{ "openapi": "3.0.1", "info": { "title": "arXiv Research Papers & Abstracts Scraper", "description": "Scrape arXiv preprints by keyword, author or subject with arXiv ID, title, authors, abstract, subject categories, DOI, publication and update dates and PDF links. Export to JSON, CSV or Excel.", "version": "0.1", "x-build-id": "xlitZRTfkc5O5LTh4" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapers_lat~arxiv-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapers_lat-arxiv-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapers_lat~arxiv-papers-scraper/runs": { "post": { "operationId": "runs-sync-scrapers_lat-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapers_lat~arxiv-papers-scraper/run-sync": { "post": { "operationId": "run-sync-scrapers_lat-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "maxPapers": { "title": "Max Papers", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Maximum number of papers to collect. Optional." }, "searchQuery": { "title": "Search query", "type": "string", "description": "Words or phrase to search across arXiv papers (for example 'large language models', 'quantum computing', 'protein folding'). Advanced users can pass a native arXiv query with field prefixes such as 'ti:transformer AND cat:cs.CL'." }, "field": { "title": "Search in", "enum": [ "all", "ti", "abs", "au", "cat" ], "type": "string", "description": "Which field to match the search query against when a plain phrase is entered.", "default": "all" }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "newest", "lastUpdated" ], "type": "string", "description": "Order the results by relevance, newest submitted, or most recently updated.", "default": "relevance" }, "dateFrom": { "title": "Submitted after", "type": "string", "description": "Optional. Only keep papers submitted on or after this date (YYYY-MM-DD)." }, "dateTo": { "title": "Submitted before", "type": "string", "description": "Optional. Only keep papers submitted on or before this date (YYYY-MM-DD)." }, "withAiSummary": { "title": "AI abstract summary (paid add-on)", "type": "boolean", "description": "Off by default. When on, generates a 1-2 sentence plain-English summary from each paper's abstract (skipped when no abstract). Requires a paid Apify plan. Billed only when a summary is produced.", "default": false }, "withAiKeywords": { "title": "AI keywords (paid add-on)", "type": "boolean", "description": "Off by default. When on, extracts 5-10 topical keywords for each paper from its title/abstract/categories. Requires a paid Apify plan. Billed only when keywords are produced.", "default": false }, "withAiField": { "title": "AI field classification (paid add-on)", "type": "boolean", "description": "Off by default. When on, classifies each paper's academic field/discipline. Requires a paid Apify plan. Billed only when a classification is produced.", "default": false } } }, "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 } } } } } } } } } }