{ "openapi": "3.0.1", "info": { "title": "College Football Roster Scraper", "description": "Scrape college football roster pages into clean player datasets. Extract names, jersey numbers, positions, class year, height, weight, hometown, profile URLs, and headshots from FCS/default URLs or custom roster links. Includes adapters for multiple athletics site formats.", "version": "0.0", "x-build-id": "VhVMOtNzzpwT5K8A7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ericfox~college-football-roster-scraper-apify/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ericfox-college-football-roster-scraper-apify", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ericfox~college-football-roster-scraper-apify/runs": { "post": { "operationId": "runs-sync-ericfox-college-football-roster-scraper-apify", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ericfox~college-football-roster-scraper-apify/run-sync": { "post": { "operationId": "run-sync-ericfox-college-football-roster-scraper-apify", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "useDefaultFcsUrls": { "title": "Use bundled FCS roster URL dataset", "type": "boolean", "description": "When enabled, the Actor uses the bundled 2025 FCS roster URL list as the demo/default source set. Add startUrls below to merge custom URLs into the run.", "default": true }, "startUrls": { "title": "Additional roster URLs", "type": "array", "description": "Optional additional college football roster page URLs. Each item can include userData.team_name.", "default": [], "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "season": { "title": "Season label", "type": "string", "description": "Optional season value to place on each result. If blank, the Actor tries to infer it from /roster/2025-style URLs.", "default": "2025" }, "sport": { "title": "Sport label", "type": "string", "description": "Output label. Keep as football for this Actor unless adapting the selectors for another sport.", "default": "football" }, "maxRosterUrls": { "title": "Max roster URLs", "minimum": 0, "type": "integer", "description": "Safety cap for the number of roster pages to crawl. Set to 0 to run the full bundled/default list.", "default": 10 }, "maxPlayersPerTeam": { "title": "Max players per team", "minimum": 0, "type": "integer", "description": "Optional cap per roster page. Set to 0 for no cap.", "default": 0 }, "adapterMode": { "title": "Adapter mode", "enum": [ "auto", "sidearm", "presto", "json-state", "table", "generic-card" ], "type": "string", "description": "Auto runs the platform/domain adapters plus safe fallbacks. Use a specific adapter only for debugging a problem domain.", "default": "auto" }, "emitDiagnosticRows": { "title": "Emit diagnostic rows for zero-player pages", "type": "boolean", "description": "When enabled, pages with no extracted players add a visible diagnostic row to the dataset. Detailed diagnostics are always saved in ZERO_PLAYER_PAGES and RUN_SUMMARY key-value records.", "default": false }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many roster pages to fetch in parallel. Keep moderate for school athletics sites.", "default": 10 }, "maxRequestRetries": { "title": "Max request retries", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of retries for failed roster page requests.", "default": 2 }, "requestHandlerTimeoutSecs": { "title": "Request handler timeout seconds", "minimum": 10, "maximum": 180, "type": "integer", "description": "How long to allow extraction from each roster page before timing out.", "default": 45 }, "navigationTimeoutSecs": { "title": "Navigation timeout seconds", "minimum": 10, "maximum": 120, "type": "integer", "description": "How long to wait for each page HTTP response.", "default": 30 }, "useSessionPool": { "title": "Use session pool", "type": "boolean", "description": "Keep enabled for more stable crawling across many athletics domains.", "default": true }, "respectRobotsTxtFile": { "title": "Respect robots.txt", "type": "boolean", "description": "Enable this if you want the crawler to obey robots.txt for each domain. You should still review source-site terms before commercial reuse.", "default": 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 } } } } } } } } } }