name: Fetch Congress Trades
 
on:
  schedule:
    - cron: '0 6 * * *'
  workflow_dispatch:
 
permissions:
  contents: write
 
jobs:
  fetch:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repo
        uses: actions/checkout@v4
        with:
          token: ${{ secrets.GITHUB_TOKEN }}
 
      - name: Install Playwright
        run: |
          pip install playwright
          playwright install chromium
          playwright install-deps chromium
 
      - name: Scrape Capitol Trades with real browser
        run: |
          python3 << 'PYEOF'
          import json, datetime
          from playwright.sync_api import sync_playwright
 
          all_trades = []
 
          with sync_playwright() as p:
              browser = p.chromium.launch(headless=True)
              context = browser.new_context(
                  user_agent='Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'
              )
              page = context.new_page()
 
              # Intercept API responses
              api_data = []
              def handle_response(response):
                  if 'capitoltrades.com/trades' in response.url:
                      try:
                          data = response.json()
                          api_data.append(('trades', data))
                          print(f"Intercepted: {response.url} - {len(str(data))} bytes")
                      except:
                          pass
 
              page.on('response', handle_response)
 
              # Visit Capitol Trades
              print("Loading Capitol Trades...")
              page.goto('https://www.capitoltrades.com/trades', wait_until='networkidle', timeout=30000)
              page.wait_for_timeout(3000)
 
              print(f"Intercepted {len(api_data)} API calls")
 
              # Parse intercepted data
              for name, data in api_data:
                  for t in (data.get('data') or []):
                      ticker = (t.get('ticker') or t.get('asset', {}).get('ticker') or '').upper().replace('--','')
                      if not ticker or len(ticker) > 6:
                          continue
                      all_trades.append({
                          'date': t.get('txDate') or t.get('reportedDate', ''),
                          'representative': t.get('politician', {}).get('name', ''),
                          'ticker': ticker,
                          'type': t.get('txType', ''),
                          'amount': str(t.get('txValue', '')),
                          'description': t.get('asset', {}).get('assetName', ticker),
                          'source': 'house'
                      })
 
              # If no API data, scrape the HTML
              if not all_trades:
                  print("No API data intercepted, trying HTML scrape...")
                  content = page.content()
                  print(f"Page content length: {len(content)}")
                  print(f"First 500 chars: {content[:500]}")
 
              browser.close()
 
          all_trades.sort(key=lambda x: x.get('date',''), reverse=True)
          output = {
              'trades': all_trades[:200],
              'house_count': len(all_trades),
              'senate_count': 0,
              'updated': datetime.datetime.now(datetime.timezone.utc).isoformat()
          }
          with open('trades.json', 'w') as f:
              json.dump(output, f)
          print(f"Saved {len(all_trades)} trades")
          PYEOF
 
      - name: Commit trades.json
        run: |
          git config user.name "github-actions"
          git config user.email "actions@github.com"
          git add trades.json
          git diff --staged --quiet || git commit -m "Auto-update trades $(date -u '+%Y-%m-%d')"
          git push