{ "openapi": "3.0.1", "info": { "title": "GitHub Repository Intelligence - API-Based Data Scraper", "description": "Extract repository metadata, README content, and documentation from GitHub using the official REST API. Perfect for LLM training data, developer research, and competitive analysis. Search by keywords or fetch specific repositories.", "version": "1.0", "x-build-id": "HFtBV8pZ3GgwdnZ1u" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/benthepythondev~github-repository-intelligence/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-benthepythondev-github-repository-intelligence", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/benthepythondev~github-repository-intelligence/runs": { "post": { "operationId": "runs-sync-benthepythondev-github-repository-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/benthepythondev~github-repository-intelligence/run-sync": { "post": { "operationId": "run-sync-benthepythondev-github-repository-intelligence", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mode": { "title": "Scraping Mode", "enum": [ "search", "direct" ], "type": "string", "description": "Search for repositories by keywords or fetch specific repositories by URL", "default": "search" }, "searchQuery": { "title": "Search Query (Search Mode)", "type": "string", "description": "Search query for repositories (e.g., 'language:python stars:>1000', 'react', 'machine-learning'). Supports GitHub search syntax.", "default": "language:python stars:>1000" }, "repositoryUrls": { "title": "Repository URLs (Direct Mode)", "type": "string", "description": "GitHub repository URLs (one per line). Format: https://github.com/owner/repo" }, "sortBy": { "title": "Sort By (Search Mode)", "enum": [ "stars", "forks", "updated", "help-wanted-issues" ], "type": "string", "description": "How to sort search results", "default": "stars" }, "maxResults": { "title": "Maximum Results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Maximum number of repositories to fetch (search mode only)", "default": 30 }, "includeReadme": { "title": "Include README Content", "type": "boolean", "description": "Extract and include README file content (recommended for AI/LLM training)", "default": true }, "includeTopics": { "title": "Include Repository Topics", "type": "boolean", "description": "Fetch and include repository topics/tags", "default": true }, "includeLanguages": { "title": "Include Programming Languages", "type": "boolean", "description": "Fetch programming language statistics", "default": true }, "githubToken": { "title": "GitHub Personal Access Token (Optional)", "type": "string", "description": "Optional GitHub token for higher rate limits (5,000 vs 60 requests/hour). Create at: https://github.com/settings/tokens" }, "debugMode": { "title": "Debug Mode", "type": "boolean", "description": "Enable verbose logging for troubleshooting", "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 } } } } } } } } } }