{ "openapi": "3.0.1", "info": { "title": "Baseball Savant Scraper: Scheduled Statcast Data", "description": "Extract MLB Statcast pitch data (velocity, spin rate, launch angle, exit velocity) and player-season leaderboards (xBA, xwOBA, barrel%) from Baseball Savant. The only Statcast actor with scheduled incremental sync, pulling only games since last run. No pybaseball timeouts or manual CSV exports.", "version": "0.1", "x-build-id": "jKY6tLZJ5pWbA1bkn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/getascraper~baseball-savant-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-getascraper-baseball-savant-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/getascraper~baseball-savant-scraper/runs": { "post": { "operationId": "runs-sync-getascraper-baseball-savant-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/getascraper~baseball-savant-scraper/run-sync": { "post": { "operationId": "run-sync-getascraper-baseball-savant-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "runMode": { "title": "Run mode", "enum": [ "dateRange", "incremental" ], "type": "string", "description": "Incremental mode is designed for Apify Schedules: each run automatically picks up where the previous successful run left off, so you never re-pull the same games twice.", "default": "dateRange" }, "startDate": { "title": "Start date", "type": "string", "description": "First game date to include (YYYY-MM-DD). Ignored when Run mode is Incremental.", "default": "" }, "endDate": { "title": "End date", "type": "string", "description": "Last game date to include (YYYY-MM-DD). Ignored when Run mode is Incremental (incremental mode always pulls through yesterday, since today's games may still be in progress).", "default": "" }, "lookbackDays": { "title": "First-run lookback (days)", "minimum": 1, "maximum": 30, "type": "integer", "description": "Only used the very first time Incremental mode runs (no saved sync state yet). How many days back from today to start pulling.", "default": 3 }, "playerType": { "title": "Player perspective", "enum": [ "pitcher", "batter" ], "type": "string", "description": "Statcast search perspective. Both return the same pitch events, just filterable from either side.", "default": "pitcher" }, "team": { "title": "Team (optional)", "type": "string", "description": "Optional 3-letter MLB team abbreviation (e.g. NYY, LAD, BOS) to restrict results to games involving this team. Leave blank for all teams.", "default": "" }, "outputMode": { "title": "Output mode", "enum": [ "pitchDetails", "leaderboard", "both" ], "type": "string", "description": "Pitch-level detail is the full 100+ column Statcast export per pitch. Leaderboard is aggregated player-season expected-stats (xBA, xwOBA, barrel%).", "default": "pitchDetails" }, "leaderboardYear": { "title": "Leaderboard season year", "minimum": 2015, "maximum": 2030, "type": "integer", "description": "MLB season year for the leaderboard pull (e.g. 2026).", "default": 2026 }, "leaderboardType": { "title": "Leaderboard type", "enum": [ "batter", "pitcher" ], "type": "string", "description": "Whether the leaderboard covers batters or pitchers.", "default": "batter" }, "leaderboardMinPa": { "title": "Minimum qualifier (PA or IP)", "minimum": 0, "type": "integer", "description": "Minimum plate appearances (batter) or innings pitched (pitcher) threshold for the leaderboard, matching Baseball Savant's own qualifier filter.", "default": 50 }, "chunkDays": { "title": "Date-chunk size (days)", "minimum": 1, "maximum": 14, "type": "integer", "description": "Number of days pulled per individual request to /statcast_search/csv. Smaller chunks are safer for wide ranges; MLB season runs late March through October.", "default": 3 }, "maxItems": { "title": "Max items", "minimum": 0, "type": "integer", "description": "Maximum number of dataset records to push across the whole run (0 = unlimited). If the limit is hit mid-range, the incremental sync cursor still only advances through the last fully-completed date chunk, so the next run resumes cleanly.", "default": 5000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Off by default. Baseball Savant's CSV/JSON export endpoints are fully open (no anti-bot challenge, no IP-reputation gating observed) and confirmed to time out when routed through Apify's datacenter proxy pool, so a direct connection is both faster and more reliable. Only enable if you see blocks at high volume.", "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 } } } } } } } } } }