Brancheneinstufung2/company-explorer/backend/scripts/sync_notion_industries.py

import sys
import os
import requests
import json
import logging

# Add company-explorer to path (parent of backend)
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "../..")))

from backend.database import SessionLocal, Industry, RoboticsCategory, init_db
from backend.config import settings

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

NOTION_TOKEN_FILE = "/app/notion_token.txt"
INDUSTRIES_DB_ID = "2ec88f4285448014ab38ea664b4c2b81"
CATEGORIES_DB_ID = "2ec88f42854480f0b154f7a07342eb58"

def load_notion_token():
    try:
        with open(NOTION_TOKEN_FILE, "r") as f:
            return f.read().strip()
    except FileNotFoundError:
        logger.error(f"Notion token file not found at {NOTION_TOKEN_FILE}")
        sys.exit(1)

def query_notion_db(token, db_id):
    url = f"https://api.notion.com/v1/databases/{db_id}/query"
    headers = {
        "Authorization": f"Bearer {token}",
        "Notion-Version": "2022-06-28",
        "Content-Type": "application/json"
    }
    results = []
    has_more = True
    next_cursor = None
    
    while has_more:
        payload = {}
        if next_cursor:
            payload["start_cursor"] = next_cursor
            
        response = requests.post(url, headers=headers, json=payload)
        if response.status_code != 200:
            logger.error(f"Error querying Notion DB {db_id}: {response.text}")
            break
            
        data = response.json()
        results.extend(data.get("results", []))
        has_more = data.get("has_more", False)
        next_cursor = data.get("next_cursor")
        
    return results

def extract_rich_text(prop):
    if not prop: return ""
    return "".join([t.get("plain_text", "") for t in prop.get("rich_text", [])])

def extract_title(prop):
    if not prop: return ""
    return "".join([t.get("plain_text", "") for t in prop.get("title", [])])

def extract_select(prop):
    if not prop: return ""
    return prop.get("select", {}).get("name", "") if prop.get("select") else ""

def extract_number(prop):
    if not prop: return None
    return prop.get("number")

def sync_categories(token, session):
    logger.info("Syncing Robotics Categories...")
    # session.query(RoboticsCategory).delete() # DANGEROUS - Reverted to Upsert
    # session.commit()

    pages = query_notion_db(token, CATEGORIES_DB_ID)
    
    count = 0
    for page in pages:
        props = page.get("properties", {})
        
        notion_id = page["id"]
        name = extract_title(props.get("Name"))
        
        description = extract_rich_text(props.get("Text"))
        key = name.lower().replace(" ", "_") if name else "unknown"
        
        if not name: continue

        # Upsert Logic: Check ID -> Check Key -> Create
        cat = session.query(RoboticsCategory).filter(RoboticsCategory.notion_id == notion_id).first()
        if not cat:
            cat = session.query(RoboticsCategory).filter(RoboticsCategory.key == key).first()
            if cat:
                logger.info(f"Linked existing category '{key}' to Notion ID {notion_id}")
                cat.notion_id = notion_id
            else:
                cat = RoboticsCategory(notion_id=notion_id, key=key)
                session.add(cat)
        
        cat.name = name
        cat.description = description
        cat.reasoning_guide = extract_rich_text(props.get("Constrains"))
        
        count += 1
    
    session.commit()
    logger.info(f"Synced (Upsert) {count} categories.")

def sync_industries(token, session):
    logger.info("Syncing Industries...")
    logger.warning("DELETING all existing industries before sync...")
    session.query(Industry).delete()
    session.commit()

    pages = query_notion_db(token, INDUSTRIES_DB_ID)
    
    count = 0
    for page in pages:
        props = page.get("properties", {})
        
        notion_id = page["id"]
        # In Notion, the column is now 'Vertical' not 'Industry'
        name = extract_title(props.get("Vertical"))
        if not name: continue
        
        # Removed full Notion props debug log - no longer needed
        
        # Logic is now INSERT only
        industry = Industry(notion_id=notion_id, name=name)
        session.add(industry)
            
        # Map Fields from Notion Schema
        industry.name = name
        industry.description = extract_rich_text(props.get("Definition"))
        
        # New: Map Pains & Gains explicitly
        industry.pains = extract_rich_text(props.get("Pains"))
        industry.gains = extract_rich_text(props.get("Gains"))
        industry.notes = extract_rich_text(props.get("Notes"))
        
        status = extract_select(props.get("Status"))
        industry.status_notion = status
        industry.is_focus = (status == "P1 Focus Industry")
        
        # New Schema Fields
        industry.metric_type = extract_select(props.get("Metric Type"))
        industry.min_requirement = extract_number(props.get("Min. Requirement"))
        industry.whale_threshold = extract_number(props.get("Whale Threshold"))
        industry.proxy_factor = extract_number(props.get("Proxy Factor"))
        industry.scraper_search_term = extract_select(props.get("Scraper Search Term")) # <-- FIXED HERE
        industry.scraper_keywords = extract_rich_text(props.get("Scraper Keywords"))
        industry.standardization_logic = extract_rich_text(props.get("Standardization Logic"))
        
        # New Field: Ops Focus Secondary (Checkbox)
        industry.ops_focus_secondary = props.get("Ops Focus: Secondary", {}).get("checkbox", False)
        
        # New Field: Strategy Briefing (Miller Heiman)
        industry.strategy_briefing = extract_rich_text(props.get("Strategy Briefing"))

        # Relation: Primary Product Category
        relation = props.get("Primary Product Category", {}).get("relation", [])
        if relation:
            related_id = relation[0]["id"]
            cat = session.query(RoboticsCategory).filter(RoboticsCategory.notion_id == related_id).first()
            if cat:
                industry.primary_category_id = cat.id
            else:
                logger.warning(f"Related category {related_id} not found for industry {name}")
        
        # Relation: Secondary Product Category
        relation_sec = props.get("Secondary Product", {}).get("relation", [])
        if relation_sec:
            related_id = relation_sec[0]["id"]
            cat = session.query(RoboticsCategory).filter(RoboticsCategory.notion_id == related_id).first()
            if cat:
                industry.secondary_category_id = cat.id
            else:
                logger.warning(f"Related Secondary category {related_id} not found for industry {name}")
                
        count += 1
        
    session.commit()
    logger.info(f"Synced {count} industries.")

if __name__ == "__main__":
    token = load_notion_token()
    db = SessionLocal()
    
    try:
        # First ensure tables exist (in case of new DB)
        init_db()
        
        sync_categories(token, db)
        sync_industries(token, db)
    except Exception as e:
        logger.error(f"Sync failed: {e}", exc_info=True)
    finally:
        db.close()