{
"openapi": "3.0.1",
"info": {
"title": "OpenAlex Scraper - Scholarly Works & Citations",
"description": "Scrape scholarly works from OpenAlex (250M+ papers): title, DOI, authors, institutions, journal/venue, year, citation count, open-access status, topics and PDF link. Search any topic. No key, no browser. Independent tool, not affiliated with OpenAlex.",
"version": "0.1",
"x-build-id": "qHumigmZ0T5ruDky9"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/scrapesage~openalex-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-scrapesage-openalex-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/scrapesage~openalex-scraper/runs": {
"post": {
"operationId": "runs-sync-scrapesage-openalex-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/scrapesage~openalex-scraper/run-sync": {
"post": {
"operationId": "run-sync-scrapesage-openalex-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"searchQueries": {
"title": "Search queries",
"type": "array",
"description": "What to search OpenAlex for, one per line - e.g. machine learning, gene therapy. Searches titles, abstracts and full text. Leave empty and the run returns a small free sample.",
"items": {
"type": "string"
}
},
"filter": {
"title": "Filter (optional, advanced)",
"type": "string",
"description": "An OpenAlex filter expression instead of / in addition to a search - e.g. publication_year:2024,is_oa:true or authorships.institutions.country_code:us. See the OpenAlex docs."
},
"searchQueriesFromFile": {
"title": "Import search queries from a file",
"type": "string",
"description": "Bulk-load search queries. Either paste the whole list (one per line), or give a single link to a public .txt/.csv, a Google Sheet/Drive link, or an Apify key-value-store record. A file that cannot be read says so and charges nothing."
},
"sortBy": {
"title": "Sort by",
"enum": [
"relevance",
"cited",
"newest"
],
"type": "string",
"description": "How to order results.",
"default": "relevance"
},
"maxItemsPerQuery": {
"title": "Max works per query",
"minimum": 1,
"type": "integer",
"description": "How many works to collect for each search query.",
"default": 50
},
"maxItems": {
"title": "Max works (total)",
"minimum": 1,
"type": "integer",
"description": "Overall cap across all queries. You are only charged for works actually saved.",
"default": 1000
},
"outputFields": {
"title": "Output fields (leave empty for all)",
"type": "array",
"description": "Pick the fields you want and every record is trimmed to exactly those - handy for lean CSV/Sheets exports.",
"items": {
"type": "string",
"enum": [
"type",
"id",
"doi",
"title",
"publicationYear",
"publicationDate",
"workType",
"authors",
"authorCount",
"institutions",
"venue",
"venueType",
"citedByCount",
"referencedWorksCount",
"isOpenAccess",
"oaStatus",
"pdfUrl",
"landingPageUrl",
"language",
"topics",
"openAlexUrl",
"doiUrl",
"scrapedAt"
],
"enumTitles": [
"Record type (type)",
"OpenAlex ID (id)",
"DOI (doi)",
"Title (title)",
"Publication year (publicationYear)",
"Publication date (publicationDate)",
"Work type (workType)",
"Authors (authors)",
"Author count (authorCount)",
"Institutions (institutions)",
"Venue (venue)",
"Venue type (venueType)",
"Cited-by count (citedByCount)",
"Referenced-works count (referencedWorksCount)",
"Open access (isOpenAccess)",
"OA status (oaStatus)",
"PDF URL (pdfUrl)",
"Landing page (landingPageUrl)",
"Language (language)",
"Topics (topics)",
"OpenAlex URL (openAlexUrl)",
"DOI URL (doiUrl)",
"Scraped at (scrapedAt)"
]
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}