All configs now follow the steam-economy-complete.json pattern with: - Multiple start_urls for comprehensive entry points - Improved include patterns for better targeting - Enhanced exclude patterns to skip irrelevant pages Godot Config: - Added 7 start_urls covering getting started, scripting, 2D, 3D, physics, animation, and classes - Added include patterns: /getting_started/, /tutorials/, /classes/ - More focused scraping of core documentation React Config: - Added 6 start_urls covering learn, quick-start, reference, and hooks - Existing patterns maintained (already well-optimized) Vue Config: - Added 6 start_urls covering introduction, essentials, components, composables, and API - Fixed base_url from https://vuejs.org/guide/ to https://vuejs.org/ - Added /partners/ to exclude list Django Config: - Added 7 start_urls covering intro, models, views, templates, forms, auth, and reference - Added /intro/ to include patterns - Added /releases/ to exclude list (changelog not needed) FastAPI Config: - Added 7 start_urls covering tutorial, first-steps, path-params, body, dependencies, advanced, and reference - Added /deployment/ to exclude list Benefits: - Better initial page discovery - More comprehensive documentation coverage - Faster scraping (direct entry to important sections) - Reduced unnecessary page crawling - Consistent pattern across all configs All configs tested and validated: ✅ 71/71 tests passing ✅ All 6 configs validated successfully 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
32 lines
1.0 KiB
JSON
32 lines
1.0 KiB
JSON
{
|
|
"name": "react",
|
|
"description": "React framework for building user interfaces. Use for React components, hooks, state management, JSX, and modern frontend development.",
|
|
"base_url": "https://react.dev/",
|
|
"start_urls": [
|
|
"https://react.dev/learn",
|
|
"https://react.dev/learn/quick-start",
|
|
"https://react.dev/learn/thinking-in-react",
|
|
"https://react.dev/reference/react",
|
|
"https://react.dev/reference/react-dom",
|
|
"https://react.dev/reference/react/hooks"
|
|
],
|
|
"selectors": {
|
|
"main_content": "article",
|
|
"title": "h1",
|
|
"code_blocks": "pre code"
|
|
},
|
|
"url_patterns": {
|
|
"include": ["/learn", "/reference"],
|
|
"exclude": ["/community", "/blog"]
|
|
},
|
|
"categories": {
|
|
"getting_started": ["quick-start", "installation", "tutorial"],
|
|
"hooks": ["usestate", "useeffect", "usememo", "usecallback", "usecontext", "useref", "hook"],
|
|
"components": ["component", "props", "jsx"],
|
|
"state": ["state", "context", "reducer"],
|
|
"api": ["api", "reference"]
|
|
},
|
|
"rate_limit": 0.5,
|
|
"max_pages": 300
|
|
}
|