{ "openapi": "3.0.1", "info": { "title": "bioRxiv & medRxiv Preprints Scraper (Biology, Health)", "description": "Scrape bioRxiv and medRxiv preprints by date, category or keyword: title, authors, corresponding institution, abstract, DOI, license, published-journal status and AI summary. Export to JSON, CSV or Excel.", "version": "0.1", "x-build-id": "WStNUDY767q75e4qM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapers_lat~biorxiv-medrxiv-preprints-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapers_lat-biorxiv-medrxiv-preprints-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapers_lat~biorxiv-medrxiv-preprints-scraper/runs": { "post": { "operationId": "runs-sync-scrapers_lat-biorxiv-medrxiv-preprints-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapers_lat~biorxiv-medrxiv-preprints-scraper/run-sync": { "post": { "operationId": "run-sync-scrapers_lat-biorxiv-medrxiv-preprints-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "server": { "title": "Preprint Server", "enum": [ "biorxiv", "medrxiv", "both" ], "type": "string", "description": "Which preprint server to scrape: bioRxiv (biology), medRxiv (health sciences), or both.", "default": "biorxiv" }, "dateFrom": { "title": "Posted From Date", "type": "string", "description": "Start of the posted-date range (inclusive), format YYYY-MM-DD. Ignored when a DOI is supplied." }, "dateTo": { "title": "Posted To Date", "type": "string", "description": "End of the posted-date range (inclusive), format YYYY-MM-DD. Ignored when a DOI is supplied." }, "category": { "title": "Category Filter", "type": "string", "description": "Optional. Keep only preprints whose subject category contains this text, for example \"neuroscience\", \"genomics\", \"infectious diseases\". Case-insensitive substring match." }, "searchTerm": { "title": "Keyword Filter", "type": "string", "description": "Optional. Keep only preprints whose title or abstract contains this text. Case-insensitive substring match." }, "doi": { "title": "Single DOI", "type": "string", "description": "Optional. Look up one preprint by its DOI, for example \"10.1101/2024.12.31.630767\". When set, the date range and filters are ignored and one record (latest version) is returned." }, "withPublishedStatus": { "title": "Resolve Published-Journal Status (add-on)", "type": "boolean", "description": "Also resolve whether and where each preprint was later published in a peer-reviewed journal (journal name, published DOI, published date). Opt-in add-on, billed per preprint only when a real published mapping is found. Available to paid Apify plans.", "default": false }, "withAiSummary": { "title": "AI Plain-Language Paper Summary (add-on)", "type": "boolean", "description": "Add an AI-written plain-language read of each preprint (plain summary, why it matters, field, methods) generated from the title and abstract. Opt-in add-on, billed per preprint only when a usable summary is produced. Available to paid Apify plans.", "default": false }, "maxResults": { "title": "Max Preprints To Return", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of preprints to return in one run. Free Apify plans are capped at 10." } } }, "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 } } } } } } } } } }