{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scraper - Scholarly Works, Authors & Citations Graph", "description": "Scrape OpenAlex, the open scholarly graph with 250M+ works, 100M+ authors, and 120K+ institutions. Extract titles, abstracts, authors, ORCIDs, institutions, concepts, citations, open-access flags, and grants.", "version": "1.0", "x-build-id": "jXVoRsJ9ydvmBggDV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jungle_synthesizer~openalex-works-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jungle_synthesizer-openalex-works-crawler", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jungle_synthesizer~openalex-works-crawler/runs": { "post": { "operationId": "runs-sync-jungle_synthesizer-openalex-works-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jungle_synthesizer~openalex-works-crawler/run-sync": { "post": { "operationId": "run-sync-jungle_synthesizer-openalex-works-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "sp_intended_usage", "sp_improvement_suggestions" ], "properties": { "sp_intended_usage": { "title": "What is the intended usage of this data?", "minLength": 1, "type": "string", "description": "Please describe how you plan to use the data extracted by this crawler." }, "sp_improvement_suggestions": { "title": "How can we improve this crawler for you?", "minLength": 1, "type": "string", "description": "Provide any feedback or suggestions for improvements." }, "sp_contact": { "title": "Contact Email", "minLength": 1, "type": "string", "description": "Provide your email address so we can get in touch with you." }, "entityType": { "title": "Entity Type", "enum": [ "works", "authors", "institutions", "concepts", "sources", "publishers" ], "type": "string", "description": "Which OpenAlex entity to query.", "default": "works" }, "query": { "title": "Full-text Search", "type": "string", "description": "Search query across titles and abstracts (works) or display names (other entities). Leave empty to browse all." }, "yearFrom": { "title": "Publication Year From", "type": "integer", "description": "Earliest publication year (Works only). Leave 0 for no lower bound.", "default": 0 }, "yearTo": { "title": "Publication Year To", "type": "integer", "description": "Latest publication year (Works only). Leave 0 for no upper bound.", "default": 0 }, "openAccessOnly": { "title": "Open Access Only", "type": "boolean", "description": "Restrict to open-access works (Works only).", "default": false }, "workType": { "title": "Work Type", "enum": [ "", "article", "preprint", "book", "book-chapter", "dataset", "dissertation", "review", "report", "standard", "other" ], "type": "string", "description": "Filter by work type (Works only).", "default": "" }, "concept": { "title": "Concept ID", "type": "string", "description": "Filter by OpenAlex concept ID (e.g. C41008148 = Computer Science). Works & Authors only." }, "institutionCountry": { "title": "Institution Country Code", "type": "string", "description": "Two-letter ISO country code (e.g. US, GB, DE). Applies to Works (authorships), Authors, and Institutions." }, "venueIssn": { "title": "Venue ISSN", "type": "string", "description": "Filter Works by host venue ISSN (e.g. 0028-0836 for Nature)." }, "reconstructAbstract": { "title": "Reconstruct Abstracts", "type": "boolean", "description": "Rebuild full-text abstracts from the OpenAlex inverted index (Works only). Slightly slower per record.", "default": true }, "politeEmail": { "title": "Polite Pool Email", "type": "string", "description": "Your email to qualify for the OpenAlex polite pool (higher rate limits, better latency). Recommended for any real run." }, "maxItems": { "title": "Max Items", "type": "integer", "description": "Maximum number of records to return. Set to 0 for unlimited.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "OpenAlex does not require proxies. Leave default unless your network blocks direct access." } } }, "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 } } } } } } } } } }