{ "openapi": "3.0.1", "info": { "title": "arXiv Papers Scraper: Search Papers, Abstracts & Authors", "description": "Run one or many arXiv searches by keywords, category, author, date range or ID and get titles, abstracts, authors, categories, dates, DOIs and PDF links from the official arXiv API. No login or proxy setup. $0.90 per 1,000 papers.", "version": "0.2", "x-build-id": "Hvld16KQ0dqc0e0Lh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidyharvest~arxiv-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidyharvest-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidyharvest~arxiv-papers-scraper/runs": { "post": { "operationId": "runs-sync-tidyharvest-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/tidyharvest~arxiv-papers-scraper/run-sync": { "post": { "operationId": "run-sync-tidyharvest-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": { "queries": { "title": "Search terms (one search per line)", "type": "array", "description": "Free-text searches across title, abstract, authors and comments; each line runs its own search with the filters below. Every word must match; put \"exact phrases\" in double quotes. Each paper says which search found it, and a paper found twice is returned once. Leave empty to list the latest papers in the chosen categories.", "items": { "type": "string" } }, "query": { "title": "Search terms (single search)", "type": "string", "description": "Same as one line in the list above; kept for existing integrations. Every word must match; put \"exact phrases\" in double quotes. Leave empty to list the latest papers in the chosen categories." }, "maxItemsPerQuery": { "title": "Max papers per search", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Cap for each line when you give several searches. Empty = no per-search cap (only Max papers applies)." }, "categories": { "title": "Categories", "type": "array", "description": "arXiv category codes, matched with OR (e.g. `cs.AI`, `cs.LG`, `cs.CL`, `stat.ML`, `q-bio.GN`, `astro-ph`). Full list: arxiv.org/category_taxonomy. With no input at all the run returns the latest `cs.AI` papers.", "items": { "type": "string" } }, "authors": { "title": "Authors", "type": "array", "description": "Author names, matched with OR (e.g. `Yann LeCun` or a surname like `Bengio`).", "items": { "type": "string" } }, "dateFrom": { "title": "Submitted from", "type": "string", "description": "Only papers first submitted on or after this date (YYYY-MM-DD)." }, "dateTo": { "title": "Submitted until", "type": "string", "description": "Only papers first submitted on or before this date (YYYY-MM-DD)." }, "ids": { "title": "arXiv IDs or links", "type": "array", "description": "Look up specific papers by ID (`1706.03762`, `2005.14165v4`, `hep-th/9901001`) or abs/pdf link. Combined with other fields, only these papers are searched.", "items": { "type": "string" } }, "searchQuery": { "title": "Advanced query (arXiv syntax)", "type": "string", "description": "Raw arXiv API query, ANDed with the fields above. Prefixes: `ti:` title, `abs:` abstract, `au:` author, `cat:` category, `co:` comment, `jr:` journal ref; operators AND, OR, ANDNOT. Example: `ti:transformer ANDNOT cat:cs.CV`." }, "sortBy": { "title": "Sort by", "enum": [ "auto", "relevance", "submittedDate", "lastUpdatedDate" ], "type": "string", "description": "Auto = relevance when you give search terms, otherwise newest submissions first.", "default": "auto" }, "sortOrder": { "title": "Sort order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Descending = newest (or most relevant) first.", "default": "descending" }, "maxItems": { "title": "Max papers", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum papers to return for the whole run (also caps your cost). arXiv allows about 100 papers every 3 seconds, so 1,000 papers take about 35 seconds.", "default": 50 } } }, "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 } } } } } } } } } }