{ "openapi": "3.0.1", "info": { "title": "🔍 Google Scholar Scraper", "description": "Google Scholar Scraper research papers from Google Scholar, including titles, authors, publication years, journals, citations, abstracts, PDFs, and profile links. Export structured data to JSON, CSV, Excel, or XML for academic research, literature reviews, citation analysis, and AI workflows.", "version": "0.2", "x-build-id": "tFQBWx9IIwS7TAf7O" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scraper-engine~google-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scraper-engine-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scraper-engine~google-scholar-scraper/runs": { "post": { "operationId": "runs-sync-scraper-engine-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scraper-engine~google-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-scraper-engine-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "searchQueries" ], "properties": { "searchQueries": { "title": "🔎 Search Queries / Scholar URLs", "type": "array", "description": "Bulk list of search keywords (e.g. \"Tomato Shelf Life Prediction\") OR full Google Scholar URLs (e.g. https://scholar.google.com/scholar?q=...). One per line. Required.", "items": { "type": "string" } }, "maxItems": { "title": "📊 Max items per query", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Maximum number of papers to fetch per query.", "default": 10 }, "filter": { "title": "🧰 Result filter", "enum": [ "all", "has_pdf", "open_access", "recent_5_years" ], "type": "string", "description": "Restrict results by availability or recency.", "default": "all" }, "newerThan": { "title": "🕐 Newer than (year)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Scrape only articles from this year on. Effective only when not sorting by date. Example: 2020 keeps everything published in 2020 or later." }, "olderThan": { "title": "🕒 Older than (year)", "minimum": 1800, "maximum": 2100, "type": "integer", "description": "Scrape articles up to this year. Effective only when not sorting by date. Example: 2024 keeps everything published in 2024 or earlier." }, "sortBy": { "title": "🔃 Sort results by", "enum": [ "relevance", "cited_by_count" ], "type": "string", "description": "How to order the final results.", "default": "relevance" }, "articleType": { "title": "📑 Article type", "enum": [ "any", "journal", "conference", "book", "preprint" ], "type": "string", "description": "Restrict to a specific article type.", "default": "any" }, "enableDebugDumps": { "title": "🐞 Enable debug dumps", "type": "boolean", "description": "Store a dump of every API response (OpenAlex + Semantic Scholar) into the default key-value store so you can inspect what was fetched. Useful for troubleshooting.", "default": false }, "proxyConfiguration": { "title": "🌐 Proxy Configuration", "type": "object", "description": "By default the actor connects directly. If a request is blocked or rate-limited, it auto-escalates to a Datacenter proxy, then to a Residential proxy (with 3 retries). Once switched to Residential, that stays sticky for the rest of the run.", "default": { "useApifyProxy": 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 } } } } } } } } } }