{ "openapi": "3.0.1", "info": { "title": "Research Papers Scraper - OpenAlex 250M+ Works, $0.50/1K", "description": "Search 250M+ research papers from the open OpenAlex catalog: titles, DOIs, abstracts, authors with ORCIDs and institutions, citations, topics and open-access PDF links. Author, institution and citation lookups. $0.50 per 1,000 records.", "version": "0.1", "x-build-id": "XX4bYJcdgrLQglJce" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/plotpointtech~research-papers-scraper-openalex/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-plotpointtech-research-papers-scraper-openalex", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/plotpointtech~research-papers-scraper-openalex/runs": { "post": { "operationId": "runs-sync-plotpointtech-research-papers-scraper-openalex", "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/plotpointtech~research-papers-scraper-openalex/run-sync": { "post": { "operationId": "run-sync-plotpointtech-research-papers-scraper-openalex", "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": { "mode": { "title": "What to get", "enum": [ "searchWorks", "getWorks", "authors", "institutions", "citations" ], "type": "string", "description": "Search works by keyword and filters, fetch specific works by DOI/ID, look up authors or institutions with their works, or expand the citation network of seed papers.", "default": "searchWorks" }, "query": { "title": "Search query", "type": "string", "description": "Keywords to search for (search papers mode). Supports AND, OR, NOT and \"exact phrases\".", "default": "large language models" }, "searchIn": { "title": "Search in", "enum": [ "titleAbstract", "title", "fulltext" ], "type": "string", "description": "Where to match the query: title and abstract (default, precise), title only, or full text (title, abstract and indexed full text; widest).", "default": "titleAbstract" }, "workIds": { "title": "Work IDs (DOIs, OpenAlex IDs, PMIDs)", "type": "array", "description": "For 'Get papers' and 'Citations' modes: DOIs (10.1038/nature14539 or https://doi.org/...), OpenAlex work IDs (W2741809807 or URL) or PubMed IDs.", "items": { "type": "string" } }, "citationDirection": { "title": "Citation direction", "enum": [ "citedBy", "references", "both" ], "type": "string", "description": "Citations mode: papers that cite each seed (cited by), papers each seed cites (references), or both.", "default": "citedBy" }, "includeSeedWorks": { "title": "Include the seed papers", "type": "boolean", "description": "Citations mode: also output each seed paper itself.", "default": true }, "authors": { "title": "Authors", "type": "array", "description": "Authors mode: names (e.g. Jennifer Doudna), ORCIDs (0000-0001-9161-999X) or OpenAlex author IDs (A5067184382).", "items": { "type": "string" } }, "matchesPerName": { "title": "Author matches per name", "minimum": 1, "maximum": 25, "type": "integer", "description": "Authors mode: how many matching author profiles to return for a name search (names can be ambiguous; ORCIDs are exact).", "default": 1 }, "institutions": { "title": "Institutions", "type": "array", "description": "Institutions mode: names (e.g. MIT), ROR IDs (https://ror.org/042nb2s44) or OpenAlex institution IDs (I63966007).", "items": { "type": "string" } }, "includeWorks": { "title": "Include their papers", "type": "boolean", "description": "Authors / institutions mode: also output their papers (filters and sort below apply).", "default": true }, "maxWorksPerSeed": { "title": "Max papers per author / institution / seed", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Upper limit of papers per author, institution or seed paper (the overall maximum still applies).", "default": 100 }, "yearFrom": { "title": "Published from year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Only papers published in or after this year." }, "yearTo": { "title": "Published to year", "minimum": 1000, "maximum": 2100, "type": "integer", "description": "Only papers published in or before this year." }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Only papers that are free to read somewhere (gold, green, hybrid, bronze or diamond).", "default": false }, "hasAbstract": { "title": "Only papers with an abstract", "type": "boolean", "description": "Skip records without an abstract in OpenAlex.", "default": false }, "workTypes": { "title": "Work types", "type": "array", "description": "Only these types. Leave empty for all.", "items": { "type": "string", "enum": [ "article", "review", "preprint", "book", "book-chapter", "dataset", "dissertation", "report", "editorial", "letter", "paratext", "other" ], "enumTitles": [ "Article", "Review", "Preprint", "Book", "Book chapter", "Dataset", "Dissertation", "Report", "Editorial", "Letter", "Paratext", "Other" ] } }, "topics": { "title": "Topics", "type": "array", "description": "Only papers in these OpenAlex topics. Enter topic names (matched to the closest OpenAlex topic, shown in the log) or topic IDs like T10181.", "items": { "type": "string" } }, "minCitations": { "title": "Minimum citations", "minimum": 0, "type": "integer", "description": "Only papers cited at least this many times." }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code, e.g. en, de, es, zh. Leave empty for all." }, "excludeRetracted": { "title": "Exclude retracted papers", "type": "boolean", "description": "Skip papers flagged as retracted.", "default": true }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "citations", "newest", "oldest" ], "type": "string", "description": "Relevance (searches only; otherwise falls back to most cited), most cited, newest or oldest.", "default": "relevance" }, "maxResults": { "title": "Maximum results", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many records in total (papers plus author / institution profiles).", "default": 50 }, "includeReferencedWorkIds": { "title": "Include referenced work IDs", "type": "boolean", "description": "Add the list of OpenAlex IDs each paper cites (referencedWorks).", "default": false }, "apiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Your free OpenAlex API key (https://openalex.org/settings/api). Recommended for large jobs: it gives you your own daily OpenAlex budget and unlocks results beyond the first 10,000 per query. Without it, the tool uses OpenAlex's shared free budget." } } }, "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 } } } } } } } } } }