PubMed Search Scraper
Pricing
from $0.03 / 1,000 pubmed articles
PubMed Search Scraper
Search PubMed and export public article metadata, abstracts, authors, journals, DOI, MeSH terms, and keywords.
PubMed Search Scraper
Pricing
from $0.03 / 1,000 pubmed articles
Search PubMed and export public article metadata, abstracts, authors, journals, DOI, MeSH terms, and keywords.
You can access the PubMed Search Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "dqHjQUmdWGJqatKO5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fetch_cat~pubmed-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fetch_cat-pubmed-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fetch_cat~pubmed-search-scraper/runs": { "post": { "operationId": "runs-sync-fetch_cat-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/fetch_cat~pubmed-search-scraper/run-sync": { "post": { "operationId": "run-sync-fetch_cat-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": "PubMed search query. You can use keywords, phrases, MeSH terms, PMID-like terms, or Boolean operators supported by PubMed." }, "maxItems": { "title": "Maximum articles", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of articles to save, from 1 to 10000. The form defaults to 10; omitting maxItems in raw API input uses 25. PubMed search limits can return fewer articles.", "default": 10 }, "sort": { "title": "Sort order", "enum": [ "relevance", "pub_date", "most_recent", "first_author", "journal" ], "type": "string", "description": "Sort passed to PubMed: relevance (default), publication date, most recent, first author or journal. Saved rows follow the returned PMID order; the source index may change between runs.", "default": "relevance" }, "includeAbstracts": { "title": "Include abstracts and subject terms", "type": "boolean", "description": "Include available abstracts, MeSH terms, keywords and language. When disabled, abstract/language are null and MeSH terms/keywords are empty; basic publication types may still be returned. Defaults to true.", "default": true }, "dateRange": { "title": "Publication date range", "enum": [ "any", "1_year", "5_years", "10_years", "custom" ], "type": "string", "description": "Default any. The 1/5/10-year presets use the current UTC date and ignore minDate/maxDate. Custom requires at least one bound. Any also applies explicit minDate/maxDate when supplied.", "default": "any" }, "minDate": { "title": "Minimum publication date", "type": "string", "description": "Minimum publication date for a custom range. Custom mode requires this field or Maximum publication date. Accepted formats: YYYY, YYYY/MM, or YYYY/MM/DD." }, "resumeFromIndex": { "title": "Resume from search result", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Absolute search offset from 0 to 100000, default 0. After an interrupted run, use nextIndex from PENDING_WORK with identical query, filters and sort. Source results may change; resuming is not duplicate-free and does not bypass PubMed search limits.", "default": 0 }, "maxDate": { "title": "Maximum publication date", "type": "string", "description": "Maximum publication date for a custom range. Custom mode requires this field or Minimum publication date. Accepted formats: YYYY, YYYY/MM, or YYYY/MM/DD." }, "journal": { "title": "Journal filter", "type": "string", "description": "Optional journal name filter, for example The Lancet or Nature Medicine." }, "author": { "title": "Author filter", "type": "string", "description": "Optional author name filter, for example Smith J." }, "articleType": { "title": "Article type filter", "type": "string", "description": "Optional article type, for example Review, Clinical Trial, Meta-Analysis, Randomized Controlled Trial, or Case Reports." } } }, "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 } } } } } } } } }}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: