Brancheneinstufung2/lead-engine/trading_twins_ingest.py

import os
import sys
import re
import logging
import requests
import json
from datetime import datetime
from dotenv import load_dotenv

# Ensure we can import from root directory
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))

# Import db functions
try:
    from db import insert_lead, init_db
except ImportError:
    # Fallback for direct execution
    sys.path.append(os.path.dirname(__file__))
    from db import insert_lead, init_db

# Configuration
env_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', '.env'))
load_dotenv(dotenv_path=env_path, override=True)

CLIENT_ID = os.getenv("INFO_Application_ID")
TENANT_ID = os.getenv("INFO_Tenant_ID")
CLIENT_SECRET = os.getenv("INFO_Secret")
USER_EMAIL = "info@robo-planet.de"

# Setup logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

def get_access_token():
    url = f"https://login.microsoftonline.com/{TENANT_ID}/oauth2/v2.0/token"
    data = {
        "client_id": CLIENT_ID,
        "scope": "https://graph.microsoft.com/.default",
        "client_secret": CLIENT_SECRET,
        "grant_type": "client_credentials"
    }
    response = requests.post(url, data=data)
    response.raise_for_status()
    return response.json().get("access_token")

def fetch_tradingtwins_emails(token, limit=200):
    url = f"https://graph.microsoft.com/v1.0/users/{USER_EMAIL}/messages"
    headers = {
        "Authorization": f"Bearer {token}",
        "Content-Type": "application/json"
    }
    
    # Graph API restriction: 'contains' on subject is often blocked.
    # Strategy: Fetch metadata + body for last 200 messages and filter client-side.
    params = {
        "$top": limit,
        "$select": "id,subject,receivedDateTime,body",
        "$orderby": "receivedDateTime desc"
    }
    
    response = requests.get(url, headers=headers, params=params)
    if response.status_code != 200:
        logger.error(f"Graph API Error: {response.status_code} - {response.text}")
        return []
    
    all_msgs = response.json().get("value", [])
    
    # Filter strictly for the subject pattern locally
    # Handle case where subject might be None
    filtered = [m for m in all_msgs if "Neue Anfrage zum Thema Roboter" in (m.get('subject') or '')]
    return filtered

def parse_tradingtwins_html(html_body):
    """
    Extracts data from the Tradingtwins HTML table structure.
    Pattern: <p ...>Label:</p>...<p ...>Value</p>
    """
    data = {}
    
    # Map label names in HTML to our keys
    field_map = {
        'Firma': 'company',
        'Vorname': 'contact_first', # Key fixed to match ingest.py logic
        'Nachname': 'contact_last', # Key fixed to match ingest.py logic
        'E-Mail': 'email',
        'Rufnummer': 'phone',
        'Einsatzzweck': 'purpose', # Specific field
        'Reinigungs-Fläche': 'area', # Specific field
        'PLZ': 'zip',
        'Stadt': 'city',
        'Lead-ID': 'source_id' # Mapped to DB column source_id
    }
    
    for label, key in field_map.items():
        pattern = fr'>\s*{re.escape(label)}:\s*</p>.*?<p[^>]*>(.*?)</p>'
        match = re.search(pattern, html_body, re.DOTALL | re.IGNORECASE)
        if match:
            raw_val = match.group(1).strip()
            clean_val = re.sub(r'<[^>]+>', '', raw_val).strip()
            data[key] = clean_val
            
    # Composite fields
    if data.get('contact_first') and data.get('contact_last'):
        data['contact'] = f"{data['contact_first']} {data['contact_last']}"
    
    # Ensure source_id is present and map to 'id' for db.py compatibility
    if not data.get('source_id'):
         data['source_id'] = f"tt_unknown_{int(datetime.now().timestamp())}"
    
    data['id'] = data['source_id'] # db.py expects 'id' for source_id column

    return data

def process_leads(auto_sync=True):
    init_db()
    new_count = 0
    try:
        token = get_access_token()
        emails = fetch_tradingtwins_emails(token)
        logger.info(f"Found {len(emails)} Tradingtwins emails.")
        
        for email in emails:
            # ... (parsing logic remains same)
            body = email.get('body', {}).get('content', '')
            received_at_str = email.get('receivedDateTime')
            
            # Convert ISO string to datetime object
            received_at = None
            if received_at_str:
                try:
                    received_at = datetime.fromisoformat(received_at_str.replace('Z', '+00:00'))
                except:
                    pass

            lead_data = parse_tradingtwins_html(body)
            lead_data['raw_body'] = body
            lead_data['received_at'] = received_at
            
            company_name = lead_data.get('company')
            if not company_name or company_name == '-':
                company_name = lead_data.get('contact')
                lead_data['company'] = company_name
            
            if not company_name:
                continue
                
            lead_data['id'] = lead_data.get('source_id') or f"tt_{int(datetime.now().timestamp())}"
            
            if insert_lead(lead_data):
                logger.info(f" -> Ingested: {company_name}")
                new_count += 1
        
        if new_count > 0 and auto_sync:
            logger.info(f"Triggering auto-sync for {new_count} new leads...")
            from enrich import run_sync
            run_sync()
                 
        return new_count
            
    except Exception as e:
        logger.error(f"Error in process_leads: {e}")
        return 0

if __name__ == "__main__":
    count = process_leads()
    print(f"Ingested {count} new leads.")