{
"openapi": "3.0.1",
"info": {
"title": "arXiv Scraper - Papers, Authors, Abstracts & PDFs",
"description": "Scrape arXiv papers by search query or ID from the official API: title, abstract, authors, categories, publication date, DOI, journal reference and PDF link. No key, no browser, cents per paper. Independent tool, not affiliated with arXiv.",
"version": "0.1",
"x-build-id": "omlxzkN8erSTGBnLl"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/scrapesage~arxiv-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-scrapesage-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/scrapesage~arxiv-scraper/runs": {
"post": {
"operationId": "runs-sync-scrapesage-arxiv-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/scrapesage~arxiv-scraper/run-sync": {
"post": {
"operationId": "run-sync-scrapesage-arxiv-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"searchQueries": {
"title": "Search queries",
"type": "array",
"description": "What to search arXiv for, one per line - e.g. large language models, quantum error correction. Advanced field syntax works too (cat:cs.AI, au:hinton, ti:transformer). Leave empty and the run returns a small free sample.",
"items": {
"type": "string"
}
},
"arxivIds": {
"title": "arXiv IDs (optional)",
"type": "array",
"description": "Fetch specific papers by arXiv ID (e.g. 2312.00752 or cs/9901002). When set, papers are fetched by ID.",
"items": {
"type": "string"
}
},
"searchQueriesFromFile": {
"title": "Import search queries from a file",
"type": "string",
"description": "Bulk-load search queries. Either paste the whole list (one per line), or give a single link to a public .txt/.csv, a Google Sheet/Drive link, or an Apify key-value-store record. A file that cannot be read says so and charges nothing."
},
"sortBy": {
"title": "Sort by",
"enum": [
"relevance",
"submitted",
"updated"
],
"type": "string",
"description": "How to order search results.",
"default": "relevance"
},
"maxItemsPerQuery": {
"title": "Max papers per query",
"minimum": 1,
"type": "integer",
"description": "How many papers to collect for each search query.",
"default": 50
},
"maxItems": {
"title": "Max papers (total)",
"minimum": 1,
"type": "integer",
"description": "Overall cap across all queries. You are only charged for papers actually saved.",
"default": 1000
},
"outputFields": {
"title": "Output fields (leave empty for all)",
"type": "array",
"description": "Pick the fields you want and every record is trimmed to exactly those - handy for lean CSV/Sheets exports.",
"items": {
"type": "string",
"enum": [
"type",
"id",
"title",
"summary",
"authors",
"authorCount",
"published",
"updated",
"primaryCategory",
"categories",
"pdfUrl",
"arxivUrl",
"doi",
"journalRef",
"comment",
"scrapedAt"
],
"enumTitles": [
"Record type (type)",
"arXiv ID (id)",
"Title (title)",
"Abstract (summary)",
"Authors (authors)",
"Author count (authorCount)",
"Published (published)",
"Updated (updated)",
"Primary category (primaryCategory)",
"Categories (categories)",
"PDF URL (pdfUrl)",
"arXiv URL (arxivUrl)",
"DOI (doi)",
"Journal reference (journalRef)",
"Comment (comment)",
"Scraped at (scrapedAt)"
]
}
}
}
},
"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
}
}
}
}
}
}
}
}
}
}