{ "openapi": "3.0.1", "info": { "title": "NIH RePORTER Scraper - Grants, PIs & Linked Publications", "description": "Scrape NIH-funded research projects from the official RePORTER v2 API. Extract PI names, award amounts, activity codes (R01, R21, K99), study sections, dates, and active/terminated status. Optionally pull linked publications (PMIDs). Filter by keyword, fiscal year, PI, org, state, or institute.", "version": "0.1", "x-build-id": "GBFHwba8g4Ztr8nHJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~nih-reporter-grants-publications-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-nih-reporter-grants-publications-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~nih-reporter-grants-publications-scraper/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-nih-reporter-grants-publications-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~nih-reporter-grants-publications-scraper/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-nih-reporter-grants-publications-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sp_intended_usage", "sp_improvement_suggestions" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "Please describe how you plan to use the data extracted by this crawler." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact Email", "minLength": 1, "type": "string", "description": "Provide your email address so we can get in touch with you." }, "textQuery": { "title": "Keyword / Text Search", "type": "string", "description": "Free-text search across project title, abstract, and terms. Leave empty to browse by filters." }, "fiscalYears": { "title": "Fiscal Years", "type": "array", "description": "One or more NIH fiscal years (e.g. 2024, 2025). Recommended for large pulls to stay under the API 15k offset cap.", "items": { "type": "string" } }, "piNames": { "title": "Principal Investigator Names", "type": "array", "description": "Filter by PI last name(s) (e.g. 'Doudna', 'Collins').", "items": { "type": "string" } }, "orgNames": { "title": "Organization Names", "type": "array", "description": "Filter by funded organization (e.g. 'STANFORD UNIVERSITY').", "items": { "type": "string" } }, "orgStates": { "title": "Organization States", "type": "array", "description": "Filter by organization US state code(s) (e.g. CA, MA, NY).", "items": { "type": "string" } }, "activityCodes": { "title": "Activity Codes", "type": "array", "description": "NIH activity code(s) (e.g. R01, R21, K99, F31, P30, U54).", "items": { "type": "string" } }, "agencyIcAdmin": { "title": "Administering Institute/Center", "type": "string", "description": "Filter by administering IC (e.g. NCI, NIAID, NHLBI, NIGMS)." }, "activeOnly": { "title": "Active Projects Only", "type": "boolean", "description": "Return only currently active projects. Disable to include closed/terminated awards (useful for the grant-termination story).", "default": false }, "newlyAddedOnly": { "title": "Newly Added Projects Only", "type": "boolean", "description": "Only projects added to RePORTER recently (incremental pulls).", "default": false }, "includeLinkedData": { "title": "Include Linked Publications", "type": "boolean", "description": "For each project, also fetch linked publication PMIDs. Adds one request per batch of 50 core project numbers.", "default": false }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of project records to return. Set to 0 for unlimited (use fiscalYears to paginate beyond the 15k API offset cap).", "default": 10 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. The NIH RePORTER API is public and does not require a proxy." } } }, "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 } } } } } } } } } }