{ "openapi": "3.0.1", "info": { "title": "arXiv Papers Scraper", "description": "Scrape academic preprints from arXiv.org by keyword, author, or category. Returns clean records with title, authors, abstract, categories, PDF URL, DOI. HTTP-only via the public arXiv API. No login, no proxy.", "version": "1.0", "x-build-id": "SBL4eaoLVASb30hhK" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~arxiv-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-arxiv-papers-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~arxiv-papers-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~arxiv-papers-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "string", "description": "Free-text query against title + abstract + authors. e.g. `transformer attention`, `large language models`. Combined with `categories` if both are set.", "default": "large language models" }, "categories": { "title": "Categories (multi-select)", "type": "array", "description": "arXiv subject categories. Empty = all categories.", "items": { "type": "string", "enum": [ "cs.AI", "cs.LG", "cs.CL", "cs.CV", "cs.NE", "cs.RO", "cs.CR", "cs.DB", "cs.DC", "cs.DS", "cs.GT", "cs.HC", "cs.IR", "cs.IT", "cs.LO", "cs.MA", "cs.MM", "cs.NI", "cs.OS", "cs.PL", "cs.SC", "cs.SD", "cs.SE", "cs.SI", "cs.SY", "stat.ML", "stat.AP", "stat.CO", "stat.ME", "stat.TH", "math.PR", "math.ST", "math.OC", "math.NA", "math.CO", "math.AT", "math.AG", "physics.optics", "physics.comp-ph", "physics.data-an", "quant-ph", "cond-mat.mes-hall", "cond-mat.dis-nn", "q-bio.NC", "q-bio.QM", "q-bio.GN", "q-bio.MN", "q-fin.ST", "q-fin.TR", "q-fin.RM", "econ.EM", "econ.TH" ], "enumTitles": [ "CS / Artificial Intelligence", "CS / Machine Learning", "CS / Computation & Language (NLP)", "CS / Computer Vision", "CS / Neural & Evolutionary Computing", "CS / Robotics", "CS / Cryptography & Security", "CS / Databases", "CS / Distributed Computing", "CS / Data Structures & Algorithms", "CS / Game Theory", "CS / Human-Computer Interaction", "CS / Information Retrieval", "CS / Information Theory", "CS / Logic in CS", "CS / Multiagent Systems", "CS / Multimedia", "CS / Networking & Internet", "CS / Operating Systems", "CS / Programming Languages", "CS / Symbolic Computation", "CS / Sound", "CS / Software Engineering", "CS / Social & Information Networks", "CS / Systems & Control", "Stats / Machine Learning", "Stats / Applications", "Stats / Computation", "Stats / Methodology", "Stats / Theory", "Math / Probability", "Math / Statistics Theory", "Math / Optimization & Control", "Math / Numerical Analysis", "Math / Combinatorics", "Math / Algebraic Topology", "Math / Algebraic Geometry", "Physics / Optics", "Physics / Computational Physics", "Physics / Data Analysis", "Quantum Physics", "Cond-mat / Mesoscale & Nanoscale", "Cond-mat / Disordered Systems", "Q-bio / Neurons & Cognition", "Q-bio / Quantitative Methods", "Q-bio / Genomics", "Q-bio / Molecular Networks", "Q-fin / Statistical Finance", "Q-fin / Trading & Microstructure", "Q-fin / Risk Management", "Econ / Econometrics", "Econ / Theoretical Economics" ] }, "default": [] }, "authorContains": { "title": "Author name contains", "type": "string", "description": "Filter by author name (case-insensitive substring). e.g. `Yann LeCun`, `Bengio`." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "submittedDate", "lastUpdatedDate" ], "type": "string", "description": "How arXiv ranks the result list.", "default": "submittedDate" }, "sortOrder": { "title": "Sort order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Ascending = oldest first; Descending = newest first.", "default": "descending" }, "dateRangeFrom": { "title": "Date range from (YYYY-MM-DD)", "type": "string", "description": "Drop papers submitted before this date. Empty = no lower bound." }, "dateRangeTo": { "title": "Date range to (YYYY-MM-DD)", "type": "string", "description": "Drop papers submitted after this date. Empty = no upper bound." }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Hard cap on emitted records.", "default": 50 }, "includeDoiOnly": { "title": "DOI required", "type": "boolean", "description": "Drop papers that don't have a DOI (typically pre-publication preprints).", "default": false }, "minAbstractLength": { "title": "Min abstract length (chars)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Drop papers with abstracts shorter than this. Filters out incomplete records." }, "abstractContains": { "title": "Abstract contains", "type": "string", "description": "Only emit papers whose abstract contains this substring (case-insensitive)." } } }, "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 } } } } } } } } } }