{ "openapi": "3.0.1", "info": { "title": "Google Scholar Scraper - Papers, Citations & h-index", "description": "Scrape Google Scholar without login: search results, author profiles (h-index, i10, citations per year, all articles) and cited-by lists. Title, authors with profile ids, venue, year, PDF link, cited-by count, versions. Pay per result.", "version": "0.1", "x-build-id": "8ENTxNdS8mBdIiTzp" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapewise~google-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapewise-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapewise~google-scholar-scraper/runs": { "post": { "operationId": "runs-sync-scrapewise-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapewise~google-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-scrapewise-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Queries as you would type them in Google Scholar, one per line, for example large language models. Operators work: \"exact phrase\", author:\"lecun\", source:nature, intitle:transformer. You can also paste a full scholar.google.com/scholar?... link to keep its filters. Each result row has title, authors, venue, year, snippet, citation count, PDF link and citesId, charged as 'Result delivered'.", "items": { "type": "string" } }, "authorProfiles": { "title": "Author profiles", "type": "array", "description": "Google Scholar author profiles, one per line: the profile id (DhtAFkwAAAAJ) or a link like https://scholar.google.com/citations?user=DhtAFkwAAAAJ. Returns one profile row (affiliation, interests, citations, h-index, i10-index, citations per year, co-authors), charged as 'Author profile delivered', plus one row per article.", "items": { "type": "string" } }, "citedBy": { "title": "Cited by (articles that cite a paper)", "type": "array", "description": "Papers whose citing papers you want, one per line: the number after cites= in a \"Cited by\" link (every search result has it in 'citesId'), or the whole link. Returns the papers that cite it, one row each, charged as results.", "items": { "type": "string" } }, "maxResultsPerQuery": { "title": "Max results per query or cited-by list", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum results for each query and each cited-by list, from 1 to 1,000 (default 50). Google Scholar shows up to 1,000 results (100 pages of 10) per query. You pay per result delivered, so this caps the cost of each query.", "default": 50 }, "maxArticlesPerAuthor": { "title": "Max articles per author profile", "minimum": 0, "type": "integer", "description": "Maximum articles for each author profile, default 100. Articles are read 100 per page. Set 0 to get only the profile row, without articles.", "default": 100 }, "yearFrom": { "title": "Published from year", "minimum": 1500, "type": "integer", "description": "Only results published in or after this year, for example 2020. Applies to searches and cited-by lists. Empty = any year." }, "yearTo": { "title": "Published up to year", "minimum": 1500, "type": "integer", "description": "Only results published in or before this year, for example 2024. Applies to searches and cited-by lists. Empty = any year." }, "sortBy": { "title": "Sort by", "enum": [ "relevance", "date" ], "type": "string", "description": "Relevance (default) or Date, newest first. Google Scholar only sorts by date within the last year, so Date returns recent papers only.", "default": "relevance" }, "excludeCitations": { "title": "Exclude [CITATION] entries", "type": "boolean", "description": "Off (default). On: skip [CITATION] entries, which Google Scholar only knows from other papers' references (no full text or link). Skipped entries are not charged.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Apify Proxy is the default and recommended. When Google Scholar shows a captcha, the Actor retries on its own, with no extra charge; it never solves captchas. Change it only to use your own proxies.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } }