PubMed Search Scraper
Pricing
from $1.99 / 1,000 search results
Go to Apify Store
PubMed Search Scraper
Fetch biomedical articles from NCBI PubMed using the public E-utilities API.
PubMed Search Scraper
Pricing
from $1.99 / 1,000 search results
Fetch biomedical articles from NCBI PubMed using the public E-utilities API.
You can access the PubMed Search Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.1", "x-build-id": "NI9oF3FQVl1Ak2Zvv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/searchapi~pubmed-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-searchapi-pubmed-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/searchapi~pubmed-search-scraper/runs": { "post": { "operationId": "runs-sync-searchapi-pubmed-search-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/searchapi~pubmed-search-scraper/run-sync": { "post": { "operationId": "run-sync-searchapi-pubmed-search-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": [ "query" ], "properties": { "query": { "title": "Search query", "type": "string", "description": "Keyword query passed to PubMed search endpoint.", "default": "machine learning" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum article records returned across all pages.", "default": 20 }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100, "type": "integer", "description": "Number of search IDs fetched per page.", "default": 25 }, "maxPages": { "title": "Max search pages", "minimum": 1, "maximum": 20, "type": "integer", "description": "Hard bound on how many search pages are scanned.", "default": 4 }, "sortBy": { "title": "Sort", "enum": [ "relevance", "pub_date", "first_author", "last_author", "journal" ], "type": "string", "description": "PubMed sort order for search results.", "default": "relevance" }, "dateFrom": { "title": "From date", "type": "string", "description": "Filter from publication date (YYYY-MM-DD). Leave empty for no lower bound." }, "dateTo": { "title": "To date", "type": "string", "description": "Filter to publication date (YYYY-MM-DD). Leave empty for no upper bound." }, "articleType": { "title": "Article type filters", "type": "string", "description": "Comma-separated PubMed publication types, e.g. \"Journal Article, Clinical Trial, Meta-Analysis\"." }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Load article abstracts from EFetch XML payload.", "default": true }, "includeAuthors": { "title": "Include authors", "type": "boolean", "description": "Extract author names and affiliations when available.", "default": true }, "includeMeSH": { "title": "Include MeSH terms", "type": "boolean", "description": "Extract MeSH descriptors when available.", "default": true }, "includeKeywords": { "title": "Include keywords", "type": "boolean", "description": "Extract author keywords when available.", "default": true }, "requestDelayMs": { "title": "Request delay (ms)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Respectful delay between HTTP calls.", "default": 250 }, "maxConcurrent": { "title": "Max concurrent details fetches", "minimum": 1, "maximum": 8, "type": "integer", "description": "Concurrency cap for PubMed details requests.", "default": 3 }, "maxRequestRetries": { "title": "Maximum request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries for temporary network errors, rate limits, timeouts, and 5xx responses.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 90, "type": "integer", "description": "Bounded timeout for each NCBI API request.", "default": 25 }, "ncbiApiKey": { "title": "NCBI API key (optional)", "type": "string", "description": "Optional API key for higher rate limits (use a valid NCBI API key)." } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for PubMed Search Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: