{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scraper - Research Papers, Citations & Authors API", "description": "OpenAlex API scraper: export research papers, citations, authors, institutions, journals and topics from 250M+ scholarly works to CSV, Excel or JSON. Abstracts included. $3 per 1,000 results.", "version": "0.1", "x-build-id": "XfTDdLMYkFR6g3cru" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/deanko~openalex-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-deanko-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/deanko~openalex-scraper/runs": { "post": { "operationId": "runs-sync-deanko-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/deanko~openalex-scraper/run-sync": { "post": { "operationId": "run-sync-deanko-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": { "entity": { "title": "What to scrape", "enum": [ "works", "authors", "institutions", "sources", "topics", "concepts" ], "type": "string", "description": "OpenAlex entity type to export. Works are papers and other research outputs.", "default": "works" }, "search": { "title": "Search query", "type": "string", "description": "Full-text search. For works it matches title, abstract and full text; for other entities it matches the name. Supports AND, OR, NOT and \"exact phrases\". Leave empty to list everything matching the filters.", "default": "" }, "fromYear": { "title": "Publication year from", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Works only. Earliest publication year (inclusive)." }, "toYear": { "title": "Publication year to", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Works only. Latest publication year (inclusive)." }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Works and sources only. Return only open-access works (or fully open-access journals).", "default": false }, "workType": { "title": "Work type", "enum": [ "", "article", "review", "preprint", "book", "book-chapter", "dataset", "dissertation", "editorial", "letter", "report", "other" ], "type": "string", "description": "Works only. Restrict to one work type.", "default": "" }, "institutionId": { "title": "Institution ID", "type": "string", "description": "Works and authors. OpenAlex institution ID or URL, e.g. I136199984 (Harvard). Find IDs by running this Actor with entity = institutions.", "default": "" }, "authorId": { "title": "Author ID", "type": "string", "description": "Works only. OpenAlex author ID or URL, e.g. A5023888391. Find IDs by running this Actor with entity = authors.", "default": "" }, "topicId": { "title": "Topic or concept ID", "type": "string", "description": "OpenAlex topic ID (T10346) or legacy concept ID (C41008148, works only). Find IDs by running this Actor with entity = topics.", "default": "" }, "countryCode": { "title": "Country code", "pattern": "^([A-Za-z]{2})?$", "type": "string", "description": "Two-letter ISO country code, e.g. US, DE, KR. Works: any author's institution country. Authors: last known institution. Institutions and sources: their country.", "default": "" }, "extraFilter": { "title": "Extra OpenAlex filter (advanced)", "type": "string", "description": "Any raw OpenAlex filter string, appended to the filters above, e.g. cited_by_count:>100,has_doi:true,language:en. See https://docs.openalex.org for all filters.", "default": "" }, "sort": { "title": "Sort by", "enum": [ "", "relevance_score:desc", "cited_by_count:desc", "publication_date:desc", "publication_year:desc", "works_count:desc", "display_name" ], "type": "string", "description": "Sort order. Default is relevance when you search, otherwise OpenAlex's default order.", "default": "" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of rows to save. You are charged per row, so this caps your cost (100 rows is about $0.30; 1,000 rows is about $3).", "default": 100 }, "mailto": { "title": "Your email (optional, polite pool)", "type": "string", "description": "Optional. Sent to OpenAlex as the mailto parameter so they can contact you about your usage. Not stored by the Actor.", "default": "" }, "apiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Optional. Your free OpenAlex API key (https://openalex.org/settings/api) gives you your own daily budget instead of the shared per-IP one. Recommended for very large exports." } } }, "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 } } } } } } } } } }