{ "openapi": "3.0.1", "info": { "title": "PubMed Scraper — Articles, Abstracts, Authors, MeSH & DOI", "description": "PubMed scraper: search PubMed by keyword (full query syntax, date range, best match or newest) or by PMID and get title, abstract, authors, affiliations, journal, publication date, DOI, PMCID, publication types, MeSH terms and keywords as JSON via NCBI E-utilities. From US$0.55 per 1,000 articles.", "version": "0.1", "x-build-id": "IfIZxRL1vYmY9oMQM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fabrikit~pubmed-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fabrikit-pubmed-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fabrikit~pubmed-scraper/runs": { "post": { "operationId": "runs-sync-fabrikit-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/fabrikit~pubmed-scraper/run-sync": { "post": { "operationId": "run-sync-fabrikit-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": { "searchTerms": { "title": "Search terms", "type": "array", "description": "One PubMed search per entry. Plain keywords work (crispr gene editing) and so does the full PubMed query syntax: AND / OR / NOT, field tags such as diabetes[ti], smith j[au], \"Neoplasms\"[mesh], review[pt], humans[mh], free full text[sb]. The rank of each article in its search is saved as `position`. PubMed pages at most 10,000 results per query; use dateFrom / dateTo to split larger queries.", "items": { "type": "string" } }, "pmids": { "title": "PMIDs or PubMed URLs", "type": "array", "description": "Specific articles to fetch: PubMed IDs (36319653, PMID: 36319653) or article URLs (https://pubmed.ncbi.nlm.nih.gov/36319653/). Fetched before the search terms, 200 per request.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum articles", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Stop after this many articles in total (exact; an article found by several search terms is saved and charged once).", "default": 100 }, "sort": { "title": "Sort order", "enum": [ "relevance", "pub_date" ], "type": "string", "description": "Order of the search results: PubMed's Best Match (relevance) or most recent publication date first.", "default": "relevance" }, "dateFrom": { "title": "Published from", "type": "string", "description": "Only articles published on or after this date: YYYY-MM-DD, YYYY-MM or YYYY (for example 2024-01-01). Applies to the search terms, not to PMIDs." }, "dateTo": { "title": "Published until", "type": "string", "description": "Only articles published on or before this date: YYYY-MM-DD, YYYY-MM or YYYY. Leave empty for no upper limit." }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Save the full abstract text (structured abstracts keep their section labels: BACKGROUND, METHODS, RESULTS...). Turn off to keep records small; the same requests are made either way.", "default": true }, "apiKey": { "title": "NCBI API key (optional)", "type": "string", "description": "Your free NCBI API key (My NCBI > Account settings). Without it NCBI allows 3 requests per second per IP and the Actor spaces calls 0.4 s apart; with it the limit is 10 per second. Only sent to eutils.ncbi.nlm.nih.gov." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. NCBI E-utilities accept direct connections, so no proxy is used by default. Enable Apify Proxy (datacenter) only if a shared IP hits NCBI's rate limit (HTTP 429).", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }