{ "openapi": "3.0.1", "info": { "title": "PubMed Scraper", "description": "Extract biomedical articles from PubMed via the NCBI E-utilities API. 37M+ records: PMID, DOI, title, abstract, authors, journal, MeSH terms, keywords, references. No API key, no browser, no proxy.", "version": "0.0", "x-build-id": "JovxeRTkKK1Lk26mh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/aurenic~pubmed-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-aurenic-pubmed-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/aurenic~pubmed-scraper/runs": { "post": { "operationId": "runs-sync-aurenic-pubmed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/aurenic~pubmed-scraper/run-sync": { "post": { "operationId": "run-sync-aurenic-pubmed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mode": { "title": "Mode", "enum": [ "search", "fetch" ], "type": "string", "description": "What to fetch.", "default": "search" }, "query": { "title": "Search Query", "type": "string", "description": "PubMed query. Supports full PubMed syntax: field tags (e.g. 'cancer[Title]'), Boolean operators (AND/OR/NOT), and quoted phrases.", "default": "CRISPR AND 2024[PDAT]" }, "pmids": { "title": "PMIDs", "type": "array", "description": "PubMed IDs to fetch directly (e.g. 38000000). Used in fetch mode.", "items": { "type": "string" } }, "retmax": { "title": "Results per Page", "minimum": 1, "maximum": 10000, "type": "integer", "description": "PMIDs to retrieve per esearch call. Max 10,000.", "default": 500 }, "retstart": { "title": "Start Offset", "minimum": 0, "maximum": 100000, "type": "integer", "description": "First result index for pagination.", "default": 0 }, "sort": { "title": "Sort", "enum": [ "relevance", "date" ], "type": "string", "description": "Result order.", "default": "relevance" }, "dateFrom": { "title": "Date From", "type": "string", "description": "Earliest publication date (YYYY/MM/DD). Applied as a PDAT filter.", "default": "" }, "dateTo": { "title": "Date To", "type": "string", "description": "Latest publication date (YYYY/MM/DD).", "default": "" }, "publicationTypes": { "title": "Publication Types", "type": "array", "description": "Filter by publication type: 'Review', 'Clinical Trial', 'Meta-Analysis', 'Randomized Controlled Trial', 'Systematic Review', 'Case Reports', 'Editorial', 'Letter'.", "items": { "type": "string" } }, "includeAbstract": { "title": "Include Abstracts", "type": "boolean", "description": "Attach full abstract text to each record.", "default": true }, "includeMeSH": { "title": "Include MeSH Terms", "type": "boolean", "description": "Attach MeSH (Medical Subject Headings) descriptor and qualifier terms.", "default": true }, "email": { "title": "Contact Email (NCBI requirement)", "type": "string", "description": "Required by NCBI policy for all E-utilities requests. Used for IP-block notices — should be a real address.", "default": "apify-pubmed-scraper@example.com" }, "tool": { "title": "Tool Name", "type": "string", "description": "Tool identifier sent with every request. Required by NCBI policy.", "default": "apify-pubmed-scraper" }, "apiKey": { "title": "NCBI API Key (optional)", "type": "string", "description": "Optional. Raises rate limit from 3 req/s to 10 req/s. Get a free key from your NCBI account at https://account.ncbi.nlm.nih.gov/.", "default": "" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Hard cap on articles per run.", "default": 500 }, "requestDelayMs": { "title": "Request Delay (ms)", "minimum": 350, "maximum": 5000, "type": "integer", "description": "Delay between requests. NCBI allows 3 req/s without a key. Default 400ms stays safely under.", "default": 400 } } }, "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 } } } } } } } } } }