{ "openapi": "3.0.1", "info": { "title": "Academic Paper Search: Crossref, arXiv & PubMed Scraper", "description": "Search research papers across Crossref, arXiv and PubMed (plus OpenAlex) in one run. Titles, authors, abstracts, DOIs, citation counts, journals and PDF links, merged and de-duplicated. For literature reviews, RAG and research.", "version": "0.0", "x-build-id": "KdAUn3g09YYSY8oSe" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/pankajbhatia~academic-paper-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-pankajbhatia-academic-paper-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/pankajbhatia~academic-paper-search/runs": { "post": { "operationId": "runs-sync-pankajbhatia-academic-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/pankajbhatia~academic-paper-search/run-sync": { "post": { "operationId": "run-sync-pankajbhatia-academic-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "query" ], "properties": { "query": { "title": "Search query", "type": "string", "description": "Topic, keywords or a paper title, e.g. 'large language models' or 'crispr gene therapy'. For arXiv you can also use fields like ti:, au:, cat:." }, "sources": { "title": "Sources", "type": "array", "description": "Which scholarly databases to search. Crossref covers most journals and DOIs, arXiv covers preprints (CS, physics, math...), PubMed covers biomedicine. OpenAlex needs your free API key.", "items": { "type": "string", "enum": [ "crossref", "arxiv", "pubmed", "openalex" ], "enumTitles": [ "Crossref (all journals, DOIs, citations)", "arXiv (preprints)", "PubMed (biomedical)", "OpenAlex (needs free API key)" ] }, "default": [ "crossref", "arxiv", "pubmed" ] }, "maxResultsPerSource": { "title": "Max results per source", "minimum": 1, "maximum": 2000, "type": "integer", "description": "How many papers to take from each source.", "default": 50 }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "date", "citations" ], "type": "string", "description": "Most relevant, newest, or most cited first (citation counts come from Crossref and OpenAlex).", "default": "relevance" }, "fromYear": { "title": "From year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Only papers published in or after this year." }, "toYear": { "title": "To year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Only papers published in or before this year." }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Only free-to-read papers (where the source reports it).", "default": false }, "onlyWithAbstract": { "title": "Only papers with an abstract", "type": "boolean", "description": "Skip papers whose abstract isn't available.", "default": false }, "removeDuplicates": { "title": "Merge duplicates across sources", "type": "boolean", "description": "The same paper found in several sources (same DOI or title) is returned once, with the best fields merged.", "default": true }, "openAlexApiKey": { "title": "OpenAlex API key (optional)", "type": "string", "description": "Free key from openalex.org. Only needed if you select OpenAlex as a source." }, "contactEmail": { "title": "Contact email for Crossref (optional)", "type": "string", "description": "Crossref gives faster, more reliable service to requests that include a contact email (their 'polite pool'). Not stored or used for anything else." } } }, "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 } } } } } } } } } }