{ "openapi": "3.0.1", "info": { "title": "Research Paper Scraper", "description": "Gather information such as paper titles, authors, abstracts, categories, PDF links, DOIs, and additional relevant details. This process does not require an API key for access.", "version": "0.0", "x-build-id": "A4QyhRpg0ePTmOnQX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/moving_beacon-owner1~my-actor-77/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-moving_beacon-owner1-my-actor-77", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/moving_beacon-owner1~my-actor-77/runs": { "post": { "operationId": "runs-sync-moving_beacon-owner1-my-actor-77", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/moving_beacon-owner1~my-actor-77/run-sync": { "post": { "operationId": "run-sync-moving_beacon-owner1-my-actor-77", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "scrape_mode", "max_results" ], "properties": { "scrape_mode": { "title": "Scrape Mode", "enum": [ "keyword_search", "author_search", "category_browse", "id_lookup" ], "type": "string", "description": "How to search arXiv.", "default": "keyword_search" }, "search_query": { "title": "Search Query", "type": "string", "description": "Keywords to search for (used in 'Keyword Search' mode). Supports arXiv query syntax: 'ti:deep learning', 'abs:transformer', 'all:reinforcement learning'. Plain text also works.", "default": "machine learning" }, "search_field": { "title": "Search Field", "enum": [ "all", "ti", "abs", "au", "co", "jr", "cat" ], "type": "string", "description": "Which field to search in (used in 'Keyword Search' mode).", "default": "all" }, "author_name": { "title": "Author Name", "type": "string", "description": "Author name to search for (used in 'Author Search' mode). Example: 'Yoshua Bengio'.", "default": "" }, "category": { "title": "arXiv Category", "type": "string", "description": "arXiv category to browse (used in all modes as a filter). Examples: cs.AI, cs.LG, cs.CL, stat.ML, math.CO, physics, quant-ph, econ, q-bio.", "default": "" }, "date_from": { "title": "Date From", "type": "string", "description": "Only include papers submitted on or after this date (YYYY-MM-DD). Leave empty for no lower bound.", "default": "" }, "date_to": { "title": "Date To", "type": "string", "description": "Only include papers submitted on or before this date (YYYY-MM-DD). Leave empty for no upper bound.", "default": "" }, "paper_ids": { "title": "Paper IDs", "type": "string", "description": "Comma-separated arXiv paper IDs to look up (used in 'ID Lookup' mode). Example: '2301.07041,1706.03762,2005.14165'.", "default": "" }, "max_results": { "title": "Max Results", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Maximum number of papers to scrape (1–2000). arXiv API limit is 2000 per query.", "default": 50 }, "sort_by": { "title": "Sort By", "enum": [ "relevance", "submitted_date", "last_updated" ], "type": "string", "description": "How to sort the results.", "default": "relevance" }, "include_abstract": { "title": "Include Abstract", "type": "boolean", "description": "Include the full abstract text in results.", "default": true }, "include_pdf_links": { "title": "Include PDF Links", "type": "boolean", "description": "Include direct PDF download URLs.", "default": true }, "abstract_contains": { "title": "Abstract Must Contain", "type": "string", "description": "Optional: only include papers whose abstract contains ALL of these comma-separated keywords. Example: 'transformer,attention'.", "default": "" }, "exclude_keywords": { "title": "Exclude Keywords", "type": "string", "description": "Optional: exclude papers whose title or abstract contains ANY of these comma-separated keywords.", "default": "" }, "min_authors": { "title": "Min Authors", "minimum": 0, "type": "integer", "description": "Minimum number of authors a paper must have (0 = no filter).", "default": 0 }, "proxy_configuration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy configuration (rarely needed — arXiv API is open)." } } }, "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 } } } } } } } } } }