{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scholarly Works Scraper: Papers, Citations, Abstracts", "description": "Search 250M+ research papers in OpenAlex: many keyword searches per run, or by author, institution or DOI. Authors with ORCID and affiliations, venue, citations, open-access PDF links, topics and full abstracts. No API key or proxy. $0.80 per 1,000 works.", "version": "0.2", "x-build-id": "brnnVOPPeQYezohhV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyharvest~openalex-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyharvest-openalex-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidyharvest~openalex-papers-scraper/runs": { "post": { "operationId": "runs-sync-tidyharvest-openalex-papers-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/tidyharvest~openalex-papers-scraper/run-sync": { "post": { "operationId": "run-sync-tidyharvest-openalex-papers-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": { "queries": { "title": "Search queries", "type": "array", "description": "Keywords to search in 250M+ scholarly works, one search per line, e.g. `large language models` or `CRISPR off-target`. Each search returns up to Max works per search; a work found by two searches is returned once. Supports AND, OR, NOT and \"exact phrases\". Leave empty to list works by author, institution or filters alone.", "items": { "type": "string" } }, "query": { "title": "Search query (single)", "type": "string", "description": "One search, the same as one line of Search queries (kept for existing API callers). Supports AND, OR, NOT and \"exact phrases\"." }, "searchIn": { "title": "Search in", "enum": [ "titleAbstract", "title", "fullText" ], "type": "string", "description": "Where the query must match. Title and abstract gives the most relevant results; full text also matches words deep inside papers (more results, less precise).", "default": "titleAbstract" }, "dois": { "title": "DOIs (look up specific papers)", "type": "array", "description": "One DOI per line (`10.1038/nature14539` or `https://doi.org/...`). When set, the actor returns exactly these works and ignores the search fields below.", "items": { "type": "string" } }, "authorName": { "title": "Author", "type": "string", "description": "Only works by this author (applies to every search). A name (the main OpenAlex profile with that exact name is used, see the log), an ORCID (`0000-0002-1992-2684`) or an OpenAlex author id (`A5108093963`)." }, "institutionName": { "title": "Institution", "type": "string", "description": "Only works (in every search) with an author from this institution (including its sub-units). A name (`MIT`, `University of Oxford`), a ROR id or an OpenAlex institution id (`I63966007`)." }, "yearFrom": { "title": "Published from year", "minimum": 1500, "maximum": 2100, "type": "integer", "description": "Only works published in or after this year." }, "yearTo": { "title": "Published up to year", "minimum": 1500, "maximum": 2100, "type": "integer", "description": "Only works published in or before this year." }, "type": { "title": "Work type", "enum": [ "any", "article", "preprint", "review", "book", "book-chapter", "conference-paper", "dataset", "dissertation", "report", "editorial", "letter" ], "type": "string", "description": "Limit to one kind of work.", "default": "any" }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Only works that are free to read somewhere (an OA link is included in each result).", "default": false }, "minCitations": { "title": "Minimum citations", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Only works cited at least this many times." }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code, e.g. `en`, `de`, `zh`. Empty = all languages." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "citations", "date" ], "type": "string", "description": "Relevance to the query, most cited first, or newest first. Without a query, relevance falls back to most cited.", "default": "relevance" }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Adds the abstract (rebuilt from OpenAlex's word index) when the publisher allows it. Turn off for smaller rows.", "default": true }, "excludeRetracted": { "title": "Exclude retracted works", "type": "boolean", "description": "Skip works flagged as retracted.", "default": true }, "maxItems": { "title": "Max works per search", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cap on results for each search (the DOI list returns every DOI found). Also caps your cost; set a maximum charge per run for a hard total.", "default": 50 }, "apiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Optional. OpenAlex gives keyless callers a small shared daily budget. For large or frequent runs, paste your own free key from openalex.org/settings/api (10x the daily budget). Never shared or logged." } } }, "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 } } } } } } } } } }