California & SF Construction Regulations Scraper ## 🚧 What does it do? This Actor scrapes detailed construction safety orders and building regulations from official California government sources (specifically Cal/OSHA Title 8). It is designed to be the "Data Acquisition Layer" for Construction AI agents, RAG pipelines, and compliance checking tools. Unlike general scrapers, this actor: - Filters out junk: Ignores "Contact Us", "Jobs", and unrelated pages. - Deep crawling: Penetrates 3 levels deep to find the actual text of the law (Section/Article level). - Clean Output: Returns structured JSON ready for Vector Databases (Pinecone, Milvus, etc.). ## 🎯 Use Cases - AI Compliance Agents: Feed this data into an LLM to answer questions like "What is the railing height requirement in SF?". - Construction Bidding: Automatically check if a project plan meets specific safety codes. - Legal Monitoring: Track changes in Title 8 Safety Orders. ## ⚙️ Input Configuration You can configure the target region. Currently optimized for San Francisco / California. Example Input (JSON): ```json { "city": "San Francisco", "state": "CA", "max_pages": 99999 } 📦 Output Format The actor stores results in the Apify Dataset. Each item represents a specific regulation section containing the full legal text. Example JSON Result: { "source_url": "https://www.dir.ca.gov/title8/1620.html", "title": "§1620. Design and Construction of Guardrails.", "text": "A. Railing specifications... (full legal text here)...", "region": "San Francisco, CA", "segment": "cal_osha_detailed", "timestamp": "2025-12-06T20:30:00+00:00" } 🚀 How to use Click the green Start button. Wait for the run to finish (it scans dir.ca.gov). Go to the Storage tab -> Dataset to view results. Click Export to download the data in JSON, CSV, or Excel format. (Optional) Use the API to integrate this data directly into your AI application.