{ "openapi": "3.0.1", "info": { "title": "Scholarly Papers Scraper: OpenAlex and arXiv", "description": "Scrape scholarly papers from OpenAlex and arXiv. Get abstracts, citations, field weighted impact, open access links, topics, authors with institutions and countries, funders and retraction flags, plus author and institution profiles with h-index. Export to CSV or Excel.", "version": "1.0", "x-build-id": "MVSippVRn4kzHSRIv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parselab~openalex-arxiv-scholarly-works-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parselab-openalex-arxiv-scholarly-works-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parselab~openalex-arxiv-scholarly-works-scraper/runs": { "post": { "operationId": "runs-sync-parselab-openalex-arxiv-scholarly-works-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parselab~openalex-arxiv-scholarly-works-scraper/run-sync": { "post": { "operationId": "run-sync-parselab-openalex-arxiv-scholarly-works-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "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." }, "mode": { "title": "What to collect", "enum": [ "arxiv", "works", "authors", "institutions" ], "type": "string", "description": "arXiv preprints needs no setup. Works, authors and institutions come from OpenAlex, a catalog of more than 250 million papers, and work best with a free OpenAlex access code.", "default": "arxiv" }, "searchTerms": { "title": "Search terms", "type": "array", "description": "Words or phrases, for example retrieval augmented generation or perovskite solar cells. Each term is searched on its own. For authors and institutions it is a name.", "items": { "type": "string" } }, "searchIn": { "title": "Search in", "enum": [ "everything", "titleAbstract" ], "type": "string", "description": "Works mode. Everything includes the full text when it is available. Title and abstract gives tighter results.", "default": "everything" }, "arxivCategories": { "title": "arXiv categories", "type": "array", "description": "arXiv mode. For example cs.AI, cs.LG, stat.ML, physics.optics, q-bio.NC.", "items": { "type": "string" } }, "arxivSort": { "title": "arXiv order", "enum": [ "submitted", "updated", "relevance" ], "type": "string", "description": "arXiv mode.", "default": "submitted" }, "yearFrom": { "title": "From year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "First publication year." }, "yearTo": { "title": "To year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Last publication year." }, "dateFrom": { "title": "From date", "type": "string", "description": "First publication date, in the form 2025-01-31. It replaces the year." }, "dateTo": { "title": "To date", "type": "string", "description": "Last publication date." }, "workTypes": { "title": "Types of work", "type": "array", "description": "Works mode. For example article, review, preprint, book-chapter, dissertation, dataset.", "items": { "type": "string" } }, "fields": { "title": "Research fields", "type": "array", "description": "Works mode. Names such as Medicine, Computer Science, Physics and Astronomy, Economics, Econometrics and Finance.", "items": { "type": "string" } }, "countries": { "title": "Countries", "type": "array", "description": "Two letter country codes of the authors institutions, for example US, GB, DE, CN. For institutions mode it is the country of the institution.", "items": { "type": "string" } }, "institutions": { "title": "Institutions", "type": "array", "description": "Works and authors modes. Names such as Stanford University or OpenAlex ids such as I97018004. The first match of each name is used.", "items": { "type": "string" } }, "authors": { "title": "Authors", "type": "array", "description": "Works and arXiv modes. Author names, ORCID numbers or OpenAlex ids.", "items": { "type": "string" } }, "openAccessOnly": { "title": "Only open access works", "type": "boolean", "description": "Works mode.", "default": false }, "openAccessStatuses": { "title": "Open access kinds", "type": "array", "description": "Works mode. gold, green, hybrid, bronze, diamond or closed.", "items": { "type": "string" } }, "minCitations": { "title": "Minimum citations", "minimum": 0, "type": "integer", "description": "Works, authors and institutions modes." }, "hasAbstractOnly": { "title": "Only works with an abstract", "type": "boolean", "description": "Works mode.", "default": false }, "retractedOnly": { "title": "Only retracted works", "type": "boolean", "description": "Works mode. Lists works that were retracted.", "default": false }, "sortBy": { "title": "Sort by", "enum": [ "citations", "newest", "relevance", "fwci", "works" ], "type": "string", "description": "Works, authors and institutions modes. Works can also be sorted by field weighted citation impact.", "default": "citations" }, "institutionTypes": { "title": "Institution types", "type": "array", "description": "Institutions mode. education, healthcare, company, government, nonprofit, facility, archive or other.", "items": { "type": "string" } }, "minWorks": { "title": "Minimum works", "minimum": 0, "type": "integer", "description": "Authors and institutions modes." }, "minHIndex": { "title": "Minimum h-index", "minimum": 0, "type": "integer", "description": "Authors and institutions modes." }, "openAlexApiKey": { "title": "OpenAlex access code (recommended)", "type": "string", "description": "Free code from openalex.org. Without it OpenAlex gives a very small daily budget that all users of the same network address share, so works, authors and institutions runs may stop early. arXiv needs no code." }, "contactEmail": { "title": "Contact email (optional)", "type": "string", "description": "Sent to OpenAlex as a courtesy contact." } } }, "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 } } } } } } } } } }