{ "openapi": "3.0.1", "info": { "title": "Research Paper Scraper — Papers, Abstracts & Citations", "description": "Scrape academic papers from OpenAlex: title, full reconstructed abstract, authors, institutions, journal, publisher, DOI, publication date, citation count, field-weighted impact, topics, open-access status and PDF links. Filter by keyword, year, DOI, citations, country or type. No API key.", "version": "0.1", "x-build-id": "ybOP7C8wIwNVuXEYj" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hichemdev~openalex-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hichemdev-openalex-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hichemdev~openalex-scraper/runs": { "post": { "operationId": "runs-sync-hichemdev-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hichemdev~openalex-scraper/run-sync": { "post": { "operationId": "run-sync-hichemdev-openalex-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchTerm": { "title": "Search term", "type": "string", "description": "Words to search titles, abstracts and full text for, e.g. CRISPR gene editing, large language models, microplastics." }, "doi": { "title": "DOI", "type": "string", "description": "Fetch one exact paper by DOI, e.g. 10.1038/s41586-021-03819-2." }, "publicationYear": { "title": "Publication year", "type": "string", "description": "Exact year, e.g. 2024. Use the date range below for anything finer." }, "fromPublicationDate": { "title": "Published on or after", "type": "string", "description": "YYYY-MM-DD." }, "toPublicationDate": { "title": "Published on or before", "type": "string", "description": "YYYY-MM-DD." }, "minCitations": { "title": "Min citations", "minimum": 0, "type": "integer", "description": "Keep only papers cited at least this many times." }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Keep only papers with a free full text available.", "default": false }, "workType": { "title": "Work type", "enum": [ "", "article", "review", "book", "book-chapter", "preprint", "dissertation", "dataset", "report" ], "type": "string", "description": "Restrict to one publication type.", "default": "" }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code, e.g. en, de, zh." }, "institutionCountry": { "title": "Institution country", "type": "string", "description": "Two-letter country code of an author institution, e.g. us, gb, cn." }, "sortBy": { "title": "Sort by", "enum": [ "relevance_score:desc", "cited_by_count:desc", "publication_date:desc", "publication_date:asc" ], "type": "string", "description": "Result order. Relevance needs a search term; without one the actor sorts by citations.", "default": "relevance_score:desc" }, "contactEmail": { "title": "Contact e-mail (optional)", "type": "string", "description": "OpenAlex gives faster, more reliable service to requests that identify a contact address. Supplying your own e-mail puts your runs in their polite pool." }, "maxWorks": { "title": "Max papers", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Stop after this many papers.", "default": 100 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Optional. A proxy is not required for this actor.", "default": { "useApifyProxy": false } } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }