{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scientific Papers & Citations Scraper — 250M+ Acade", "description": "Scrape academic papers, scientific research studies, citation metrics, author institutions, open-access PDFs, and DOIs from OpenAlex. Global scholarly literature search and monitoring.", "version": "0.1", "x-build-id": "09Z2qtlBkecieFlLE" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spotless_studios~openalex-research-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spotless_studios-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spotless_studios~openalex-research-scraper/runs": { "post": { "operationId": "runs-sync-spotless_studios-openalex-research-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spotless_studios~openalex-research-scraper/run-sync": { "post": { "operationId": "run-sync-spotless_studios-openalex-research-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Search query / topic", "type": "string", "description": "Search title, abstract, and fulltext across 250M+ works (e.g. 'large language models', 'CRISPR gene editing', 'solid state battery').", "default": "large language models" }, "searchQueries": { "title": "Multiple search queries", "type": "array", "description": "Optional list of multiple research queries to run sequentially in a single job.", "items": { "type": "string" } }, "workType": { "title": "Publication type", "enum": [ "all", "article", "preprint", "review", "book-chapter", "dataset", "dissertation" ], "type": "string", "description": "Filter by scholarly work type.", "default": "all" }, "fromYear": { "title": "From publication year", "minimum": 1900, "type": "integer", "description": "Minimum publication year (e.g. 2023)." }, "toYear": { "title": "To publication year", "minimum": 1900, "type": "integer", "description": "Maximum publication year (e.g. 2026)." }, "minCitations": { "title": "Minimum citation count", "minimum": 0, "type": "integer", "description": "Only return works cited at least this many times." }, "openAccessOnly": { "title": "Open Access (OA) PDF only", "type": "boolean", "description": "When enabled, only returns works with free full-text Open Access links.", "default": false }, "institutionName": { "title": "Author institution filter", "type": "string", "description": "Filter works by institution name (e.g. 'Stanford University', 'MIT', 'Oxford')." }, "countryCode": { "title": "Institution country code", "type": "string", "description": "Two-letter ISO country code of the author's institution (e.g. 'US', 'GB', 'DE', 'CH')." }, "authorOrcid": { "title": "Author ORCID", "type": "string", "description": "Filter works by a specific author's ORCID (e.g. '0000-0002-1825-0097')." }, "funderName": { "title": "Grant funder filter", "type": "string", "description": "Keep only works funded by a matching agency (e.g. 'National Science Foundation', 'NIH', 'European Commission')." }, "sortBy": { "title": "Sort by", "enum": [ "cited_by_count:desc", "publication_date:desc", "relevance_score:desc" ], "type": "string", "description": "Order results by citation count, publication date, or relevance.", "default": "cited_by_count:desc" }, "workIds": { "title": "Direct DOIs or OpenAlex IDs", "type": "array", "description": "Scrape specific works directly by DOI ('10.1038/s41586-021-03819-2') or OpenAlex ID ('W2741809807').", "items": { "type": "string" } }, "includeKeywords": { "title": "Include keywords", "type": "array", "description": "Keep only papers matching these keywords or /regex/ in title, abstract, authors, or concepts.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Skip papers matching any of these keywords or /regex/.", "items": { "type": "string" } }, "keywordMatch": { "title": "Include keyword logic", "enum": [ "any", "all" ], "type": "string", "description": "Require any or all includeKeywords to match.", "default": "any" }, "onlyNewItems": { "title": "Only new papers (monitoring mode)", "type": "boolean", "description": "Remember seen work IDs across runs and emit only newly discovered publications.", "default": false }, "stateKey": { "title": "Monitor state name", "type": "string", "description": "Separate state key per saved search or schedule.", "default": "default" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of scholarly works to save.", "default": 100 }, "outputPreset": { "title": "Data preset", "enum": [ "full", "lean", "contacts" ], "type": "string", "description": "Choose full record, lean summary, or contacts & links only.", "default": "full" }, "outputFields": { "title": "Output fields", "type": "array", "description": "Keep only these specific fields in each saved record.", "items": { "type": "string" } }, "excludeFields": { "title": "Exclude fields", "type": "array", "description": "Remove specific fields from each saved record.", "items": { "type": "string" } }, "includeEmptyFields": { "title": "Keep empty / null fields", "type": "boolean", "description": "When disabled, strips null and empty values from each saved record.", "default": true }, "requiredFields": { "title": "Required non-empty fields", "type": "array", "description": "Only save records where every listed field has a non-empty value (e.g. pdfUrl, abstract).", "items": { "type": "string" } }, "maxPages": { "title": "Max search pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum search pages per query (100 works per page).", "default": 15 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 15, "type": "integer", "description": "Parallel requests when fetching direct DOIs or work IDs.", "default": 5 }, "maxRequestRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries per failed HTTP request.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per HTTP request.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy settings.", "default": { "useApifyProxy": false } }, "proxyEscalation": { "title": "Auto-escalate proxies when blocked", "type": "boolean", "description": "Automatically step up from direct to Apify datacenter/residential proxies if blocked.", "default": true } } }, "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 } } } } } } } } } }