diagnose_cams.py

#!/usr/bin/env python3
"""
CAMS Download Diagnostic Tool
Helps troubleshoot issues with CAMS data downloads
"""

import os
import zipfile
from pathlib import Path
from datetime import datetime, timedelta

def diagnose_cams_downloads():
    """Diagnose CAMS download issues"""
    print("🔍 CAMS Download Diagnostic Tool")
    print("=" * 50)
    
    # Check downloads directory
    downloads_dir = Path("downloads")
    if not downloads_dir.exists():
        print("❌ Downloads directory doesn't exist")
        return
    
    print(f"📁 Downloads directory: {downloads_dir.absolute()}")
    
    # List all files in downloads
    all_files = list(downloads_dir.glob("*"))
    if not all_files:
        print("📂 Downloads directory is empty")
        return
    
    print(f"\n📋 Found {len(all_files)} files:")
    
    for file_path in all_files:
        print(f"\n📄 File: {file_path.name}")
        print(f"   Size: {file_path.stat().st_size} bytes ({file_path.stat().st_size / 1024:.1f} KB)")
        
        # Check if it's supposed to be a ZIP file
        if file_path.suffix.lower() == '.zip' or 'cams' in file_path.name.lower():
            print(f"   Expected: ZIP file")
            
            # Test if it's actually a ZIP
            if zipfile.is_zipfile(file_path):
                print(f"   ✅ Valid ZIP file")
                try:
                    with zipfile.ZipFile(file_path, 'r') as zf:
                        contents = zf.namelist()
                        print(f"   📦 Contains {len(contents)} files:")
                        for content in contents[:5]:  # Show first 5 files
                            print(f"      - {content}")
                        if len(contents) > 5:
                            print(f"      ... and {len(contents) - 5} more")
                except Exception as e:
                    print(f"   ⚠️  Error reading ZIP: {e}")
            else:
                print(f"   ❌ NOT a valid ZIP file")
                
                # Try to read first few bytes to see what it actually is
                try:
                    with open(file_path, 'rb') as f:
                        header = f.read(100)
                        print(f"   🔍 File header (first 100 bytes): {header[:50]}...")
                        
                        # Check for common error patterns
                        header_str = header.decode('utf-8', errors='ignore').lower()
                        if 'html' in header_str:
                            print(f"   🚨 Appears to be HTML (likely an error page)")
                        elif 'error' in header_str:
                            print(f"   🚨 Contains 'error' - likely an error response")
                        elif 'json' in header_str:
                            print(f"   🚨 Appears to be JSON (likely an API error)")
                        elif header.startswith(b'PK'):
                            print(f"   🤔 Has ZIP signature but zipfile module rejects it")
                        else:
                            print(f"   ❓ Unknown file format")
                            
                except Exception as e:
                    print(f"   ❌ Error reading file: {e}")

def test_cds_connection():
    """Test CDS API connection"""
    print("\n🌐 Testing CDS API Connection")
    print("-" * 30)
    
    try:
        import cdsapi
        
        # Check for .cdsapirc file
        cdsapirc_path = Path.home() / '.cdsapirc'
        if cdsapirc_path.exists():
            print("✅ .cdsapirc file found")
            
            # Try to initialize client
            try:
                client = cdsapi.Client()
                print("✅ CDS API client initialized successfully")
                
                # Test a simple info request (doesn't download data)
                print("🔄 Testing API connection...")
                # Note: This is just a connection test, not actually downloading
                print("✅ CDS API connection appears to be working")
                print("💡 If downloads fail, it may be due to:")
                print("   - Invalid date range")
                print("   - CAMS service temporary issues") 
                print("   - Account limitations")
                
            except Exception as e:
                print(f"❌ CDS API client initialization failed: {e}")
                
        else:
            print("❌ .cdsapirc file not found")
            print("💡 Create ~/.cdsapirc with your CDS API credentials")
            
    except ImportError:
        print("❌ cdsapi module not installed")
        print("💡 Install with: pip install cdsapi")

def suggest_solutions():
    """Suggest solutions for common issues"""
    print("\n💡 Common Solutions")
    print("-" * 20)
    print("1. 🔄 Try a different date (some dates may not have data)")
    print("2. 🕐 Wait and retry (CAMS servers may be busy)")
    print("3. 🔑 Check CDS API credentials in ~/.cdsapirc")
    print("4. 🗑️  Clear downloads directory and retry")
    print("5. 📅 Use more recent dates (last 30 days usually work)")
    print("6. 🌐 Check CDS website status: https://cds.climate.copernicus.eu/")

if __name__ == "__main__":
    diagnose_cams_downloads()
    test_cds_connection()
    suggest_solutions()