{ "openapi": "3.0.1", "info": { "title": "arXiv Paper Scraper — Abstracts, Authors & Metadata", "description": "Scrape research paper metadata from arXiv.org the worlds largest open-access repository. Search by keyword across computer science physics mathematics biology. Returns titles abstracts authors categories PDF links and DOIs. No API key required.", "version": "1.0", "x-build-id": "KPZYtAnmeRTc1rbph" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/logiover~arxiv-paper-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-logiover-arxiv-paper-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/logiover~arxiv-paper-scraper/runs": { "post": { "operationId": "runs-sync-logiover-arxiv-paper-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/logiover~arxiv-paper-scraper/run-sync": { "post": { "operationId": "run-sync-logiover-arxiv-paper-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQueries": { "title": "Search Queries", "type": "array", "description": "Optional. Search terms to query on arXiv (author names, paper titles, keywords, topics like 'large language models'). You can also use arXiv field syntax such as 'ti:transformer' or 'au:hinton'. Leave EMPTY to browse the most recent submissions in the chosen category (or cs.AI by default).", "default": [], "items": { "type": "string" } }, "category": { "title": "arXiv Category", "enum": [ "", "cs.AI", "cs.CL", "cs.CV", "cs.LG", "cs.NE", "cs.RO", "cs.CR", "cs.DC", "cs.DS", "cs.SE", "cs.IR", "cs.HC", "cs.SI", "cs.CY", "cs.DB", "cs.GT", "cs.PL", "cs.OS", "cs.AR", "stat.ML", "stat.ME", "stat.AP", "stat.TH", "math.OC", "math.PR", "math.ST", "math.NA", "math.CO", "math.AG", "math.NT", "physics.optics", "physics.comp-ph", "physics.data-an", "physics.med-ph", "physics.soc-ph", "physics.flu-dyn", "astro-ph.GA", "astro-ph.CO", "astro-ph.EP", "astro-ph.HE", "astro-ph.SR", "cond-mat.mtrl-sci", "cond-mat.stat-mech", "cond-mat.mes-hall", "cond-mat.supr-con", "quant-ph", "hep-ph", "hep-th", "hep-ex", "gr-qc", "nucl-th", "nlin.CD", "q-bio.GN", "q-bio.NC", "q-bio.BM", "q-bio.PE", "q-fin.PM", "q-fin.TR", "q-fin.ST", "q-fin.CP", "econ.EM", "econ.TH", "eess.SP", "eess.IV", "eess.AS", "eess.SY" ], "type": "string", "description": "Optional. Restrict results to a single arXiv subject category. Leave empty to search across all categories. If no search query is given, this category is browsed newest-first.", "default": "" }, "categories": { "title": "Additional Categories (advanced)", "type": "array", "description": "Optional advanced field. Extra arXiv category codes to include (OR-combined with the category above), e.g. cs.AI, stat.ML. Most users only need the dropdown above.", "default": [], "items": { "type": "string" } }, "maxResults": { "title": "Max Results", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Maximum total number of papers to return across all search queries.", "default": 200 }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "lastUpdatedDate", "submittedDate" ], "type": "string", "description": "Sort field for results.", "default": "submittedDate" }, "sortOrder": { "title": "Sort Order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Ascending or descending order (ignored when Sort By is Relevance).", "default": "descending" }, "dateFrom": { "title": "Submitted After (YYYY-MM-DD)", "type": "string", "description": "Optional. Only include papers submitted on/after this date (YYYY-MM-DD). Leave empty for no date filter.", "default": "" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "arXiv is a clean public API. Apify Proxy (Automatic) is used with a direct-connection fallback on the final retry.", "default": { "useApifyProxy": 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 } } }, "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 } } } } } } } } } }