{ "openapi": "3.0.1", "info": { "title": "Zenodo Scraper — Research Records, Datasets & Software", "description": "Scrape Zenodo.org (CERN open research repository) for records, datasets, and software. Four modes: search with type/access filters, record details by DOI/ID, community browse, recent submissions. Extracts titles, authors, DOIs, files, stats. Uses official API. No auth, 60 req/min.", "version": "1.0", "x-build-id": "sNaJQ0Rl1yWevaCjE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/openclawmara~zenodo-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-openclawmara-zenodo-scraper", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/openclawmara~zenodo-scraper/runs": { "post": { "operationId": "runs-sync-openclawmara-zenodo-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/openclawmara~zenodo-scraper/run-sync": { "post": { "operationId": "run-sync-openclawmara-zenodo-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "search", "record_details", "community", "recent" ], "type": "string", "description": "What to scrape: search records, get record details, browse by community, or list recent uploads.", "default": "search" }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Search query (search mode). Supports Zenodo advanced syntax like 'title:climate AND creators.name:smith'." }, "resourceType": { "title": "Resource Type", "enum": [ "", "publication", "poster", "presentation", "dataset", "image", "video", "software", "lesson", "physicalobject", "other" ], "type": "string", "description": "Filter by resource type (search/community/recent modes). Leave empty for all.", "default": "" }, "recordIds": { "title": "Record IDs or DOIs", "type": "array", "description": "Zenodo record IDs (numeric) or DOIs (10.5281/zenodo.NNN) — record_details mode.", "items": { "type": "string" } }, "communityId": { "title": "Community ID", "type": "string", "description": "Community identifier (community mode). Example: 'biodiversity_literature_repository', 'covid-19'." }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of records to return.", "default": 50 }, "sortBy": { "title": "Sort By", "enum": [ "bestmatch", "mostrecent", "mostviewed" ], "type": "string", "description": "Sort search results by (search/community/recent modes).", "default": "bestmatch" }, "accessRight": { "title": "Access Right", "enum": [ "", "open", "embargoed", "restricted", "closed" ], "type": "string", "description": "Filter by access right.", "default": "" } } }, "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 } } } } } } } } } }