{ "openapi": "3.0.1", "info": { "title": "Google Scholar Paper & Citation Search Scraper", "description": "Search Google Scholar by keyword and get structured records for papers and citations, with author, venue, year, citation counts, and links to PDFs and related work. Filter by year range, document format, and article type.", "version": "1.0", "x-build-id": "pdUktx8PmbvFPEYYD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dataspryva~google-scholar-paper-and-citation-search-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dataspryva-google-scholar-paper-and-citation-search-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dataspryva~google-scholar-paper-and-citation-search-scraper/runs": { "post": { "operationId": "runs-sync-dataspryva-google-scholar-paper-and-citation-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dataspryva~google-scholar-paper-and-citation-search-scraper/run-sync": { "post": { "operationId": "run-sync-dataspryva-google-scholar-paper-and-citation-search-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Mode", "enum": [ "search", "citations", "authorProfile" ], "type": "string", "description": "What to fetch: paper search, citing papers, or public author profiles.", "default": "search" }, "queries": { "title": "Search Queries", "type": "array", "description": "Keywords or paper titles to search on Google Scholar (mode=search). Each query runs separately.", "items": { "type": "string" } }, "clusterIds": { "title": "Cluster IDs or Citing URLs", "type": "array", "description": "Paper cluster IDs or Google Scholar 'cites=' URLs to list citing papers for (mode=citations).", "items": { "type": "string" } }, "authorIds": { "title": "Author IDs or Profile URLs", "type": "array", "description": "Google Scholar author IDs or profile URLs to export (mode=authorProfile).", "items": { "type": "string" } }, "maxItems": { "title": "Maximum Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum papers per query or cluster, or papers per author. Google Scholar serves about 10 search results per page.", "default": 100 }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "date" ], "type": "string", "description": "Sort search results by relevance or date (mode=search).", "default": "relevance" }, "filter": { "title": "Document Format", "enum": [ "all", "pdfOnly", "htmlOnly" ], "type": "string", "description": "Keep only PDF or HTML results; applied to returned rows (mode=search).", "default": "all" }, "articleType": { "title": "Article Type", "enum": [ "any", "review" ], "type": "string", "description": "Return all articles or review articles only (mode=search).", "default": "any" }, "newerThan": { "title": "Published After (Year)", "minimum": 1900, "maximum": 2030, "type": "integer", "description": "Only include papers published in this year or later (mode=search)." }, "olderThan": { "title": "Published Before (Year)", "minimum": 1900, "maximum": 2030, "type": "integer", "description": "Only include papers published in this year or earlier (mode=search)." }, "author": { "title": "Authored By", "type": "string", "description": "Return papers written by this author, e.g. 'Geoffrey Hinton' (mode=search)." }, "publication": { "title": "Published In", "type": "string", "description": "Return papers from this journal or venue, e.g. 'Nature' (mode=search)." }, "titleOnly": { "title": "Search Titles Only", "type": "boolean", "description": "Match the query against paper titles instead of the full text (mode=search).", "default": false }, "includeCitationFormats": { "title": "Include Citation Formats", "type": "boolean", "description": "Also return MLA, APA, Chicago, Harvard, and Vancouver citations for returned rows, within a bounded budget (mode=search or citations).", "default": false }, "includePaperDetails": { "title": "Include Paper Details", "type": "boolean", "description": "Fetch journal, volume, pages, publisher, and abstract for each author publication (mode=authorProfile).", "default": false } } }, "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 } } } } } } } } } }