{ "openapi": "3.0.1", "info": { "title": "REST API to Dataset: Auto Pagination, Auth & Retries", "description": "Fetch any JSON REST or GraphQL API into a clean dataset: auto pagination (next links, cursors, pages, offsets), API key auth, retries, rate limits, records extraction and per-row enrichment. Failed requests are free.", "version": "1.0", "x-build-id": "8nXbp0aeMdyHPS7Ok" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/genesis.labs.co~rest-api-to-dataset/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-genesis.labs.co-rest-api-to-dataset", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/genesis.labs.co~rest-api-to-dataset/runs": { "post": { "operationId": "runs-sync-genesis.labs.co-rest-api-to-dataset", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/genesis.labs.co~rest-api-to-dataset/run-sync": { "post": { "operationId": "run-sync-genesis.labs.co-rest-api-to-dataset", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "url": { "title": "API URL", "type": "string", "description": "The JSON API endpoint to fetch, e.g. https://api.example.com/v1/items?status=active. With an Input dataset this is a template: https://api.example.com/users/{{id}}, or {{url}} to call a URL stored in each row. Leave empty to run a free demo." }, "urls": { "title": "More API URLs", "type": "array", "description": "Optional extra endpoints, fetched with the same settings. Each one is paginated on its own.", "items": { "type": "string" } }, "method": { "title": "HTTP method", "enum": [ "GET", "POST", "PUT", "PATCH", "DELETE", "HEAD" ], "type": "string", "description": "GET for most APIs; POST for GraphQL and search endpoints.", "default": "GET" }, "queryParams": { "title": "Query parameters", "type": "object", "description": "Added to every first request, e.g. {\"per_page\": 100, \"state\": \"open\"}. Values can use {{field}} placeholders." }, "headers": { "title": "Headers", "type": "object", "description": "Extra request headers, e.g. {\"Accept\": \"application/vnd.github+json\"}. Put API keys in \"API key / token\" below instead, which is stored encrypted." }, "body": { "title": "Request body (JSON)", "type": "object", "description": "For POST/PUT/PATCH, e.g. a GraphQL {\"query\": \"...\", \"variables\": {}} or a search filter. Values can use {{field}} placeholders (a value that is exactly \"{{field}}\" keeps its type)." }, "bodyFormat": { "title": "Body format", "enum": [ "json", "form" ], "type": "string", "description": "How the request body is encoded.", "default": "json" }, "authType": { "title": "Auth type", "enum": [ "none", "bearer", "header", "query", "basic" ], "type": "string", "description": "How your API key or token is sent.", "default": "none" }, "authToken": { "title": "API key / token", "type": "string", "description": "The token or API key. For Basic auth use username:password." }, "authName": { "title": "Header or parameter name", "type": "string", "description": "Header name for \"API key in a header\" (default X-API-Key) or query parameter for \"API key in the query string\" (default api_key). For Bearer, overrides the Authorization header name." }, "recordsPath": { "title": "Records path", "type": "string", "description": "Where the list of records is in the response, as a dot path, e.g. data.items or results. Leave empty to auto-detect (top-level arrays, data, results, items, hits.hits, GraphQL edges/nodes...). Use . to save the whole response as one record." }, "outputMode": { "title": "Output", "enum": [ "records", "responses" ], "type": "string", "description": "Records: the record list is split into rows (best for CSV/Excel). Per response: one item per HTTP response, for non-JSON or when you want the raw body.", "default": "records" }, "fields": { "title": "Keep only these fields", "type": "array", "description": "Optional. Dot paths like id, name, price.amount. Leave empty to keep every field.", "items": { "type": "string" } }, "renameFields": { "title": "Rename fields", "type": "object", "description": "Optional map of old name or dot path to new name, e.g. {\"price.amount\": \"price\"}." }, "flatten": { "title": "Flatten nested objects", "type": "boolean", "description": "Turn {\"a\": {\"b\": 1}} into {\"a.b\": 1} for spreadsheets. Arrays of values are joined with commas.", "default": false }, "includeRequestInfo": { "title": "Add source URL and page number", "type": "boolean", "description": "Adds _sourceUrl and _page (and _inputIndex with an Input dataset) to every record.", "default": false }, "includeResponseHeaders": { "title": "Include response headers (per-response output)", "type": "boolean", "description": "Per-response output only: adds the response headers to each item.", "default": false }, "pagination": { "title": "Pagination", "enum": [ "auto", "none", "nextUrl", "linkHeader", "cursor", "page", "offset" ], "type": "string", "description": "How to find the next page. Auto-detect works for most APIs.", "default": "auto" }, "nextUrlPath": { "title": "Next URL path", "type": "string", "description": "For \"Next URL\": dot path of the next page's URL, e.g. links.next or paging.next." }, "cursorPath": { "title": "Cursor path", "type": "string", "description": "For \"Cursor\": dot path of the next cursor in the response, e.g. meta.next_cursor or data.search.pageInfo.endCursor." }, "cursorParam": { "title": "Cursor parameter", "type": "string", "description": "For \"Cursor\": the query parameter (or body path, e.g. variables.after) that receives the cursor." }, "pageParam": { "title": "Page parameter", "type": "string", "description": "For \"Page number\". Default page." }, "startPage": { "title": "First page number", "minimum": 0, "type": "integer", "description": "For \"Page number\". Default 1 (use 0 for zero-based APIs)." }, "offsetParam": { "title": "Offset parameter", "type": "string", "description": "For \"Offset\". Default offset (e.g. skip, start)." }, "startOffset": { "title": "First offset", "minimum": 0, "type": "integer", "description": "For \"Offset\". Default 0." }, "limitParam": { "title": "Page size parameter", "type": "string", "description": "For \"Page number\" or \"Offset\": the parameter that sets page size, e.g. limit or per_page. Sent with Page size." }, "pageSize": { "title": "Page size", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Records per page. When set, a shorter page means it was the last one." }, "paginationParamIn": { "title": "Send pagination parameter in", "enum": [ "query", "body" ], "type": "string", "description": "Where the page, offset or cursor parameter is sent.", "default": "query" }, "hasMorePath": { "title": "Has-more path", "type": "string", "description": "Optional dot path of a true/false flag; false stops paging (e.g. has_more, pageInfo.hasNextPage)." }, "totalPagesPath": { "title": "Total pages path", "type": "string", "description": "Optional, for \"Page number\": dot path of the page count, e.g. meta.total_pages or nbPages." }, "totalPath": { "title": "Total records path", "type": "string", "description": "Optional, for \"Offset\": dot path of the total record count, e.g. total or numFound." }, "stopOnEmptyPage": { "title": "Stop on an empty page", "type": "boolean", "description": "Stop paging when a page has no records.", "default": true }, "maxPagesPerUrl": { "title": "Max pages per URL", "minimum": 1, "type": "integer", "description": "Safety limit per endpoint (or per input row).", "default": 1000 }, "datasetId": { "title": "Input dataset (one request per row)", "type": "string", "description": "Optional. Calls the API once per row, filling {{field}} placeholders in the URL, query, headers and body from that row. In an integration use {{resource.defaultDatasetId}}." }, "inputFields": { "title": "Copy fields from the input row", "type": "array", "description": "Fields of the input row to add to every output record, e.g. id or email, so you can join results back.", "items": { "type": "string" } }, "maxInputItems": { "title": "Max input rows", "minimum": 0, "type": "integer", "description": "0 = all rows." }, "maxRecords": { "title": "Max records", "minimum": 0, "type": "integer", "description": "Stop after this many records in total. 0 = no limit." }, "maxRequests": { "title": "Max requests", "minimum": 1, "type": "integer", "description": "Safety limit on API requests per run (retries not counted).", "default": 10000 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "Endpoints or input rows fetched in parallel. Pages of one endpoint are always fetched in order.", "default": 5 }, "requestsPerSecond": { "title": "Requests per second", "minimum": 0, "maximum": 100, "type": "number", "description": "Global rate limit across all parallel requests. 0 = no limit. A 429 pauses everyone for the Retry-After time.", "default": 10 }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Per request, including reading the body.", "default": 30 }, "maxRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries for timeouts, connection errors, 408, 425, 429 and 5xx, with exponential backoff and Retry-After.", "default": 3 }, "maxResponseMB": { "title": "Max response size (MB)", "minimum": 1, "maximum": 200, "type": "integer", "description": "Larger responses fail with TOO_LARGE instead of exhausting memory.", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. Most APIs don't need one. Use it for APIs that block datacenter IPs or need a specific country.", "default": { "useApifyProxy": false } }, "failOnRequestError": { "title": "Fail the run on any error", "type": "boolean", "description": "By default the run succeeds if at least one request worked, and failures are listed in the ERRORS record. Turn on to fail the run instead (useful in pipelines).", "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 } } } } } } } } } }