{ "openapi": "3.0.1", "info": { "title": "Semantic Scholar Scraper", "description": "Scrape Semantic Scholar with 200M+ academic papers and authors with full citation graph. Search, fetch by paper/author ID, get citations / references / recommendations, with abstracts, TLDRs, fields-of-study, open-access PDFs, h-index, affiliations, and more", "version": "1.0", "x-build-id": "6Ux96rY9ZEia5xQr5" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/crawlerbros~semanticscholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-crawlerbros-semanticscholar-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/crawlerbros~semanticscholar-scraper/runs": { "post": { "operationId": "runs-sync-crawlerbros-semanticscholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/crawlerbros~semanticscholar-scraper/run-sync": { "post": { "operationId": "run-sync-crawlerbros-semanticscholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "searchPaper", "searchPaperBulk", "byPaper", "byPaperCitations", "byPaperReferences", "searchAuthor", "byAuthor", "byAuthorPapers", "recommendations", "byUrl" ], "type": "string", "description": "What to fetch.", "default": "byPaper" }, "searchQuery": { "title": "Search query", "type": "string", "description": "Free-text query for searchPaper / searchPaperBulk / searchAuthor modes. Examples: `transformer attention`, `geoffrey hinton`, `crispr cas9`.", "default": "transformer attention" }, "year": { "title": "Year filter (search modes)", "type": "string", "description": "Filter papers by publication year. Accepts a single year (`2023`), an open range (`2018-`, `-2010`), or a closed range (`2015-2020`)." }, "fieldsOfStudy": { "title": "Fields of study (search modes)", "uniqueItems": true, "type": "array", "description": "Filter to one or more Semantic Scholar fields-of-study. Multi-select.", "items": { "type": "string", "enum": [ "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" ], "enumTitles": [ "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" ] }, "default": [] }, "publicationTypes": { "title": "Publication types (search modes)", "uniqueItems": true, "type": "array", "description": "Filter by publication type. Multi-select.", "items": { "type": "string", "enum": [ "Review", "JournalArticle", "CaseReport", "ClinicalTrial", "Conference", "Dataset", "Editorial", "LettersAndComments", "MetaAnalysis", "News", "Study", "Book", "BookSection" ], "enumTitles": [ "Review", "Journal Article", "Case Report", "Clinical Trial", "Conference", "Dataset", "Editorial", "Letters / Comments", "Meta-Analysis", "News", "Study", "Book", "Book Section" ] }, "default": [] }, "venues": { "title": "Venues (search modes)", "type": "array", "description": "Filter by publication venue (e.g. `Nature`, `NeurIPS`, `IEEE Transactions on Pattern Analysis`).", "default": [], "items": { "type": "string" } }, "openAccessOnly": { "title": "Open-access only (search modes)", "type": "boolean", "description": "Drop papers without an open-access PDF.", "default": false }, "minCitationCount": { "title": "Min citation count (search modes)", "minimum": 0, "maximum": 10000000, "type": "integer", "description": "Drop papers with fewer than this many citations." }, "sort": { "title": "Sort (searchPaperBulk only)", "enum": [ "", "relevance", "citationCount:desc", "citationCount:asc", "publicationDate:desc", "publicationDate:asc" ], "type": "string", "description": "Sort order for bulk search. Relevance-ranked search uses an internal score and ignores this field.", "default": "" }, "paperIds": { "title": "Paper IDs (byPaper / byPaperCitations / byPaperReferences / recommendations)", "type": "array", "description": "Semantic Scholar paper IDs (40-char hex), or prefixed external IDs: `DOI:10.1145/...`, `ARXIV:1706.03762`, `MAG:...`, `PMID:...`, `PMCID:PMC...`, `ACL:...`. Bare DOIs and arXiv IDs are auto-prefixed.", "default": [], "items": { "type": "string" } }, "authorIds": { "title": "Author IDs (byAuthor / byAuthorPapers)", "type": "array", "description": "Numeric Semantic Scholar author IDs (e.g. `1741101`).", "default": [], "items": { "type": "string" } }, "urls": { "title": "URLs (byUrl mode)", "type": "array", "description": "Semantic Scholar / DOI / arXiv URLs. Examples: `https://www.semanticscholar.org/paper/`, `https://arxiv.org/abs/1706.03762`, `https://doi.org/10.1145/...`, `https://www.semanticscholar.org/author/1741101`.", "default": [], "items": { "type": "string" } }, "includeCitationsOnPaper": { "title": "Include citations on paper records (byPaper)", "type": "boolean", "description": "Embed up to 200 citing-paper summaries inside each paper record (byPaper mode only). Increases payload size.", "default": false }, "includeReferencesOnPaper": { "title": "Include references on paper records (byPaper)", "type": "boolean", "description": "Embed up to 200 cited-paper summaries inside each paper record (byPaper mode only).", "default": false }, "paperFields": { "title": "Custom paper fields (advanced)", "type": "array", "description": "Override the default `fields=` list sent to the API for paper endpoints. Leave empty to use the curated default. See https://api.semanticscholar.org/api-docs/graph for the full list.", "default": [], "items": { "type": "string" } }, "authorFields": { "title": "Custom author fields (advanced)", "type": "array", "description": "Override the default `fields=` list sent to the API for author endpoints.", "default": [], "items": { "type": "string" } }, "semanticScholarApiKey": { "title": "Semantic Scholar API key (optional)", "type": "string", "description": "Raises rate limits 10x. Free signup: https://www.semanticscholar.org/product/api#api-key-form. The actor works without a key." }, "requestDelaySeconds": { "title": "Request delay (seconds)", "minimum": 0, "maximum": 30, "type": "integer", "description": "Delay between API calls. Defaults to 0 (with API key) or 2 (without). Honour the source's rate-limit budget." }, "maxItems": { "title": "Max items", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on emitted records.", "default": 50 }, "useProxy": { "title": "Use Apify proxy", "type": "boolean", "description": "Force routing through Apify proxy from the first request. Recommended when running without an API key from datacenter IPs (Apify cloud is rate-limited heavily by Semantic Scholar's free tier).", "default": false }, "autoEscalateOnBlock": { "title": "Auto-escalate to proxy on rate-limit", "type": "boolean", "description": "If the API responds 429 from direct IP, automatically rotate through Apify proxy sessions for the rest of the run. Helps avoid getting stuck on the unauthenticated 100-req/5-min cap from a single datacenter IP.", "default": true }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy configuration. Used only when useProxy is enabled. Auto-escalation falls back to the default Apify proxy group automatically.", "default": { "useApifyProxy": true, "apifyProxyGroups": [] } } } }, "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 } } } } } } } } } }