{ "openapi": "3.0.1", "info": { "title": "Google Scholar Scraper: Papers, Authors, Citations, BibTeX", "description": "Search Google Scholar at scale. Pulls paper metadata, author affiliations, h-index, cited by counts, citing paper lists, BibTeX, and PDF links. One row per paper. Pay per row.", "version": "0.1", "x-build-id": "y0pJJgwuPmr7p3ORV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapemint~google-scholar-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapemint-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapemint~google-scholar-scraper/runs": { "post": { "operationId": "runs-sync-scrapemint-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapemint~google-scholar-scraper/run-sync": { "post": { "operationId": "run-sync-scrapemint-google-scholar-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "queries": { "title": "Search queries", "type": "array", "description": "Free text queries. Supports Scholar operators: \"exact phrase\", author:Hinton, intitle:transformer. Example: [\"large language model\", \"author:LeCun convolutional\"].", "default": [], "items": { "type": "string" } }, "authorUrls": { "title": "Author profile URLs", "type": "array", "description": "Google Scholar citations profile URLs. Example: https://scholar.google.com/citations?user=JicYPdAAAAAJ. Returns the author's full publication list.", "default": [], "items": { "type": "string" } }, "clusterIds": { "title": "Cluster IDs", "type": "array", "description": "Scholar cluster IDs to fetch all versions of one paper, or its citing papers. Example: 17784817748666649498.", "default": [], "items": { "type": "string" } }, "paperUrls": { "title": "Direct paper URLs", "type": "array", "description": "Scholar result URLs to enrich with full metadata (BibTeX, citing papers, related). Useful when you already have a list of papers and need citations.", "default": [], "items": { "type": "string" } }, "yearFrom": { "title": "Published from year", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Lower bound on publication year. 0 means no lower bound.", "default": 0 }, "yearTo": { "title": "Published until year", "minimum": 0, "maximum": 2100, "type": "integer", "description": "Upper bound on publication year. 0 means no upper bound.", "default": 0 }, "sortBy": { "title": "Sort order", "enum": [ "relevance", "date" ], "type": "string", "description": "Relevance is Scholar's default. Date sorts newest first.", "default": "relevance" }, "language": { "title": "Language", "enum": [ "en", "es", "de", "fr", "it", "pt-BR", "ja", "zh-CN" ], "type": "string", "description": "Scholar interface language. Affects venue parsing and citation labels.", "default": "en" }, "includePatents": { "title": "Include patents", "type": "boolean", "description": "Include patent results. Off by default to keep results to peer reviewed papers.", "default": false }, "includeCaseLaw": { "title": "Include case law", "type": "boolean", "description": "Include legal case law results. Off by default.", "default": false }, "fetchAuthorProfiles": { "title": "Enrich with author profiles", "type": "boolean", "description": "For every paper with at least one author profile linked, fetch the author's affiliation, h-index, i10-index, and total citations. Adds one extra request per unique author.", "default": false }, "fetchCitedBy": { "title": "Fetch citing papers", "type": "boolean", "description": "For papers with N or more citations, fetch the list of papers that cite this work. Adds citingPapers[] to the row.", "default": false }, "minCitationsForCitedBy": { "title": "Minimum citations to fetch cited by", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Only fetch citing papers when the paper has at least this many citations. Avoids wasting requests on low cited papers.", "default": 50 }, "maxCitedByPapers": { "title": "Max citing papers per source paper", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Cap on how many citing papers to fetch per source paper. Scholar returns 10 per page.", "default": 20 }, "fetchBibtex": { "title": "Fetch BibTeX", "type": "boolean", "description": "Pull the BibTeX export for every paper. Adds bibtex (string) to the row. Adds one extra request per paper.", "default": false }, "fetchVersions": { "title": "Fetch all versions", "type": "boolean", "description": "For each paper, fetch every Scholar cluster version (preprint, published, repository copies). Adds versions[] to the row.", "default": false }, "maxPapers": { "title": "Total maximum papers", "minimum": 0, "maximum": 50000, "type": "integer", "description": "Hard cap on paper rows pushed per run. 0 means unlimited (Scholar caps at ~1000 results per query).", "default": 100 }, "maxPagesPerQuery": { "title": "Max pages per query", "minimum": 1, "maximum": 100, "type": "integer", "description": "Pages of 10 results to walk per query. Scholar caps at 100 pages (1000 results) per query and aggressively rate limits past page 30.", "default": 10 }, "dedupe": { "title": "Deduplicate across runs", "type": "boolean", "description": "Skip cluster IDs already pushed in previous runs. Keyed on Scholar cluster ID. Turn off to refresh stale rows.", "default": true }, "navigationDelayMs": { "title": "Delay between navigations (ms)", "minimum": 0, "maximum": 60000, "type": "integer", "description": "Pause between page loads. Scholar throttles fast scraping. 4000 to 8000 ms is the safe range.", "default": 4500 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 8, "type": "integer", "description": "Parallel browser pages. Keep at 1 to 2 unless you have a residential proxy pool.", "default": 1 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify proxy. Scholar aggressively blocks datacenter IPs. RESIDENTIAL strongly recommended.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }