{ "openapi": "3.0.1", "info": { "title": "arXiv Paper Scraper — Citations, Authors, ORCID, Analytics", "description": "Scrape academic papers from arXiv via the official Atom API. Filter by category, date, query, or author. Includes citation data, ORCID IDs from Semantic Scholar, citation network graph, and built-in analytics (authors, categories, timeline). Four output formats. Proxies included.", "version": "1.1", "x-build-id": "rWN2p7WuGyyFpWgJ6" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/brilliant_gum~arxiv-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-brilliant_gum-arxiv-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/brilliant_gum~arxiv-scraper/runs": { "post": { "operationId": "runs-sync-brilliant_gum-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/brilliant_gum~arxiv-scraper/run-sync": { "post": { "operationId": "run-sync-brilliant_gum-arxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 Queries", "type": "array", "description": "List of search query strings. Multiple queries are batched and deduplicated. Multi-word queries (e.g. 'attention mechanism transformer') search for papers containing ALL words. Example: [\"attention mechanism transformer\", \"large language models reasoning\"]", "items": { "type": "string" }, "default": [] }, "searchField": { "title": "Search Field", "enum": [ "all", "title", "abstract", "author", "category" ], "type": "string", "description": "Which field the query text searches against. 'all' searches title, abstract, author, and comments.", "default": "all" }, "categories": { "title": "arXiv Categories", "type": "array", "description": "Restrict results to these arXiv subject categories. Leave empty to search all categories. Multiple categories are OR-combined. Examples: cs.AI, cs.LG, cs.CL, cs.CV, cs.NE, stat.ML, math.ST, q-bio.NC, physics.data-an, econ.EM", "items": { "type": "string" }, "default": [] }, "dateFrom": { "title": "Date From (Submitted)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Filter papers submitted on or after this date (based on arXiv v1 submission date). Format: YYYY-MM-DD" }, "dateTo": { "title": "Date To (Submitted)", "pattern": "^\\d{4}-\\d{2}-\\d{2}$", "type": "string", "description": "Filter papers submitted on or before this date (based on arXiv v1 submission date). Format: YYYY-MM-DD" }, "maxResults": { "title": "Max Results (per query)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of results to fetch per query. The actor auto-paginates in batches of 200. Hard cap: 10,000 per query (arXiv API limit). Note: very large result sets (>1,000) will be slow due to arXiv's 3.5-second rate-limit delay between pages.", "default": 100 }, "sortBy": { "title": "Sort By", "enum": [ "submittedDate", "relevance", "lastUpdatedDate" ], "type": "string", "description": "Field used to sort results returned by the arXiv API.", "default": "submittedDate" }, "sortOrder": { "title": "Sort Order", "enum": [ "descending", "ascending" ], "type": "string", "description": "Sort order for results. Descending returns newest/most-relevant results first.", "default": "descending" }, "includeAbstract": { "title": "Include Abstract", "type": "boolean", "description": "Include the full paper abstract in the output. Disable to reduce dataset size when abstracts are not needed.", "default": true }, "includeCitations": { "title": "Include Citation Data (Semantic Scholar)", "type": "boolean", "description": "Fetch citation count, influential citation count, author ORCID IDs, and top related papers from the Semantic Scholar API. Adds ~1-2 seconds per paper due to rate limiting. A CITATION_GRAPH is also saved to the Key-Value store.", "default": false }, "semanticScholarApiKey": { "title": "Semantic Scholar API Key (optional)", "type": "string", "description": "Optional API key for the Semantic Scholar Academic Graph API. Without a key the free tier allows ~1 request/second. With an API key the rate limit is significantly higher, making citation enrichment much faster for large result sets. Get a free key at: https://www.semanticscholar.org/product/api" }, "outputFormat": { "title": "Output Format", "enum": [ "papers", "authors", "categories_stats", "timeline" ], "type": "string", "description": "Controls what is pushed to the dataset. 'papers': one record per paper (default). 'authors': aggregated author analytics sorted by paper count. 'categories_stats': paper counts and top papers per arXiv category. 'timeline': publication counts by month and year.", "default": "papers" }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional. Proxies are included and configured automatically — leave this empty unless you want to override with your own." } } }, "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 } } } } } } } } } }