{ "openapi": "3.0.1", "info": { "title": "arXiv Papers Scraper - Search & Bulk by Category, Abstracts", "description": "arXiv scraper using the official API and OAI-PMH: search by keyword, author, title or category, or bulk-harvest whole categories by date. Abstracts, authors, categories, DOI, journal ref, PDF links. From US$1.00 per 1,000 papers.", "version": "0.1", "x-build-id": "FJ3I9NhaJEa4xw0lj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fabrikit~arxiv-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fabrikit-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/fabrikit~arxiv-papers-scraper/runs": { "post": { "operationId": "runs-sync-fabrikit-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/fabrikit~arxiv-papers-scraper/run-sync": { "post": { "operationId": "run-sync-fabrikit-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": { "mode": { "title": "Mode", "enum": [ "search", "harvest" ], "type": "string", "description": "Search = query the arXiv API (keywords, authors, titles, categories, dates, up to 30,000 results per query). Harvest = bulk-download every paper of one or more categories in a date range through OAI-PMH (best for large, regular exports).", "default": "search" }, "searchQueries": { "title": "Search queries (search mode)", "type": "array", "description": "One query per line. Plain words are matched in all fields (`graph neural networks`). Use arXiv syntax for precision: `ti:\"attention is all you need\"`, `au:hinton`, `abs:diffusion AND cat:cs.CV`, `all:LLM ANDNOT all:survey`. Each query runs separately.", "default": [], "items": { "type": "string" } }, "categories": { "title": "Categories", "type": "array", "description": "arXiv categories such as cs.AI, cs.LG, cs.CL, cs.CV, stat.ML, math.PR, hep-th, quant-ph, q-bio.NC, econ.EM. In search mode they restrict every query (OR between categories); in harvest mode each category is downloaded in turn.", "default": [ "cs.AI" ], "items": { "type": "string" } }, "ids": { "title": "arXiv IDs (search mode)", "type": "array", "description": "Fetch specific papers by ID, e.g. 1706.03762 or hep-th/9901001 (version suffix optional). Combined with the queries above.", "default": [], "items": { "type": "string" } }, "dateFrom": { "title": "From date (YYYY-MM-DD)", "type": "string", "description": "Search mode: first submission date. Harvest mode: start of the modification-date window (default: 3 days ago)." }, "dateTo": { "title": "To date (YYYY-MM-DD)", "type": "string", "description": "Inclusive end date. Default: today." }, "newSubmissionsOnly": { "title": "Harvest: only new papers", "type": "boolean", "description": "OAI-PMH reports every paper whose metadata changed in the window, including old papers that got a new version. When on (default), only papers first submitted inside the window are kept.", "default": true }, "sortBy": { "title": "Search: sort by", "enum": [ "submittedDate", "lastUpdatedDate", "relevance" ], "type": "string", "description": "Sort field for the search mode.", "default": "submittedDate" }, "sortOrder": { "title": "Search: sort order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Newest first (descending) or oldest first (ascending).", "default": "descending" }, "maxItemsPerQuery": { "title": "Max papers per query / category", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Cap for each search query or harvested category. Leave empty for no per-query cap." }, "maxItems": { "title": "Max papers in total", "minimum": 1, "maximum": 5000000, "type": "integer", "description": "Hard cap for the whole run. Each paper is billed once. Note arXiv asks for one request every 3 seconds, so 1,000 papers take about 15 seconds in search mode and bulk harvests are bounded by that pace.", "default": 50 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "arXiv is open, so no proxy is used by default. If arXiv rate-limits the Actor's IP (HTTP 429/403), it automatically switches to a residential proxy for the rest of the run.", "default": { "useApifyProxy": 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 }, "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 } } } } } } } } } }