{ "openapi": "3.0.1", "info": { "title": "arXiv Metadata Collector— Metadata, PDF, Authors & Abstract", "description": "Scrape arXiv research papers with metadata including title, authors, abstract, PDF links, DOI, and categories. Supports keyword search, proxy integration, and structured dataset output for AI, ML, and academic research use", "version": "0.0", "x-build-id": "5yihV5uneiEqVvD7j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapepilot~arxiv-metadata-collector---metadata-pdf-authors-abstract/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapepilot-arxiv-metadata-collector---metadata-pdf-authors-abstract", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapepilot~arxiv-metadata-collector---metadata-pdf-authors-abstract/runs": { "post": { "operationId": "runs-sync-scrapepilot-arxiv-metadata-collector---metadata-pdf-authors-abstract", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapepilot~arxiv-metadata-collector---metadata-pdf-authors-abstract/run-sync": { "post": { "operationId": "run-sync-scrapepilot-arxiv-metadata-collector---metadata-pdf-authors-abstract", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "demo_mode": { "title": "🎯 Demo Mode", "type": "boolean", "description": "ON → instantly returns 10 landmark AI/ML papers (Transformers, BERT, GPT-3, LLaMA, etc.) without making API calls.", "default": false }, "search_query": { "title": "Search Query", "type": "string", "description": "Keywords to search across all paper fields. E.g: 'machine learning', 'neural network', 'transformer', 'climate change'" }, "author": { "title": "Author Search", "type": "string", "description": "Search by author name. E.g: 'Geoffrey Hinton', 'Yann LeCun', 'Andrew Ng'" }, "category": { "title": "arXiv Category", "enum": [ "", "cs.LG", "cs.AI", "cs.CL", "cs.CV", "cs.RO", "stat.ML", "math", "physics", "econ", "q-bio", "q-fin" ], "type": "string", "description": "Filter by arXiv subject category", "default": "" }, "title_only": { "title": "Title Search Only", "type": "boolean", "description": "ON → search only in paper titles (faster, more precise). OFF → search entire paper including abstract.", "default": false }, "sort_by": { "title": "Sort Results By", "enum": [ "relevance", "date", "updated" ], "type": "string", "description": "How to sort the returned papers", "default": "relevance" }, "date_from": { "title": "Published After (YYYY-MM-DD)", "type": "string", "description": "Only return papers published after this date. E.g: 2024-01-01" }, "max_results": { "title": "Max Papers", "maximum": 2000, "type": "integer", "description": "Maximum number of papers to return (arXiv allows up to 2000 per request)", "default": 20 }, "proxyConfiguration": { "title": "Proxy (Optional)", "type": "object", "description": "arXiv is a free public API — proxy optional, but RESIDENTIAL helps for bulk requests." } } }, "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 } } } } } } } } } }