#!/usr/bin/env python3
"""
Fast-track verification: Upgrade Confirmed facilities with websites
These already have good data, just need final verification from their sites
"""

import csv
import json
from datetime import datetime

def load_facilities():
    with open('verified-scored-facilities.csv', 'r', encoding='utf-8') as f:
        return list(csv.DictReader(f))

def save_facilities(facilities):
    timestamp = datetime.now().strftime('%Y%m%d-%H%M%S')
    backup = f'verified-scored-facilities-BACKUP-{timestamp}.csv'
    
    # Backup
    with open('verified-scored-facilities.csv', 'r') as f:
        with open(backup, 'w') as bf:
            bf.write(f.read())
    
    # Save
    fieldnames = facilities[0].keys()
    with open('verified-scored-facilities.csv', 'w', encoding='utf-8', newline='') as f:
        writer = csv.DictWriter(f, fieldnames=fieldnames)
        writer.writeheader()
        writer.writerows(facilities)
    
    return backup

# Load data
facilities = load_facilities()

# Find Confirmed with websites
confirmed_with_websites = []
for f in facilities:
    if f['Confidence Level'] == 'Confirmed' and f.get('Website', 'N/A') not in ['N/A', '', 'Unknown']:
        confirmed_with_websites.append(f)

print(f"Found {len(confirmed_with_websites)} Confirmed facilities with websites")
print("\nReady for batch verification")
print("=" * 80)

# Export to JSON for easier processing
output_data = []
for f in confirmed_with_websites[:50]:  # First 50 for testing
    output_data.append({
        'company': f['Company'],
        'region': f['Region'],
        'website': f['Website'],
        'size': f.get('Size Classification', 'Unknown'),
        'rooms': f.get('Total Rooms', 'Unknown'),
        'sqft': f.get('Square Footage', 'Unknown'),
        'produce': f.get('Primary Produce', 'Unknown'),
        'current_source': f.get('Verification Source', 'Unknown'),
        'notes': f.get('Notes', '')
    })

with open('fast-track-batch-1.json', 'w') as f:
    json.dump(output_data, f, indent=2)

print("Exported first 50 to fast-track-batch-1.json")

# Show summary by state
from collections import Counter

def get_state(region):
    if ',' in region:
        return region.split(',')[-1].strip()
    elif ' - ' in region:
        parts = region.split(' - ')
        return parts[0].strip()
    return region

states = Counter([get_state(f['Region']) for f in confirmed_with_websites])
print("\n=== BY STATE ===")
for state, count in states.most_common(20):
    print(f"{state}: {count}")