feat: activate autonomous scraper

scraper.py

@@ -0,0 +1,68 @@
+import asyncio
+from playwright.async_api import async_playwright
+from supabase import create_client, Client
+
+# --- 1. SETUP YOUR SUPABASE VAULT HERE ---
+SUPABASE_URL = os.environ.get("SUPABASE_URL")
+SUPABASE_KEY = os.environ.get("SUPABASE_KEY")
+
+# Connect to the database
+supabase: Client = create_client(SUPABASE_URL, SUPABASE_KEY)
+
+async def scrape_and_upload():
+    print("🥷 Booting up GovBridge Bot (Upload Mode)...")
+    
+    async with async_playwright() as p:
+        browser = await p.chromium.launch(
+            headless=True,
+            args=["--disable-blink-features=AutomationControlled"],
+            ignore_default_args=["--enable-automation"]
+        )
+        context = await browser.new_context(
+            user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36"
+        )
+        
+        # Apply the stealth mask to hide from the firewall
+        await context.add_init_script("Object.defineProperty(navigator, 'webdriver', {get: () => undefined})")
+        page = await context.new_page()
+        
+        print("🌐 Navigating to myscheme.gov.in...")
+        await page.goto("https://www.myscheme.gov.in/search")
+        await page.wait_for_timeout(5000) 
+        
+        print("🎯 Target acquired! Ripping the text...")
+        titles = await page.locator("h2").all_inner_texts()
+        schemes = [t.strip() for t in titles if len(t.strip()) > 5 and "Filter By" not in t]
+        
+        if len(schemes) >= 2:
+            # We noticed the website groups the Title first, and the Ministry second!
+            first_scheme_title = schemes[0]
+            first_scheme_ministry = schemes[1]
+            
+            print(f"\n--- INITIATING DATABASE UPLOAD ---")
+            print(f"📤 Uploading: {first_scheme_title}...")
+            
+            # Package the data to match our official_documents table perfectly
+            data_to_save = {
+                "title": first_scheme_title,
+                "department": first_scheme_ministry,
+                "document_type": "Auto-Scraped Scheme",
+                "file_url": "https://www.myscheme.gov.in/search",
+                "authentic_source_url": "https://www.myscheme.gov.in"
+            }
+            
+            try:
+                # Fire the data directly into your Supabase vault!
+                supabase.table("official_documents").insert(data_to_save).execute()
+                print("✅ SUCCESS! The data bypassed the terminal and is now live in your database!")
+            except Exception as e:
+                print(f"❌ Upload failed: {e}")
+                
+        else:
+            print("❌ Didn't find enough data on the page to upload.")
+                
+        print("\nShutting down bot.")
+        await browser.close()
+
+if __name__ == "__main__":
+    asyncio.run(scrape_and_upload())