{ "openapi": "3.0.1", "info": { "title": "arXiv Scraper", "description": "[💰 $2.5 / 1K] Search arXiv and extract paper metadata — titles, authors, abstracts, subject categories, DOIs, journal references, submission dates, and PDF links. Search by keyword, title, author, or category, or fetch specific papers by arXiv ID.", "version": "1.0", "x-build-id": "TTDRmi48kbrTiNvGZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solidcode~arxiv-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solidcode-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/solidcode~arxiv-scraper/runs": { "post": { "operationId": "runs-sync-solidcode-arxiv-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/solidcode~arxiv-scraper/run-sync": { "post": { "operationId": "run-sync-solidcode-arxiv-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 search across the whole paper (title, abstract, authors). Example: 'large language models' or 'quantum error correction'. Advanced users can use arXiv field prefixes like ti: (title), au: (author), abs: (abstract) or cat: (category) — e.g. 'ti:transformer'." }, "title": { "title": "Title Contains", "type": "string", "description": "Only include papers whose title contains these words. Example: 'graph neural network'." }, "author": { "title": "Author", "type": "string", "description": "Only include papers by this author. Example: 'Yann LeCun' or 'Hinton'." }, "abstract": { "title": "Abstract Contains", "type": "string", "description": "Only include papers whose abstract contains these words. Example: 'reinforcement learning'." }, "categories": { "title": "Subject Categories", "uniqueItems": true, "type": "array", "description": "Restrict results to these arXiv subject areas. Leave empty to search all subjects. Papers matching any selected category are included.", "items": { "type": "string", "enum": [ "cs.AI", "cs.CL", "cs.CV", "cs.LG", "cs.NE", "cs.RO", "cs.CR", "cs.DS", "cs.DC", "cs.HC", "cs.IR", "cs.SE", "cs.SY", "stat.ML", "stat.ME", "stat.AP", "math.PR", "math.ST", "math.OC", "math.NA", "math.CO", "math.AG", "math.NT", "physics.optics", "physics.app-ph", "physics.comp-ph", "physics.med-ph", "astro-ph", "cond-mat", "gr-qc", "hep-ph", "hep-th", "nlin.CD", "nucl-th", "quant-ph", "q-bio", "q-fin.ST", "econ.EM", "eess.AS", "eess.IV", "eess.SP", "eess.SY" ], "enumTitles": [ "CS — Artificial Intelligence (cs.AI)", "CS — Computation & Language / NLP (cs.CL)", "CS — Computer Vision (cs.CV)", "CS — Machine Learning (cs.LG)", "CS — Neural & Evolutionary Computing (cs.NE)", "CS — Robotics (cs.RO)", "CS — Cryptography & Security (cs.CR)", "CS — Data Structures & Algorithms (cs.DS)", "CS — Distributed & Parallel Computing (cs.DC)", "CS — Human-Computer Interaction (cs.HC)", "CS — Information Retrieval (cs.IR)", "CS — Software Engineering (cs.SE)", "CS — Systems & Control (cs.SY)", "Statistics — Machine Learning (stat.ML)", "Statistics — Methodology (stat.ME)", "Statistics — Applications (stat.AP)", "Math — Probability (math.PR)", "Math — Statistics Theory (math.ST)", "Math — Optimization & Control (math.OC)", "Math — Numerical Analysis (math.NA)", "Math — Combinatorics (math.CO)", "Math — Algebraic Geometry (math.AG)", "Math — Number Theory (math.NT)", "Physics — Optics (physics.optics)", "Physics — Applied Physics (physics.app-ph)", "Physics — Computational Physics (physics.comp-ph)", "Physics — Medical Physics (physics.med-ph)", "Astrophysics (astro-ph)", "Condensed Matter (cond-mat)", "General Relativity & Quantum Cosmology (gr-qc)", "High Energy Physics — Phenomenology (hep-ph)", "High Energy Physics — Theory (hep-th)", "Nonlinear Sciences — Chaotic Dynamics (nlin.CD)", "Nuclear Theory (nucl-th)", "Quantum Physics (quant-ph)", "Quantitative Biology (q-bio)", "Quantitative Finance — Statistical Finance (q-fin.ST)", "Economics — Econometrics (econ.EM)", "EE — Audio & Speech Processing (eess.AS)", "EE — Image & Video Processing (eess.IV)", "EE — Signal Processing (eess.SP)", "EE — Systems & Control (eess.SY)" ] }, "default": [] }, "arxivIds": { "title": "arXiv IDs", "type": "array", "description": "Fetch specific papers by their arXiv ID — e.g. '2310.06825' or the legacy form 'cond-mat/0011267'. When provided, these papers are fetched directly and the search fields above are ignored.", "items": { "type": "string" } }, "maxResults": { "title": "Maximum Results", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Maximum number of papers to return for your search. Set to 0 to fetch all available matches — in that case a safety cap of 50,000 papers is applied so very large searches (some have hundreds of thousands of matches) don't run indefinitely. Ignored when fetching by arXiv ID.", "default": 50 }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "submittedDate", "lastUpdatedDate" ], "type": "string", "description": "How to order the results.", "default": "relevance" }, "sortOrder": { "title": "Sort Order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Order direction. Newest first is most useful when sorting by date.", "default": "descending" } } }, "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 } } } } } } } } } }