{ "openapi": "3.0.1", "info": { "title": "Academic Paper Scraper: arXiv, PubMed, Crossref & OpenAlex API", "description": "Search & scrape academic papers from arXiv, PubMed, Crossref & OpenAlex in one run, de-duplicated by DOI. Titles, authors, abstracts, citations and open-access PDF links. A Google Scholar alternative via official APIs. $2 per 1,000 papers.", "version": "0.1", "x-build-id": "Y7z5Y9s7HPeMf6DHh" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/infocomp~scholarly-paper-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-infocomp-scholarly-paper-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/infocomp~scholarly-paper-search/runs": { "post": { "operationId": "runs-sync-infocomp-scholarly-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/infocomp~scholarly-paper-search/run-sync": { "post": { "operationId": "run-sync-infocomp-scholarly-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": [ "queries" ], "properties": { "queries": { "title": "Search queries", "type": "array", "description": "One search per line, e.g. CRISPR base editing, \"large language models\" evaluation. Use quotes for exact phrases (arXiv and PubMed honor them).", "items": { "type": "string" } }, "sources": { "title": "Sources", "type": "array", "description": "Crossref (journals and books, 180M+ DOIs), arXiv (preprints), PubMed (biomedical, with MeSH). OpenAlex (250M+ works with citation counts) is added automatically when you enter your free OpenAlex key below.", "items": { "type": "string", "enum": [ "crossref", "arxiv", "pubmed", "openalex" ], "enumTitles": [ "Crossref", "arXiv", "PubMed", "OpenAlex (best with your key)" ] }, "default": [ "crossref", "arxiv", "pubmed" ] }, "maxResultsPerSource": { "title": "Max results per source per query", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Each source returns its top results in its own ranking. Results are interleaved and duplicates merged.", "default": 50 }, "maxResults": { "title": "Max papers in total", "minimum": 1, "type": "integer", "description": "Stop after this many papers (your max cost per run also applies)." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "newest" ], "type": "string", "description": "Newest first is best for alerts.", "default": "relevance" }, "requireAllTerms": { "title": "Require every query word in title/abstract", "type": "boolean", "description": "Drops loose matches (Crossref and PubMed search engines can return papers that match only some words). Words are matched by stem, quoted phrases exactly.", "default": true }, "yearFrom": { "title": "Published from year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "e.g. 2022" }, "yearTo": { "title": "Published up to year", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "e.g. 2026" }, "openAccessOnly": { "title": "Open access only", "type": "boolean", "description": "Keep papers known to be free to read (all arXiv; PubMed with a PMC copy; OpenAlex is_oa).", "default": false }, "requireAbstract": { "title": "Only papers with an abstract", "type": "boolean", "description": "Crossref has abstracts only when the publisher deposits them.", "default": false }, "minCitations": { "title": "Minimum citations", "minimum": 0, "type": "integer", "description": "Uses Crossref/OpenAlex citation counts; papers without a count are dropped." }, "excludeKeywords": { "title": "Exclude titles containing", "type": "array", "description": "e.g. review, erratum, retracted.", "items": { "type": "string" } }, "includeAbstract": { "title": "Include abstracts", "type": "boolean", "description": "Abstracts can be copyrighted by their publishers; turn off if you only need metadata.", "default": true }, "onlyNewPapers": { "title": "Only papers not seen in previous runs", "type": "boolean", "description": "Remembers papers between runs (named key-value store in your account). Schedule with \"Newest first\" for a research alert.", "default": false }, "stateKey": { "title": "Alert name (state key)", "type": "string", "description": "Separate memory per saved search.", "default": "default" }, "openAlexApiKey": { "title": "Your OpenAlex API key (optional)", "type": "string", "description": "Free at openalex.org/settings/api ($1/day of free usage). Without it OpenAlex shares a small daily budget per IP and may be skipped." }, "pubmedApiKey": { "title": "Your NCBI API key (optional)", "type": "string", "description": "Raises the PubMed limit from 3 to 10 requests per second. Free from your NCBI account settings." }, "contactEmail": { "title": "Your email for the Crossref polite pool (optional)", "type": "string", "description": "Crossref gives faster limits (3 vs 1 list request per second) to requests that include a contact email. Only sent to Crossref." } } }, "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 } } } } } } } } } }