{ "openapi": "3.0.1", "info": { "title": "arXiv Research Papers Scraper — AI/ML Preprints, Abstracts &", "description": "Scrape arXiv preprints, machine learning papers, authors, abstracts, PDF download links, categories (cs.AI, cs.LG, cs.CV), and publication dates via the official API.", "version": "0.1", "x-build-id": "Tb23RBIU1evHSeGsF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/spotless_studios~arxiv-papers-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-spotless_studios-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/spotless_studios~arxiv-papers-scraper/runs": { "post": { "operationId": "runs-sync-spotless_studios-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/spotless_studios~arxiv-papers-scraper/run-sync": { "post": { "operationId": "run-sync-spotless_studios-arxiv-papers-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchQuery": { "title": "Search query / keywords", "type": "string", "description": "Search query across title, abstract, and authors (e.g. 'reasoning agents', 'multimodal transformer', 'quantum error correction').", "default": "reasoning agents" }, "searchQueries": { "title": "Multiple search queries", "type": "array", "description": "Optional list of multiple search queries to run sequentially in a single job.", "items": { "type": "string" } }, "titleQuery": { "title": "Title-specific query", "type": "string", "description": "Require these keywords in the paper title (ti: qualifier)." }, "abstractQuery": { "title": "Abstract-specific query", "type": "string", "description": "Require these keywords in the paper abstract (abs: qualifier)." }, "category": { "title": "arXiv category code", "type": "string", "description": "Filter by primary arXiv subject taxonomy (e.g. 'cs.AI', 'cs.LG', 'cs.CL', 'cs.CV', 'cs.RO', 'stat.ML', 'quant-ph')." }, "categories": { "title": "Multiple arXiv categories", "type": "array", "description": "Filter across multiple arXiv categories (e.g. ['cs.AI', 'cs.CL', 'cs.LG']).", "items": { "type": "string" } }, "author": { "title": "Author name", "type": "string", "description": "Filter preprints by author name (e.g. 'Yann LeCun', 'Ilya Sutskever')." }, "sortBy": { "title": "Sort by", "enum": [ "submittedDate", "lastUpdatedDate", "relevance" ], "type": "string", "description": "Sort order for arXiv preprints.", "default": "submittedDate" }, "sortOrder": { "title": "Sort order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Descending (newest first) or ascending.", "default": "descending" }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Only return papers published after this date (YYYY-MM-DD, ISO, or relative like '14 days' / '3 months')." }, "publishedBefore": { "title": "Published before", "type": "string", "description": "Only return papers published before this date." }, "requireCodeUrl": { "title": "Only papers with GitHub / HuggingFace code links", "type": "boolean", "description": "When enabled, only saves papers that include a GitHub, GitLab, or HuggingFace repository link in their abstract or author comments.", "default": false }, "requireDoi": { "title": "Only papers with a published DOI", "type": "boolean", "description": "When enabled, only saves preprints that have a journal DOI assigned.", "default": false }, "arxivIds": { "title": "Direct arXiv IDs or URLs", "type": "array", "description": "Scrape specific papers directly by arXiv ID or URL (e.g. '2303.08774', 'https://arxiv.org/abs/1706.03762').", "items": { "type": "string" } }, "includeKeywords": { "title": "Include keywords", "type": "array", "description": "Keep only papers matching these keywords or /regex/ in title, abstract, authors, or comments.", "items": { "type": "string" } }, "excludeKeywords": { "title": "Exclude keywords", "type": "array", "description": "Skip papers matching any of these keywords or /regex/.", "items": { "type": "string" } }, "keywordMatch": { "title": "Include keyword logic", "enum": [ "any", "all" ], "type": "string", "description": "Require any or all includeKeywords to match.", "default": "any" }, "onlyNewItems": { "title": "Only new preprints (monitoring mode)", "type": "boolean", "description": "Remember seen arXiv IDs across runs and emit only newly published preprints.", "default": false }, "stateKey": { "title": "Monitor state name", "type": "string", "description": "Separate state key per saved search or schedule.", "default": "default" }, "maxResults": { "title": "Max results", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of papers to save.", "default": 100 }, "outputPreset": { "title": "Data preset", "enum": [ "full", "lean", "contacts" ], "type": "string", "description": "Choose full record, lean summary, or contacts & links only.", "default": "full" }, "outputFields": { "title": "Output fields", "type": "array", "description": "Keep only these specific fields in each saved record.", "items": { "type": "string" } }, "excludeFields": { "title": "Exclude fields", "type": "array", "description": "Remove specific fields from each saved record.", "items": { "type": "string" } }, "includeEmptyFields": { "title": "Keep empty / null fields", "type": "boolean", "description": "When disabled, strips null and empty values from each saved record.", "default": true }, "requiredFields": { "title": "Required non-empty fields", "type": "array", "description": "Only save records where every listed field has a non-empty value (e.g. codeUrls, doi).", "items": { "type": "string" } }, "maxPages": { "title": "Max search pages", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum search pages per query (100 papers per page).", "default": 15 }, "maxRequestRetries": { "title": "Max retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries per failed HTTP request.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout per HTTP request.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional proxy settings.", "default": { "useApifyProxy": false } }, "proxyEscalation": { "title": "Auto-escalate proxies when blocked", "type": "boolean", "description": "Automatically step up from direct to Apify datacenter/residential proxies if blocked.", "default": true } } }, "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 } } } } } } } } } }