{ "openapi": "3.0.1", "info": { "title": "arXiv Paper Scraper with Citation Metrics", "description": "Search arXiv research papers and enrich them with OpenAlex citation counts, FWCI, citing papers and references. Export to CSV, Excel, JSON or XML.", "version": "0.1", "x-build-id": "YYzqFck04EO4RMbNh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/punkrecordsdata~arxiv-research-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-punkrecordsdata-arxiv-research-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/punkrecordsdata~arxiv-research-papers-scraper/runs": { "post": { "operationId": "runs-sync-punkrecordsdata-arxiv-research-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/punkrecordsdata~arxiv-research-papers-scraper/run-sync": { "post": { "operationId": "run-sync-punkrecordsdata-arxiv-research-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "searchTerms" ], "properties": { "searchTerms": { "title": "Search terms", "type": "array", "description": "One search per term. Uses arXiv's own query syntax on the selected field (e.g. \"large language models\", \"quantum error correction\").", "items": { "type": "string" } }, "arxivIds": { "title": "Specific arXiv IDs", "type": "array", "description": "Fetch exact papers by arXiv ID (e.g. 1706.03762 or 2303.08774v3). Runs in addition to search terms.", "items": { "type": "string" } }, "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" }, "searchField": { "title": "Search in", "enum": [ "all", "ti", "abs", "au", "cat", "co" ], "type": "string", "description": "Which arXiv field the search terms match against.", "default": "all" }, "categories": { "title": "Limit to categories", "type": "array", "description": "Optional arXiv category filter combined with the search terms (AND). Pick one or more.", "items": { "type": "string", "enum": [ "cs.AI", "cs.AR", "cs.CC", "cs.CE", "cs.CG", "cs.CL", "cs.CR", "cs.CV", "cs.CY", "cs.DB", "cs.DC", "cs.DL", "cs.DM", "cs.DS", "cs.ET", "cs.FL", "cs.GL", "cs.GR", "cs.GT", "cs.HC", "cs.IR", "cs.IT", "cs.LG", "cs.LO", "cs.MA", "cs.MM", "cs.MS", "cs.NA", "cs.NE", "cs.NI", "cs.OH", "cs.OS", "cs.PF", "cs.PL", "cs.RO", "cs.SC", "cs.SD", "cs.SE", "cs.SI", "cs.SY", "econ.EM", "econ.GN", "econ.TH", "eess.AS", "eess.IV", "eess.SP", "eess.SY", "math.AC", "math.AG", "math.AP", "math.AT", "math.CA", "math.CO", "math.CT", "math.CV", "math.DG", "math.DS", "math.FA", "math.GM", "math.GN", "math.GR", "math.GT", "math.HO", "math.IT", "math.KT", "math.LO", "math.MG", "math.MP", "math.NA", "math.NT", "math.OA", "math.OC", "math.PR", "math.QA", "math.RA", "math.RT", "math.SG", "math.SP", "math.ST", "astro-ph.CO", "astro-ph.EP", "astro-ph.GA", "astro-ph.HE", "astro-ph.IM", "astro-ph.SR", "cond-mat.dis-nn", "cond-mat.mes-hall", "cond-mat.mtrl-sci", "cond-mat.other", "cond-mat.quant-gas", "cond-mat.soft", "cond-mat.stat-mech", "cond-mat.str-el", "cond-mat.supr-con", "gr-qc", "hep-ex", "hep-lat", "hep-ph", "hep-th", "math-ph", "nlin.AO", "nlin.CD", "nlin.CG", "nlin.PS", "nlin.SI", "nucl-ex", "nucl-th", "physics.acc-ph", "physics.ao-ph", "physics.app-ph", "physics.atm-clus", "physics.atom-ph", "physics.bio-ph", "physics.chem-ph", "physics.class-ph", "physics.comp-ph", "physics.data-an", "physics.ed-ph", "physics.flu-dyn", "physics.gen-ph", "physics.geo-ph", "physics.hist-ph", "physics.ins-det", "physics.med-ph", "physics.optics", "physics.plasm-ph", "physics.pop-ph", "physics.soc-ph", "physics.space-ph", "quant-ph", "q-bio.BM", "q-bio.CB", "q-bio.GN", "q-bio.MN", "q-bio.NC", "q-bio.OT", "q-bio.PE", "q-bio.QM", "q-bio.SC", "q-bio.TO", "q-fin.CP", "q-fin.EC", "q-fin.GN", "q-fin.MF", "q-fin.PM", "q-fin.PR", "q-fin.RM", "q-fin.ST", "q-fin.TR", "stat.AP", "stat.CO", "stat.ME", "stat.ML", "stat.OT", "stat.TH" ], "enumTitles": [ "CS: Artificial Intelligence", "CS: Hardware Architecture", "CS: Computational Complexity", "CS: Computational Engineering", "CS: Computational Geometry", "CS: Computation and Language (NLP)", "CS: Cryptography and Security", "CS: Computer Vision", "CS: Computers and Society", "CS: Databases", "CS: Distributed Computing", "CS: Digital Libraries", "CS: Discrete Mathematics", "CS: Data Structures and Algorithms", "CS: Emerging Technologies", "CS: Formal Languages", "CS: General Literature", "CS: Graphics", "CS: Game Theory", "CS: Human-Computer Interaction", "CS: Information Retrieval", "CS: Information Theory", "CS: Machine Learning", "CS: Logic in Computer Science", "CS: Multiagent Systems", "CS: Multimedia", "CS: Mathematical Software", "CS: Numerical Analysis", "CS: Neural and Evolutionary Computing", "CS: Networking and Internet", "CS: Other Computer Science", "CS: Operating Systems", "CS: Performance", "CS: Programming Languages", "CS: Robotics", "CS: Symbolic Computation", "CS: Sound", "CS: Software Engineering", "CS: Social and Information Networks", "CS: Systems and Control", "Econ: Econometrics", "Econ: General Economics", "Econ: Theoretical Economics", "EESS: Audio and Speech Processing", "EESS: Image and Video Processing", "EESS: Signal Processing", "EESS: Systems and Control", "Math: Commutative Algebra", "Math: Algebraic Geometry", "Math: Analysis of PDEs", "Math: Algebraic Topology", "Math: Classical Analysis", "Math: Combinatorics", "Math: Category Theory", "Math: Complex Variables", "Math: Differential Geometry", "Math: Dynamical Systems", "Math: Functional Analysis", "Math: General Mathematics", "Math: General Topology", "Math: Group Theory", "Math: Geometric Topology", "Math: History and Overview", "Math: Information Theory", "Math: K-Theory and Homology", "Math: Logic", "Math: Metric Geometry", "Math: Mathematical Physics", "Math: Numerical Analysis", "Math: Number Theory", "Math: Operator Algebras", "Math: Optimization and Control", "Math: Probability", "Math: Quantum Algebra", "Math: Rings and Algebras", "Math: Representation Theory", "Math: Symplectic Geometry", "Math: Spectral Theory", "Math: Statistics Theory", "Astro: Cosmology", "Astro: Earth and Planetary", "Astro: Galaxies", "Astro: High Energy Phenomena", "Astro: Instrumentation", "Astro: Solar and Stellar", "CondMat: Disordered Systems", "CondMat: Mesoscale Physics", "CondMat: Materials Science", "CondMat: Other", "CondMat: Quantum Gases", "CondMat: Soft Matter", "CondMat: Statistical Mechanics", "CondMat: Strongly Correlated", "CondMat: Superconductivity", "General Relativity and Quantum Cosmology", "HEP: Experiment", "HEP: Lattice", "HEP: Phenomenology", "HEP: Theory", "Mathematical Physics", "Nonlinear: Adaptation", "Nonlinear: Chaotic Dynamics", "Nonlinear: Cellular Automata", "Nonlinear: Pattern Formation", "Nonlinear: Integrable Systems", "Nuclear Experiment", "Nuclear Theory", "Physics: Accelerator", "Physics: Atmospheric and Oceanic", "Physics: Applied", "Physics: Atomic Clusters", "Physics: Atomic", "Physics: Biological", "Physics: Chemical", "Physics: Classical", "Physics: Computational", "Physics: Data Analysis", "Physics: Education", "Physics: Fluid Dynamics", "Physics: General", "Physics: Geophysics", "Physics: History", "Physics: Instrumentation", "Physics: Medical", "Physics: Optics", "Physics: Plasma", "Physics: Popular", "Physics: Society", "Physics: Space", "Quantum Physics", "QBio: Biomolecules", "QBio: Cell Behavior", "QBio: Genomics", "QBio: Molecular Networks", "QBio: Neurons and Cognition", "QBio: Other", "QBio: Populations and Evolution", "QBio: Quantitative Methods", "QBio: Subcellular Processes", "QBio: Tissues and Organs", "QFin: Computational Finance", "QFin: Economics", "QFin: General Finance", "QFin: Mathematical Finance", "QFin: Portfolio Management", "QFin: Pricing of Securities", "QFin: Risk Management", "QFin: Statistical Finance", "QFin: Trading and Market Microstructure", "Stat: Applications", "Stat: Computation", "Stat: Methodology", "Stat: Machine Learning", "Stat: Other", "Stat: Theory" ] }, "default": [] }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "lastUpdatedDate", "submittedDate" ], "type": "string", "description": "Order of the arXiv search results.", "default": "relevance" }, "sortOrder": { "title": "Sort order", "enum": [ "ascending", "descending" ], "type": "string", "description": "Ascending or descending.", "default": "descending" }, "includeMetrics": { "title": "Citation metrics (OpenAlex)", "type": "boolean", "description": "Enrich each paper with OpenAlex metrics: citation count, FWCI, open-access status and top concepts. Charged only when a confident match is found.", "default": true }, "includeCitations": { "title": "Citing papers", "type": "boolean", "description": "Fetch papers that cite each result (one dataset row per citing paper, newest first).", "default": false }, "maxCitationsPerPaper": { "title": "Max citing papers per paper", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap on citation rows fetched for each paper.", "default": 25 }, "includeReferences": { "title": "Referenced papers", "type": "boolean", "description": "Fetch the works each paper references (one dataset row per reference).", "default": false }, "maxReferencesPerPaper": { "title": "Max references per paper", "minimum": 1, "maximum": 200, "type": "integer", "description": "Cap on reference rows fetched for each paper.", "default": 25 } } }, "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 } } } } } } } } } }