{ "openapi": "3.0.1", "info": { "title": "arXiv Scraper", "description": "Search and extract academic papers from arXiv.org. Get paper titles, authors, abstracts, categories, and PDF links for AI/ML, physics, math, and more.", "version": "1.0", "x-build-id": "2RmbZcAwONWU1upsV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/artificially~arxiv-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-artificially-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/artificially~arxiv-scraper/runs": { "post": { "operationId": "runs-sync-artificially-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/artificially~arxiv-scraper/run-sync": { "post": { "operationId": "run-sync-artificially-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "searchQuery" ], "properties": { "searchQuery": { "title": "Search Query", "type": "string", "description": "Keywords to search arXiv papers. All words must match (title, abstract, authors, comments). Use quotes for exact phrases or arXiv field syntax for advanced queries. Example: \"large language models\" or ti:transformer AND au:vaswani." }, "category": { "title": "Category", "type": "string", "description": "Optional arXiv category code to restrict results. Example: \"cs.AI\" (artificial intelligence), \"cs.LG\" (machine learning), \"cs.CL\" (NLP), \"math.CO\", \"physics.gen-ph\", \"q-bio.NC\"." }, "maxPapers": { "title": "Maximum Papers", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of papers to save (1-1000). Each saved paper is one dataset item. Use 5-20 for quick answers.", "default": 100 }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "lastUpdatedDate", "submittedDate" ], "type": "string", "description": "Result order: \"submittedDate\" (newest submissions first), \"lastUpdatedDate\" (most recently updated first) or \"relevance\" (best keyword match first).", "default": "submittedDate" }, "compactOutput": { "title": "Compact output (for AI agents)", "type": "boolean", "description": "If true, each dataset item is a slim record with only key decision fields (arXiv ID, title, first 10 authors, author count, categories, dates, 300-character abstract preview, DOI, citation counts, PDF and arXiv URLs) instead of full abstracts, author profiles, references and related papers. Recommended for AI agents and MCP clients. If false, the full record is returned.", "default": false }, "includeCitations": { "title": "Include Citations", "type": "boolean", "description": "If true, adds citation counts, influential citations and citations per year from Semantic Scholar.", "default": true }, "includeAuthorProfiles": { "title": "Include Author Profiles", "type": "boolean", "description": "If true, adds authorProfiles with each author's h-index, total citations, paper count and affiliations from Semantic Scholar.", "default": true }, "includeReferences": { "title": "Include References", "type": "boolean", "description": "If true, adds references: the papers cited by each result (bibliography).", "default": false }, "maxReferences": { "title": "Max References", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum references listed per paper (1-50) when includeReferences is true. Example: 10.", "default": 10 }, "includeRelatedPapers": { "title": "Include Related Papers", "type": "boolean", "description": "If true, adds relatedPapers: Semantic Scholar recommendations of similar papers.", "default": false }, "maxRelatedPapers": { "title": "Max Related Papers", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum related papers listed per result (1-20) when includeRelatedPapers is true. Example: 5.", "default": 5 }, "semanticScholarApiKey": { "title": "Semantic Scholar API key (optional)", "type": "string", "description": "Optional free API key from semanticscholar.org/product/api. Without it, citation and author data uses Semantic Scholar's shared public rate limit and may be missing when that pool is busy (the paper itself is still saved with full arXiv metadata)." }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional proxy settings. Not needed for normal use: arXiv and Semantic Scholar APIs are public." } } }, "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 } } } } } } } } } }