{ "openapi": "3.0.1", "info": { "title": "Google Scholar Scraper", "description": "[💰 $2.0 / 1K] Extract academic papers, author profiles, h-index, i10-index, citation counts, abstracts, and PDF links from Google Scholar. Batch search queries and author IDs, filter by year range, sort by relevance or date.", "version": "1.0", "x-build-id": "tZgAe4WGfzfLaYQqw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/solidcode~google-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-solidcode-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/solidcode~google-scholar-scraper/runs": { "post": { "operationId": "runs-sync-solidcode-google-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/solidcode~google-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-solidcode-google-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": { "searchQueries": { "title": "Search Queries", "type": "array", "description": "Keywords to search on Google Scholar (e.g., 'machine learning healthcare' or 'quantum error correction'). Each query produces its own set of paper results. Leave empty if you only want author profiles.", "items": { "type": "string" } }, "authorIds": { "title": "Author IDs or Profile URLs", "type": "array", "description": "Google Scholar author IDs or profile URLs to scrape full profiles (h-index, i10-index, citation counts, publication list). Paste either the 10-14 character ID (e.g., 'JicYPdAAAAAJ') or the full profile URL (e.g., 'https://scholar.google.com/citations?user=JicYPdAAAAAJ&hl=en'). The ID is the value after `user=` in the URL.", "items": { "type": "string" } }, "maxResults": { "title": "Maximum Results per Query", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Maximum number of papers to return per search query. Google Scholar caps searches at roughly 1,000 results. Set to 0 for all available results.", "default": 50 }, "yearFrom": { "title": "Year From", "minimum": 1900, "maximum": 2100, "type": "integer", "description": "Only include papers published in this year or later. Leave empty for no lower bound." }, "yearTo": { "title": "Year To", "minimum": 1900, "maximum": 2100, "type": "integer", "description": "Only include papers published in this year or earlier. Leave empty for no upper bound." }, "sortBy": { "title": "Sort By", "enum": [ "relevance", "date" ], "type": "string", "description": "How to order paper results.", "default": "relevance" }, "language": { "title": "Language", "enum": [ "en", "es", "de", "fr", "it", "pt", "nl", "pl", "tr", "ru", "ja", "ko", "zh-CN", "zh-TW", "ar", "he", "th", "vi", "id", "hi" ], "type": "string", "description": "Language of the Scholar interface and result snippets.", "default": "en" }, "country": { "title": "Country", "enum": [ "us", "uk", "ca", "au", "nz", "ie", "fr", "de", "es", "it", "nl", "be", "pt", "ch", "at", "se", "no", "dk", "fi", "pl", "jp", "kr", "cn", "hk", "tw", "sg", "my", "th", "id", "ph", "vn", "in", "br", "mx", "ar", "cl", "co", "ae", "sa", "tr", "il", "za", "eg" ], "type": "string", "description": "Country code (gl) for result localization. Affects which regional mirror is used.", "default": "us" }, "includeAbstracts": { "title": "Include Abstracts", "type": "boolean", "description": "Include the snippet/abstract text for each paper. Disable to reduce dataset size.", "default": true }, "includeCitations": { "title": "Include Citing Papers", "type": "boolean", "description": "For each paper, follow the 'Cited by' link and return the papers that cite it. This significantly increases runtime and cost — leave off unless you need citation graphs.", "default": false }, "maxCitationsPerPaper": { "title": "Max Citing Papers per Source Paper", "minimum": 1, "maximum": 200, "type": "integer", "description": "When 'Include Citing Papers' is on, this caps how many citing papers are fetched per source paper. Default 20; higher values linearly increase runtime and cost.", "default": 20 }, "includeBibtex": { "title": "Include BibTeX", "type": "boolean", "description": "Also collect a BibTeX entry and formatted citation strings (MLA, APA, Chicago, Harvard, Vancouver) for every paper. Adds 2 extra requests per paper — useful for bibliography workflows.", "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 } } }, "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 } } } } } } } } } }