Scrapy MCP Server

# Data Extractor Configuration # Copy this file to .env and customize the values # Server Settings DATA_EXTRACTOR_SERVER_NAME=data-extractor # DATA_EXTRACTOR_SERVER_VERSION=auto # 版本号自动从 pyproject.toml 读取，无需手动配置 # Data Extractor Framework Settings DATA_EXTRACTOR_CONCURRENT_REQUESTS=16 DATA_EXTRACTOR_DOWNLOAD_DELAY=1.0 DATA_EXTRACTOR_RANDOMIZE_DOWNLOAD_DELAY=true DATA_EXTRACTOR_AUTOTHROTTLE_ENABLED=true DATA_EXTRACTOR_AUTOTHROTTLE_START_DELAY=1.0 DATA_EXTRACTOR_AUTOTHROTTLE_MAX_DELAY=60.0 DATA_EXTRACTOR_AUTOTHROTTLE_TARGET_CONCURRENCY=1.0 # Browser Automation Settings DATA_EXTRACTOR_ENABLE_JAVASCRIPT=false DATA_EXTRACTOR_BROWSER_HEADLESS=true DATA_EXTRACTOR_BROWSER_TIMEOUT=30 # Anti-Detection Settings DATA_EXTRACTOR_USE_RANDOM_USER_AGENT=true DATA_EXTRACTOR_DEFAULT_USER_AGENT="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36" # Proxy Settings (optional) DATA_EXTRACTOR_USE_PROXY=false DATA_EXTRACTOR_PROXY_URL= # Request Settings DATA_EXTRACTOR_MAX_RETRIES=3 DATA_EXTRACTOR_REQUEST_TIMEOUT=30