Google Scholar Scraper
Pricing
from $3.99 / 1,000 results
Go to Apify Store
Google Scholar Scraper
Collect public Google Scholar publication records with bibliographic metadata, author links, public full-text links, citations, and versions.
Google Scholar Scraper
Pricing
from $3.99 / 1,000 results
Collect public Google Scholar publication records with bibliographic metadata, author links, public full-text links, citations, and versions.
You can access the Google Scholar Scraper programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "2.0", "x-build-id": "KtkpSK36VZTSGYLaM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/googleapi~google-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-googleapi-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/googleapi~google-scholar-scraper/runs": { "post": { "operationId": "runs-sync-googleapi-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/googleapi~google-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-googleapi-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": { "sourceTransport": { "title": "Source transport", "enum": [ "http", "browser" ], "type": "string", "description": "Direct HTTP or a fresh standard browser session from the start. Both stop at access boundaries. Browser sessions use more compute and do not reuse account cookies.", "default": "http" }, "query": { "title": "Search query", "maxLength": 300, "type": "string", "description": "One public Google Scholar query. Use this or queries." }, "queries": { "title": "Search queries", "maxItems": 20, "type": "array", "description": "Up to 20 public Google Scholar queries. Results share the global maxItems limit.", "items": { "type": "string", "minLength": 1, "maxLength": 300 } }, "keywords": { "title": "Queries alias", "maxItems": 20, "type": "array", "description": "Compatibility alias for queries.", "items": { "type": "string", "minLength": 1, "maxLength": 300 } }, "searchQuery": { "title": "Query alias", "maxLength": 300, "type": "string", "description": "Compatibility alias for query." }, "startUrls": { "title": "Google Scholar URLs", "maxItems": 20, "type": "array", "description": "Public HTTPS Google Scholar /scholar search URLs containing a q parameter. When supplied with queries, both sources are searched.", "items": { "type": "object", "properties": { "url": { "title": "Public Scholar search URL", "description": "HTTPS Google Scholar /scholar URL with a q search parameter.", "type": "string" } }, "required": [ "url" ], "additionalProperties": false } }, "urls": { "title": "Scholar URL alias", "maxItems": 20, "type": "array", "description": "Compatibility alias for public Google Scholar URLs.", "items": { "type": "string", "maxLength": 2000 } }, "maxItems": { "title": "Maximum publications", "minimum": 1, "maximum": 100, "type": "integer", "description": "Global maximum unique publication records across all queries and URLs.", "default": 25 }, "page": { "title": "Starting page", "minimum": 1, "maximum": 1000, "type": "integer", "description": "One-based Google Scholar results page to start from. Each page contains up to 10 results.", "default": 1 }, "maxPages": { "title": "Maximum pages per source", "minimum": 1, "maximum": 100, "type": "integer", "description": "Maximum result pages to inspect for each query or start URL.", "default": 10 }, "includeAuthors": { "title": "Include author and venue data", "type": "boolean", "description": "Include source-visible authors, author profile links, venue, year, and the publication metadata line.", "default": true }, "includeCitations": { "title": "Include citation data", "type": "boolean", "description": "Include visible citation counts and related-article links.", "default": true }, "includeVersions": { "title": "Include version data", "type": "boolean", "description": "Include visible version counts and version links.", "default": true }, "language": { "title": "Scholar language", "maxLength": 20, "type": "string", "description": "Google Scholar language code used in the public search URL and request language.", "default": "en" }, "country": { "title": "Country compatibility value", "maxLength": 5, "type": "string", "description": "Accepted for input compatibility. Google Scholar's public search page does not provide a country filter.", "default": "US" }, "timeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Timeout for each public Google Scholar request.", "default": 30 }, "timeoutMs": { "title": "Request timeout alias (milliseconds)", "minimum": 5000, "maximum": 120000, "type": "integer", "description": "Compatibility override for timeoutSecs; when both are supplied, timeoutMs takes precedence." }, "requestDelayMs": { "title": "Delay between requests (milliseconds)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Polite pause between sequential public page requests.", "default": 200 }, "maxRetries": { "title": "Maximum retries", "minimum": 0, "maximum": 3, "type": "integer", "description": "Finite retries for transient public request failures. Access boundaries are not retried.", "default": 1 }, "maxResponseBytes": { "title": "Maximum response size (bytes)", "minimum": 100000, "maximum": 10000000, "type": "integer", "description": "Maximum HTML body size accepted for one public page.", "default": 4000000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional existing Apify or custom HTTP proxy applied to every public source request and approved redirect. Residential proxies are recommended for Google domains. Proxy initialization or authentication failures stop without direct fallback." }, "enrichPublications": { "title": "Enrich from public Scholar details", "type": "boolean", "description": "Opt-in identity-matched public author and article details. Disabled by default.", "default": false }, "maxEnrichedPublications": { "title": "Maximum publications to enrich", "minimum": 1, "maximum": 20, "type": "integer", "description": "Maximum number of publication records considered for optional public detail fetching across the run.", "default": 3 }, "maxSourcePagesPerPublication": { "title": "Maximum detail pages per publication", "minimum": 1, "maximum": 2, "type": "integer", "description": "1: matched author profile. 2: profile and its matching public publication detail.", "default": 1 }, "detailTransport": { "title": "Public detail transport", "enum": [ "http", "browser" ], "type": "string", "description": "Explicit transport for opt-in public Scholar author and article details. A fresh ordinary browser can be selected from the start; no challenge fallback or cookie reuse.", "default": "http" } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Google Scholar Scraper from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: