{ "openapi": "3.0.1", "info": { "title": "arXiv Research Paper Scraper", "description": "Extract comprehensive research paper data from arXiv search results including titles, authors, abstracts, categories, and more.", "version": "1.3", "x-build-id": "PGNbtvgwbicgQTBgY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/codingfrontend~arxiv-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-codingfrontend-arxiv-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/codingfrontend~arxiv-search-scraper/runs": { "post": { "operationId": "runs-sync-codingfrontend-arxiv-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/codingfrontend~arxiv-search-scraper/run-sync": { "post": { "operationId": "run-sync-codingfrontend-arxiv-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "query": { "title": "Search query", "maxLength": 500, "type": "string", "description": "Legacy single query. Required unless queries or sourceUrls/startUrls is supplied." }, "searchQuery": { "title": "Search query alias", "maxLength": 500, "type": "string", "description": "Compatibility alias for query. Do not provide a different value together with query." }, "searchKeywords": { "title": "Search keywords alias", "maxLength": 500, "type": "string", "description": "Compatibility alias for query; it is treated as the complete arXiv search expression." }, "queries": { "title": "Multiple search queries", "minItems": 1, "maxItems": 20, "type": "array", "description": "Up to 20 distinct search queries. maxItems is global across queries and deduplication is global when enabled.", "items": { "type": "string", "minLength": 1, "maxLength": 500 } }, "sourceUrls": { "title": "Source API URLs", "minItems": 1, "maxItems": 20, "type": "array", "description": "Optional HTTPS arXiv API query URLs. Each URL must include search_query; URL parameters are preserved while start and max_results are controlled by the Actor. These URLs cannot be combined with query fields.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "Public arXiv API URL", "description": "An HTTPS arXiv API query URL containing search_query.", "pattern": "^https://(export\\.)?arxiv\\.org/api/query\\?" } }, "required": [ "url" ], "additionalProperties": false } }, "startUrls": { "title": "Source API URLs (legacy alias)", "minItems": 1, "maxItems": 20, "type": "array", "description": "Compatibility alias for sourceUrls. Use one of sourceUrls or startUrls unless both arrays are identical.", "items": { "type": "object", "properties": { "url": { "type": "string", "title": "Public arXiv API URL", "description": "An HTTPS arXiv API query URL containing search_query.", "pattern": "^https://(export\\.)?arxiv\\.org/api/query\\?" } }, "required": [ "url" ], "additionalProperties": false } }, "searchType": { "title": "Search field", "enum": [ "all", "ti", "au", "abs", "co", "jr", "cat", "rn", "id" ], "type": "string", "description": "arXiv field used for generated query sources.", "default": "all" }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "lastUpdatedDate", "submittedDate" ], "type": "string", "description": "Sort order used for generated API sources. A source URL's explicit sortBy is preserved.", "default": "relevance" }, "sortOrder": { "title": "Sort direction", "enum": [ "descending", "ascending" ], "type": "string", "description": "Sort direction for generated API sources.", "default": "descending" }, "maxItems": { "title": "Maximum papers", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Global maximum of normal paper records across all queries/sources. Diagnostics do not count.", "default": 50 }, "maxResults": { "title": "Maximum papers (legacy alias)", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Compatibility alias for maxItems. Do not provide a conflicting value." }, "maxPages": { "title": "Maximum pages per source", "minimum": 1, "maximum": 100, "type": "integer", "description": "Optional page budget per source. When omitted, derives from the maximum paper count and 50-paper page size. A lower explicit budget can return partial results." }, "deduplicate": { "title": "Deduplicate papers", "type": "boolean", "description": "Deduplicate by version-independent arXiv ID across pages and sources.", "default": true }, "requestDelayMs": { "title": "Delay between pages (ms)", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Delay between API requests. Values below 3000 retain the input contract but use the publisher-required three-second minimum.", "default": 3000 }, "maxRequestRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Retries after transient network/server failures. Access-control and rate-limit responses are not retried.", "default": 2 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each public API request.", "default": 30 }, "maxResponseBytes": { "title": "Maximum response bytes", "minimum": 100000, "maximum": 10000000, "type": "integer", "description": "Safety limit for each public Atom response.", "default": 5000000 } } }, "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 } } } } } } } } } }