{ "openapi": "3.0.1", "info": { "title": "Semantic Scholar Scraper", "description": "Scrapes academic papers from Semantic Scholar search results. Returns each paper as a flat row with title, authors, year, citations, venue, and abstract. Supports year and PDF filters.", "version": "1.0", "x-build-id": "16zib1xbySypngpZY" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/parseforge~semantic-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-parseforge-semantic-scholar-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/parseforge~semantic-scholar-scraper/runs": { "post": { "operationId": "runs-sync-parseforge-semantic-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/parseforge~semantic-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-parseforge-semantic-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "searchType": { "title": "What to search", "enum": [ "papers", "authors", "ids" ], "type": "string", "description": "Papers: keyword or title search (phrase match first, most-cited first). Authors: author name search, optionally with each author's papers. Paper IDs: look up specific papers by Semantic Scholar id, DOI, arXiv id, PubMed id or Corpus id." }, "query": { "title": "Search query", "type": "string", "description": "Paper title, keywords, or an author name. Examples: \"attention is all you need\", \"graph neural networks drug discovery\", \"Yoshua Bengio\"." }, "startUrl": { "title": "Semantic Scholar URL (optional)", "type": "string", "description": "Alternative to the query: a semanticscholar.org search URL (query, year range and PDF filter are read from it), a paper URL or an author URL." }, "ids": { "title": "Paper IDs (Paper IDs mode)", "uniqueItems": true, "type": "array", "description": "One id per line: a 40-character Semantic Scholar id, DOI:10.xxxx/…, ArXiv:1706.03762, PMID:…, PMCID:… or CorpusId:…. Plain DOIs and arXiv numbers are recognised without a prefix.", "items": { "type": "string" } }, "maxItems": { "title": "Maximum rows", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many rows (papers, or authors plus their papers). Free-plan runs return up to 10 rows as a preview; paid plans up to 1,000,000." }, "sort": { "title": "Sort order (Papers mode)", "enum": [ "relevance", "citations", "newest", "oldest" ], "type": "string", "description": "Relevance needs an API key (Semantic Scholar's relevance endpoint is closed to anonymous traffic); without one, relevance falls back to most-cited first, which surfaces the well-known paper for a title search.", "default": "relevance" }, "year": { "title": "Publication year", "type": "string", "description": "A single year (2019), a range (2016-2020), or an open-ended span (2020- or -2015)." }, "fieldsOfStudy": { "title": "Fields of study", "uniqueItems": true, "type": "array", "description": "Restrict to these fields. Valid values: Computer Science, Medicine, Chemistry, Biology, Materials Science, Physics, Geology, Psychology, Art, History, Geography, Sociology, Business, Political Science, Economics, Philosophy, Mathematics, Engineering, Environmental Science, Agricultural and Food Sciences, Education, Law, Linguistics.", "items": { "type": "string" } }, "publicationTypes": { "title": "Publication types", "uniqueItems": true, "type": "array", "description": "Restrict to these types: Review, JournalArticle, CaseReport, ClinicalTrial, Conference, Dataset, Editorial, LettersAndComments, MetaAnalysis, News, Study, Book, BookSection.", "items": { "type": "string" } }, "venue": { "title": "Venue", "type": "string", "description": "Journal or conference name, e.g. Nature, NeurIPS, ICML. Comma-separate several venues." }, "minCitationCount": { "title": "Minimum citations", "minimum": 0, "type": "integer", "description": "Only papers cited at least this many times." }, "hasPdf": { "title": "Only papers with a public PDF", "type": "boolean", "description": "Return only papers with an open-access PDF link.", "default": false }, "includeAuthorPapers": { "title": "Include each author's papers (Authors mode)", "type": "boolean", "description": "After each author row, list that author's papers (most recent first) until Maximum rows is reached. Author search stops at 25 authors when this is on.", "default": false }, "apiKey": { "title": "Semantic Scholar API key (optional)", "type": "string", "description": "Unlocks relevance-ranked search and higher rate limits. Free at semanticscholar.org/product/api. Without a key the actor uses the public pool at about one request per second." } } }, "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 } } } } } } } } } }