{ "openapi": "3.0.1", "info": { "title": "uData Portal Extractor (data.gouv.fr & Etalab)", "description": "Point at ANY uData open-data portal (data.gouv.fr, data.public.lu, ~30 Etalab govs) and extract datasets, organizations, or community reuses via the uniform /api/1/ REST API. Nested resources, facet filters (q/tag/org/license), server-driven pagination.", "version": "0.1", "x-build-id": "vhwOXvgiZKA6ilQkn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~udata-portal-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-udata-portal-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~udata-portal-extractor/runs": { "post": { "operationId": "runs-sync-datamule-udata-portal-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~udata-portal-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-udata-portal-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "portalUrl" ], "properties": { "portalUrl": { "title": "uData portal URL", "type": "string", "description": "Base URL of ANY uData open-data portal (the Etalab platform behind data.gouv.fr and ~30 francophone/EU government portals). The '/api/1/…' path is appended automatically. Examples: https://www.data.gouv.fr (73k+ datasets) · https://data.public.lu (Luxembourg). Note: transport.data.gouv.fr uses a different specialised API shape and is out of scope — this actor targets the standard '/api/1/' uData core." }, "mode": { "title": "Mode", "enum": [ "datasets", "organizations", "reuses" ], "type": "string", "description": "What to extract. 'datasets' (default) → one row per dataset with its resources[] summarised on (resourceCount + first resource url/format/filesize/mime) and the full lossless resources array kept. 'organizations' → one row per publishing organisation. 'reuses' → one row per community reuse (apps/articles/visualisations built on the portal's data — a uData-unique layer).", "default": "datasets" }, "query": { "title": "Search query (q=)", "type": "string", "description": "Optional full-text filter — the uData 'q=' parameter. Applies to whichever mode is selected. e.g. 'transport', 'budget', 'covid'." }, "tag": { "title": "Tag filter", "type": "string", "description": "Optional tag facet (datasets/reuses). Only records carrying this tag are returned, e.g. 'transport', 'mobilite-durable'." }, "organization": { "title": "Organization id filter", "type": "string", "description": "Optional organization id (the uData org id, e.g. '534fff8ba3a7292c64a77de4') to return only datasets/reuses published by that organization. Use 'organizations' mode first to discover ids." }, "license": { "title": "License filter", "type": "string", "description": "Optional license id facet for datasets, e.g. 'lov2' (Licence Ouverte 2.0), 'cc-by', 'odc-odbl'." }, "emitResources": { "title": "Also emit one row per resource (datasets mode)", "type": "boolean", "description": "In 'datasets' mode, additionally emit ONE extra row per resource (each an actual downloadable file: url/format/filesize/checksum/mime) joined to its parent dataset. Each resource row is billed as a record. Off by default — the dataset row already carries a resource summary + the full lossless resources array.", "default": false }, "maxRecords": { "title": "Max records", "minimum": 1, "type": "integer", "description": "Stop after emitting this many records (dataset/organization/reuse rows, plus resource rows when emitResources is on). Pagination halts early once reached.", "default": 2000 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 500, "type": "integer", "description": "Records requested per API page (uData 'page_size'). The server caps this; values above 500 are clamped to 500.", "default": 50 }, "userAgent": { "title": "User-Agent (optional)", "type": "string", "description": "Override the default descriptive User-Agent header. These are government servers — please keep a descriptive agent." }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "type": "integer", "description": "Per-request timeout in seconds for each API page fetch.", "default": 60 } } }, "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 } } }, "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 } } } } } } } } } }