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>
34 lines
1.2 KiB
JSON
34 lines
1.2 KiB
JSON
{
|
|
"name": "fastapi",
|
|
"description": "FastAPI modern Python web framework. Use for building APIs, async endpoints, dependency injection, and Python backend development.",
|
|
"base_url": "https://fastapi.tiangolo.com/",
|
|
"start_urls": [
|
|
"https://fastapi.tiangolo.com/tutorial/",
|
|
"https://fastapi.tiangolo.com/tutorial/first-steps/",
|
|
"https://fastapi.tiangolo.com/tutorial/path-params/",
|
|
"https://fastapi.tiangolo.com/tutorial/body/",
|
|
"https://fastapi.tiangolo.com/tutorial/dependencies/",
|
|
"https://fastapi.tiangolo.com/advanced/",
|
|
"https://fastapi.tiangolo.com/reference/"
|
|
],
|
|
"selectors": {
|
|
"main_content": "article",
|
|
"title": "h1",
|
|
"code_blocks": "pre code"
|
|
},
|
|
"url_patterns": {
|
|
"include": ["/tutorial/", "/advanced/", "/reference/"],
|
|
"exclude": ["/help/", "/external-links/", "/deployment/"]
|
|
},
|
|
"categories": {
|
|
"getting_started": ["first-steps", "tutorial", "intro"],
|
|
"path_operations": ["path", "operations", "routing"],
|
|
"request_data": ["request", "body", "query", "parameters"],
|
|
"dependencies": ["dependencies", "injection"],
|
|
"security": ["security", "oauth", "authentication"],
|
|
"database": ["database", "sql", "orm"]
|
|
},
|
|
"rate_limit": 0.5,
|
|
"max_pages": 250
|
|
}
|