{ "openapi": "3.0.1", "info": { "title": "arXiv Scraper: Papers, Authors, Categories & Search", "description": "Scrape arxiv.org via the official Atom API. Full-text search, by author / title / category, paper detail by id, latest in any category. Returns title, abstract, authors, DOI, PDF link. No auth, no proxies. Pay only per result item.", "version": "0.1", "x-build-id": "yhrD2JnWcUf9lWdtq" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/perconey~arxiv-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-perconey-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/perconey~arxiv-scraper/runs": { "post": { "operationId": "runs-sync-perconey-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/perconey~arxiv-scraper/run-sync": { "post": { "operationId": "run-sync-perconey-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "action" ], "properties": { "action": { "title": "What do you want to scrape?", "enum": [ "getLatestPapers", "searchPapers", "getPapersByAuthor", "getPapersByCategory", "getPapersByTitle", "getPaperDetail" ], "type": "string", "description": "Pick the action. searchPapers / getPapersByAuthor / getPapersByCategory / getPapersByTitle / getPaperDetail need at least one entry in queries. getLatestPapers takes an optional category.", "default": "getLatestPapers" }, "queries": { "title": "Queries", "type": "array", "description": "One entry per query. searchPapers: free text. getPapersByAuthor: surname (e.g. Bengio). getPapersByCategory: arXiv category code. getPapersByTitle: phrase to match. getPaperDetail: arXiv id. getLatestPapers: leave empty.", "items": { "type": "string" } }, "category": { "title": "Category filter (getLatestPapers only)", "type": "string", "description": "arXiv category code. Examples: cs.AI (AI), cs.CL (NLP), cs.CV (Vision), cs.LG (Machine Learning), stat.ML, math.OC, q-bio.QM. Default: cs.AI.", "default": "cs.AI" }, "maxItems": { "title": "Max items per query", "minimum": 0, "maximum": 30000, "type": "integer", "description": "Stop after this many items per query. arXiv API caps a single call at 30,000 but we paginate in batches of 100 with a 3 s delay between batches (per arXiv API guidelines).", "default": 30 }, "sortBy": { "title": "Sort order", "enum": [ "submittedDate", "relevance", "lastUpdatedDate" ], "type": "string", "description": "submittedDate = newest first (default for getLatestPapers). relevance = best match (default for search actions). lastUpdatedDate = most-recently-revised first.", "default": "submittedDate" }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "arxiv aggressively rate-limits per IP. The default (Apify proxy with datacenter group) rotates IPs and bypasses the limit. Disable only if you intend to run from a single trusted IP.", "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 } } } } } } } } } }