{ "openapi": "3.0.1", "info": { "title": "medRxiv Scraper", "description": "Extract comprehensive preprint data from medRxiv, including titles, authors, abstracts, full text, DOIs, citations, and metadata. Automate access to health-science preprints with structured outputs, ideal for researchers and analysts who need reliable, large-scale article data without manual work.", "version": "1.1", "x-build-id": "jdmpBGWGx2njPM55K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~medrxiv-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-medrxiv-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~medrxiv-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-medrxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~medrxiv-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-medrxiv-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrl": { "title": "Start URL", "type": "string", "description": "medRxiv.org search URL to start scraping from. Use this for custom searches or specific URLs. Cannot be used together with searchQuery. Example: https://www.medrxiv.org/search/asd or https://www.medrxiv.org/search/asd?page=1" }, "maxItems": { "title": "Max Items", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Free users: Limited to 10 items (preview). Paid users: Optional, max 1,000,000" }, "searchQuery": { "title": "Search Query", "type": "string", "description": "Search term to query medRxiv articles. Cannot be used together with startUrl. The scraper will search for articles matching this query." }, "subjectCollection": { "title": "Subject Collection", "enum": [ "", "addiction-medicine", "allergy-and-immunology", "anesthesia", "cardiovascular-medicine", "dentistry-and-oral-medicine", "dermatology", "emergency-medicine", "endocrinology", "epidemiology", "forensic-medicine", "gastroenterology", "genetic-and-genomic-medicine", "geriatric-medicine", "health-economics", "health-informatics", "health-policy", "health-systems-and-quality-improvement", "hematology", "hiv-aids", "infectious-diseases", "intensive-care-and-critical-care-medicine", "medical-education", "medical-ethics", "nephrology", "neurology", "nursing", "nutrition", "obstetrics-and-gynecology", "occupational-and-environmental-health", "oncology", "ophthalmology", "orthopedics", "otolaryngology", "pain-medicine", "palliative-medicine", "pathology", "pediatrics", "pharmacology-and-therapeutics", "primary-care-research", "psychiatry-and-clinical-psychology", "public-and-global-health", "radiology-and-imaging", "rehabilitation-medicine-and-physical-therapy", "respiratory-medicine", "rheumatology", "sexual-and-reproductive-health", "sports-medicine", "surgery", "toxicology", "transplantation", "urology" ], "type": "string", "description": "Restrict results to articles posted in a specific medRxiv subject collection. Maps to the source's subject_collection_code filter." }, "dateFrom": { "title": "Posted From", "type": "string", "description": "Lower bound for the posting date, in YYYY-MM-DD format. Maps to the source's limit_from filter." }, "dateTo": { "title": "Posted To", "type": "string", "description": "Upper bound for the posting date, in YYYY-MM-DD format. Maps to the source's limit_to filter." }, "author": { "title": "Author", "type": "string", "description": "Restrict results to articles where this name appears in the author list. Maps to the source's author1 filter." }, "orderBy": { "title": "Sort Order", "enum": [ "relevance", "oldest", "newest" ], "type": "string", "description": "How to sort the search results. 'relevance' = Best match, 'oldest' = Oldest First, 'newest' = Newest First" } } }, "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 } } } } } } } } } }