import json
import csv
import re
import os

# Files from the previous step
files = [
    r'C:\Users\a931627\.gemini\antigravity\brain\6060ab5d-4406-4d40-803f-c8d1df8bb430\.system_generated\steps\219\output.txt',
    r'C:\Users\a931627\.gemini\antigravity\brain\6060ab5d-4406-4d40-803f-c8d1df8bb430\.system_generated\steps\220\output.txt',
    r'C:\Users\a931627\.gemini\antigravity\brain\6060ab5d-4406-4d40-803f-c8d1df8bb430\.system_generated\steps\221\output.txt',
    r'C:\Users\a931627\.gemini\antigravity\brain\6060ab5d-4406-4d40-803f-c8d1df8bb430\.system_generated\steps\222\output.txt',
    r'C:\Users\a931627\.gemini\antigravity\brain\6060ab5d-4406-4d40-803f-c8d1df8bb430\.system_generated\steps\223\output.txt'
]

output_csv = 'cologne_duesseldorf_data/duesseldorf_batch1.csv'
names = ["Baugewerbe", "Metall", "Dachdecker", "Elektro", "Sanitär"]

def parse_batch1():
    leads = []
    email_regex = re.compile(r'[\w\.-]+@[\w\.-]+\.\w+')
    
    for i, file_path in enumerate(files):
        try:
            with open(file_path, 'r', encoding='utf-8') as f:
                data = json.load(f)
                
            items = data.get('items', [])
            innung_name = names[i]
            
            found_email = False
            for item in items:
                if item.get('type') == 'organic':
                    desc = item.get('description', '')
                    title = item.get('title', '')
                    snippet = item.get('pre_snippet', '')
                    full_text = f"{title} {desc} {snippet}"
                    
                    emails = email_regex.findall(full_text)
                    for email in emails:
                        email = email.rstrip('.')
                        # Filter out trash
                        if email.endswith('png') or email.endswith('jpg') or 'datenschutz' in email:
                            continue
                            
                        # Avoid duplicates in this batch
                        if any(l['Email'] == email for l in leads):
                            continue
                            
                        leads.append({
                            'Firm/Innung': f"{innung_name} Düsseldorf",
                            'Contact': "N/A",
                            'Email': email,
                            'Phone': "N/A",
                            'Region': 'Düsseldorf'
                        })
                        found_email = True
                        break # Take first good email per Innung to avoid scraping junk
                if found_email:
                    break
        except Exception as e:
            print(f"Error parsing {file_path}: {e}")

    # Append to main list if exists, else match header
    with open(output_csv, 'w', newline='', encoding='utf-8') as f:
        writer = csv.DictWriter(f, fieldnames=['Firm/Innung', 'Contact', 'Email', 'Phone', 'Region'])
        writer.writeheader()
        writer.writerows(leads)
        
    print(f"Extracted {len(leads)} leads from Batch 1.")
    for l in leads:
        print(f"{l['Firm/Innung']}: {l['Email']}")

if __name__ == "__main__":
    parse_batch1()