{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scraper", "description": "Scrape OpenAlex the free, open catalog of 250M+ scholarly works, authors, institutions, and concepts. Search papers, authors, or fetch by OpenAlex ID / DOI. Pulls citations, open-access status, abstracts, authorships, journals, topics, and more.", "version": "1.0", "x-build-id": "fdgHEfMzVsJU03Sf1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~openalex-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~openalex-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~openalex-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "searchWorks", "searchAuthors", "byWorkIds", "byAuthorIds", "byVenueIds", "byInstitutionIds" ], "type": "string", "description": "What to fetch.", "default": "searchWorks" }, "searchQuery": { "title": "Search query (mode=searchWorks / searchAuthors)", "type": "string", "description": "Free-text query.", "default": "large language models" }, "workIds": { "title": "Work IDs (mode=byWorkIds)", "type": "array", "description": "OpenAlex work IDs (`W123...`), DOIs, PMIDs, or PMCIDs. Examples: `W2741809807`, `https://doi.org/10.1145/3442188.3445922`, `pmid:25524000`.", "default": [], "items": { "type": "string" } }, "authorIds": { "title": "Author IDs (mode=byAuthorIds)", "type": "array", "description": "OpenAlex author IDs (`A123...`) or ORCIDs.", "default": [], "items": { "type": "string" } }, "venueIds": { "title": "Venue / source IDs (mode=byVenueIds)", "type": "array", "description": "OpenAlex source IDs prefixed with `S` (journal / repository / conference). Examples: `S4306400194` (arXiv), `S137773608` (Nature), `S99775433` (Science). Or pass an ISSN like `0028-0836` and it will be resolved.", "default": [], "items": { "type": "string" } }, "institutionIds": { "title": "Institution IDs (mode=byInstitutionIds)", "type": "array", "description": "OpenAlex institution IDs prefixed with `I` (university / lab / company). Examples: `I27837315` (Univ. of Michigan), `I97018004` (Stanford), `I136199984` (Harvard), `I32971472` (MIT), `I114027177` (DeepMind). Or pass a ROR ID URL.", "default": [], "items": { "type": "string" } }, "publicationYearMin": { "title": "Publication year (min)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Drop works published before this year." }, "publicationYearMax": { "title": "Publication year (max)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Drop works published after this year." }, "minCitedBy": { "title": "Min citation count", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Drop works with fewer citations than this." }, "openAccessOnly": { "title": "Open-access only", "type": "boolean", "description": "Only emit works with open-access full-text available.", "default": false }, "workType": { "title": "Work type", "enum": [ "any", "article", "book", "book-chapter", "dataset", "dissertation", "preprint", "report", "review", "letter", "editorial", "erratum", "standard", "supplementary-materials" ], "type": "string", "description": "Optional OpenAlex `type` filter.", "default": "any" }, "sortBy": { "title": "Sort by", "enum": [ "relevance_score:desc", "cited_by_count:desc", "publication_date:desc", "publication_year:desc" ], "type": "string", "description": "OpenAlex sort field.", "default": "relevance_score:desc" }, "includeAbstract": { "title": "Include abstract", "type": "boolean", "description": "Reconstruct the abstract from OpenAlex's inverted index. Costs zero extra API calls.", "default": true }, "includeAuthorships": { "title": "Include authorships", "type": "boolean", "description": "Include the full authorship list (with affiliations).", "default": true }, "includeConcepts": { "title": "Include topics / concepts", "type": "boolean", "description": "Include the topic / concept tags assigned by OpenAlex.", "default": true }, "userAgentEmail": { "title": "User-Agent contact email", "type": "string", "description": "OpenAlex's polite pool requires a contact email in the User-Agent. Default works for low-volume; for production scraping, supply your own email.", "default": "apify-actor@noreply.apify.com" }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on emitted records.", "default": 50 } } }, "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 } } } } } } } } } }