedup/run-sync": { "post": { "operationId": "run-sync-wrentools-dataset-merge-dedup", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "datasetIds": { "title": "Apify datasets", "type": "array", "description": "Your Apify datasets to merge, for example the results of several scraper runs. Only the datasets you pick here are read, and only for reading." }, "fileUrls": { "title": "File URLs (CSV, TSV, JSON, JSON Lines, Excel)", "type": "array", "description": "Links to files you are allowed to use: CSV or TSV with a header row, a JSON array, JSON Lines, or an .xlsx workbook (first sheet, first row as header). Each file is downloaded once; the site's robots.txt is respected.", "items": { "type": "string" } }, "items": { "title": "Rows as JSON", "type": "array", "description": "Rows pasted in directly: a JSON array of objects. Read after the datasets and files." }, "dedupFields": { "title": "Deduplicate on these fields", "type": "array", "description": "Rows whose values in all these fields match are duplicates; only one is kept. Use dotted paths for nested fields (address.city). [\"*\"] compares whole rows. Leave empty to merge without deduplicating.", "items": { "type": "string" } }, "keep": { "title": "Which duplicate to keep", "enum": [ "first", "last", "mostComplete" ], "type": "string", "description": "Kept rows stay in the order they were read. 'last' and 'most complete' read every source before writing.", "default": "first" }, "trimValues": { "title": "Ignore leading and trailing spaces", "type": "boolean", "description": "' ann@example.com ' matches 'ann@example.com'.", "default": true }, "ignoreCase": { "title": "Ignore upper and lower case", "type": "boolean", "description": "'Ann@Example.com' matches 'ann@example.com'. Turn off for case-sensitive codes or IDs.", "default": true }, "collapseWhitespace": { "title": "Treat runs of spaces as one", "type": "boolean", "description": "'Harbor Supply' matches 'Harbor Supply'; tabs and line breaks count as spaces.", "default": false }, "normalizeUrls": { "title": "Compare URLs loosely", "type": "boolean", "description": "In values that are URLs, ignore http/https, 'www.', a default port, a trailing slash, the #fragment, tracking parameters (utm_*, gclid, fbclid ...) and the order of query parameters.", "default": false }, "emptyKeyRows": { "title": "Rows with empty dedup fields", "enum": [ "keep", "dedup", "drop" ], "type": "string", "description": "What to do with rows in which every dedup field is empty or missing.", "default": "keep" }, "filters": { "title": "Filters", "type": "array", "description": "Keep only rows that match: a list of {\"field\": \"country\", \"op\": \"equals\", \"value\": \"US\"}. Operators: equals, notEquals, contains, notContains, startsWith, endsWith, in, notIn (value is a list), gt, gte, lt, lte (numbers), matches, notMatches (regular expression), isEmpty, isNotEmpty. Filters run before deduplication, on the original field names." }, "filterMode": { "title": "Rows must match", "enum": [ "all", "any" ], "type": "string", "description": "Combine the filters with AND (all) or OR (any).", "default": "all" }, "filtersCaseSensitive": { "title": "Case-sensitive filters", "type": "boolean", "description": "Off: 'us' matches 'US' in text filters and regular expressions.", "default": false }, "fields": { "title": "Output only these fields", "type": "array", "description": "Write only these fields, in this order (dotted paths allowed; a missing field is written as null). Empty writes every field. For datasets, only the fields needed are downloaded.", "items": { "type": "string" } }, "omitFields": { "title": "Drop these fields", "type": "array", "description": "Top-level fields to leave out of the output.", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Old name to new name, e.g. {\"e-mail\": \"email\", \"Company Name\": \"company\"}. Applied last, to the written rows." }, "addSourceField": { "title": "Add a source field", "type": "string", "description": "If set, each written row gets a field of this name saying where it came from (dataset:, the file URL, or 'items')." }, "maxOutputRows": { "title": "Maximum rows to write", "minimum": 0, "maximum": 100000000, "type": "integer", "description": "Stop after writing this many rows (0 = no limit). Rows are charged as written.", "default": 0 }, "fileFormat": { "title": "File format", "enum": [ "auto", "csv", "json", "jsonl", "xlsx" ], "type": "string", "description": "Applies to every file URL. Detection reads the file's first bytes, its name and its content type.", "default": "auto" }, "csvDelimiter": { "title": "CSV delimiter", "enum": [ "auto", "comma", "semicolon", "tab", "pipe" ], "type": "string", "description": "The character between CSV columns.", "default": "auto" }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger downloads are stopped and reported as file-too-large, without charge. A file needs about 4 times its size in memory.", "default": 50 }, "requestDelayMs": { "title": "Delay between downloads from one site (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Minimum pause between two downloads from the same site.", "default": 500 } } }, "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 } } } } } } } } } }