{ "openapi": "3.0.1", "info": { "title": "OpenAlex Scraper", "description": "Scrape scholarly works, authors, institutions and journals from OpenAlex by search, filter or link: titles, abstracts, DOIs, citation counts, open-access PDF links, venues, authors with ORCID and affiliations, h-index. Clean JSON, no login.", "version": "1.0", "x-build-id": "holo3qiRBvvZKyOLZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/anyxsolutions~openalex-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-anyxsolutions-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/anyxsolutions~openalex-scraper/runs": { "post": { "operationId": "runs-sync-anyxsolutions-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/anyxsolutions~openalex-scraper/run-sync": { "post": { "operationId": "run-sync-anyxsolutions-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "startUrls": { "title": "OpenAlex URLs", "type": "array", "description": "openalex.org pages: a list with its search, filters and sort, such as https://openalex.org/works?search=large%20language%20models&filter=is_oa:true (also /authors, /institutions, /sources), or a single record such as https://openalex.org/W2741809807. DOI (https://doi.org/10.7717/peerj.4375), ORCID and ROR links work too.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Keywords to search OpenAlex for, one search per line, for example crispr gene therapy or \"graph neural network\". Each term searches the entity type picked below, with the filters and sort below.", "items": { "type": "string" } }, "entityType": { "title": "Search in", "enum": [ "works", "authors", "institutions", "sources" ], "type": "string", "description": "What the search terms and filters look for: works (papers, preprints, books, datasets), authors, institutions, or sources (journals and repositories).", "default": "works" }, "maxItems": { "title": "Maximum results per URL or search", "minimum": 1, "type": "integer", "description": "Maximum number of results to return per start URL or search term. Leave empty to get every match." }, "filters": { "title": "Filters", "type": "string", "description": "OpenAlex filters, comma-separated, combined with AND, for example type:article,publication_year:2020-2024,authorships.institutions.ror:00f54p054,primary_topic.field.id:17 for works, or last_known_institutions.country_code:DE for authors. With no search terms, the filters alone define the list." }, "yearFrom": { "title": "Published from year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Only works published in or after this year, for example 2020. Works only." }, "yearTo": { "title": "Published until year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Only works published in or before this year, for example 2024. Works only." }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Only works that are free to read somewhere (gold, green, hybrid, bronze or diamond open access). Works only.", "default": false }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "citedByCount", "worksCount", "newest", "oldest" ], "type": "string", "description": "Order of the search-term results: best match first, most cited, most works (authors, institutions, sources), or newest or oldest publication date (works).", "default": "relevance" }, "apiKey": { "title": "OpenAlex API key", "type": "string", "description": "Optional. Your free OpenAlex API key from openalex.org/settings/api, for example a 32-character key. Without one, OpenAlex allows about 100 searches or 1,000 filtered pages per day; a key raises that tenfold." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy settings. OpenAlex needs no proxy; the Actor keeps within OpenAlex's request rate.", "default": { "useApifyProxy": false } } } }, "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 } } } } } } } } } }