{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scraper: Research Papers, Authors & Citations", "description": "Scrape OpenAlex, the open catalog of 250M+ research papers: titles, DOIs, citations, FWCI, abstracts and open access links, plus author h-index and institution records. Filter by keyword, year and open access. Export CSV, Excel, JSON. No login or API key.", "version": "0.1", "x-build-id": "EPkDjbygvBQqThVLI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/recordsdata~openalex-research-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-recordsdata-openalex-research-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/recordsdata~openalex-research-scraper/runs": { "post": { "operationId": "runs-sync-recordsdata-openalex-research-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/recordsdata~openalex-research-scraper/run-sync": { "post": { "operationId": "run-sync-recordsdata-openalex-research-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "worksQuery": { "title": "Papers search", "type": "string", "description": "Search research papers by keywords (e.g. crispr, large language models). One search per line: each line is a separate search and every row is tagged with the search that found it. Use * to list papers by the filters below only. Leave empty to skip papers.", "default": "crispr" }, "searchIn": { "title": "Search in", "enum": [ "title", "titleAndAbstract" ], "type": "string", "description": "Where the papers search looks for the words. Title only is the original behaviour; title and abstract finds more papers.", "default": "title" }, "yearFrom": { "title": "Year from (optional)", "minimum": 1800, "type": "integer", "description": "Only papers published from this year onward." }, "yearTo": { "title": "Year to (optional)", "minimum": 1800, "type": "integer", "description": "Only papers published up to this year." }, "minCitations": { "title": "Minimum citations", "minimum": 0, "type": "integer", "description": "Only papers cited at least this many times (0 = no limit).", "default": 0 }, "workType": { "title": "Paper type", "enum": [ "any", "article", "review", "preprint", "book", "book-chapter", "dissertation", "dataset", "report", "editorial", "letter", "conference-paper", "peer-review", "retraction", "erratum", "standard", "other" ], "type": "string", "description": "Only papers of this OpenAlex type. Any keeps all types. For a type that is not listed, use the filter box (type:...).", "default": "any" }, "onlyOpenAccess": { "title": "Only open access", "type": "boolean", "description": "Keep only papers with a free full-text link.", "default": false }, "filter": { "title": "Papers filter (OpenAlex syntax, optional)", "type": "string", "description": "Extra OpenAlex filter for papers: key:value pairs separated by commas or new lines, for example language:en,authorships.countries:US,is_retracted:false,open_access.oa_status:gold or doi:https://doi.org/10.1038/nature14539|https://doi.org/10.7717/peerj.4375. Combined with the other paper inputs. A key OpenAlex does not know returns a clear error row and nothing is charged.", "default": "" }, "sortBy": { "title": "Sort papers by", "enum": [ "cited_by_count", "publication_date", "relevance" ], "type": "string", "description": "Order of the papers results. Relevance needs a papers search text.", "default": "cited_by_count" }, "authorsQuery": { "title": "Authors search (optional)", "type": "string", "description": "Search researcher profiles by name (h-index, citations, affiliation). One search per line. Use * to list authors by the entity filter only.", "default": "" }, "institutionsQuery": { "title": "Institutions search (optional)", "type": "string", "description": "Search universities and research institutions by name. One search per line. Use * to list institutions by the entity filter only.", "default": "" }, "sourcesQuery": { "title": "Journals and sources search (optional)", "type": "string", "description": "Search journals, repositories and conferences by name (ISSN, publisher, open access flags, citation metrics). One search per line. Use * to list sources by the entity filter only.", "default": "" }, "topicsQuery": { "title": "Topics search (optional)", "type": "string", "description": "Search OpenAlex research topics by name (field, subfield, domain, keywords, related topics). One search per line. Use * to list topics by the entity filter only.", "default": "" }, "fundersQuery": { "title": "Funders search (optional)", "type": "string", "description": "Search research funders by name (country, awards, works funded, citation metrics). One search per line. Use * to list funders by the entity filter only.", "default": "" }, "publishersQuery": { "title": "Publishers search (optional)", "type": "string", "description": "Search academic publishers by name (hierarchy, countries, works, citation metrics). One search per line. Use * to list publishers by the entity filter only.", "default": "" }, "entityFilter": { "title": "Filter for authors, institutions, sources, topics, funders, publishers (optional)", "type": "string", "description": "Extra OpenAlex filter applied to every non-paper search above, key:value pairs separated by commas or new lines, for example country_code:CO,type:education for institutions or is_oa:true,type:journal for sources. Keys differ per type; an unknown key returns a clear error row and nothing is charged.", "default": "" }, "omitMissing": { "title": "Leave out empty fields", "type": "boolean", "description": "Off (default): a missing value in the original columns is written as the text Not Available or Not Disclosed, as before. On: those fields are left out of the row, so numbers stay numbers and nothing needs cleaning.", "default": false }, "openalexApiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Free key from openalex.org/settings/api. OpenAlex gives every network address a small free daily budget (about 100 searches); a key gives you your own budget 10 times larger. Needed only for very large runs or when you see a daily budget message." }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 10 items (preview). Paid users: Optional, max 1,000,000. It is the total over all searches; it is shared out between several searches of the same kind.", "default": 10 } } }, "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 } } } } } } } } } }