{
"openapi": "3.0.1",
"info": {
"title": "bioRxiv Scraper ยท Preprints, Authors, Categories & Versions",
"description": "Scrape bioRxiv and medRxiv research preprints, authors, categories, versions, licensing, and abstracts via public REST API. Pay-per-event pricing per preprint record.",
"version": "1.0",
"x-build-id": "Dv5swfhia4hMt89ga"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/reapx~biorxiv-scraper/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-reapx-biorxiv-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/reapx~biorxiv-scraper/runs": {
"post": {
"operationId": "runs-sync-reapx-biorxiv-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/reapx~biorxiv-scraper/run-sync": {
"post": {
"operationId": "run-sync-reapx-biorxiv-scraper",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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",
"required": [
"maxPapers"
],
"properties": {
"server": {
"title": "Preprint Repository Server",
"enum": [
"biorxiv",
"medrxiv"
],
"type": "string",
"description": "Select the preprint repository server to query (biorxiv or medrxiv). Prefilled with biorxiv.
Choosing biorxiv extracts biological sciences research while medrxiv extracts medical and health sciences manuscripts. Leaving this unselected targets bioRxiv by default."
},
"fromDate": {
"title": "Start Date (YYYY-MM-DD)",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"type": "string",
"description": "Start date of the posting date window in YYYY-MM-DD format (e.g. 2024-01-01). Prefilled with 2024-01-01.
Leaving this field empty defaults to searching recent preprints without a lower bound. Setting a start date narrows the query timeline and reduces total execution cost."
},
"toDate": {
"title": "End Date (YYYY-MM-DD)",
"pattern": "^\\d{4}-\\d{2}-\\d{2}$",
"type": "string",
"description": "End date of the posting date window in YYYY-MM-DD format (e.g. 2024-01-05). Prefilled with 2024-01-05.
Leaving this field empty includes all papers posted up to today. Constraining the end date limits the result set and ensures faster actor execution times."
},
"category": {
"title": "Research Category Filter",
"type": "string",
"description": "Filter manuscripts by research subject category (e.g. neuroscience, genetics, bioinformatics, epidemiology, or infectious diseases).
Leave empty to extract preprints across all subject areas. Specifying a category isolates relevant discipline papers and speeds up data delivery."
},
"term": {
"title": "Search Keyword Filter",
"type": "string",
"description": "Keyword or phrase search filter to match against manuscript titles and abstract text (e.g. CRISPR, machine learning, or mRNA vaccine).
Leave empty to return all preprints in the date window. Adding search terms filters out irrelevant manuscripts and saves event charges."
},
"author": {
"title": "Author Name Filter",
"type": "string",
"description": "Author name filter string to match against primary or co-authors listed on preprints (e.g. Sinha or Holt).
Leave this field empty to include papers from all research groups. Filtering by author isolates publications from specific laboratory investigators."
},
"maxPapers": {
"title": "Maximum Papers to Extract",
"minimum": 1,
"maximum": 10000,
"type": "integer",
"description": "Maximum number of preprint records to extract and save into the default dataset (1 to 10000). Prefilled with 50.
Higher limits result in longer execution times and higher total event charges. Setting a smaller limit caps the run cost.
The higher the number, the longer the run takes and the more you are charged, because you pay per row returned.",
"default": 50
}
}
},
"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
}
}
}
}
}
}
}
}
}
}