feat: Enhanced CE schema and Notion sync (Pains/Gains)

2026-02-17 19:44:42 +00:00
parent d2e9ee2a70
commit 42bbcd1425
16 changed files with 1731 additions and 3 deletions
--- a/run_lead_engine.py
+++ b/run_lead_engine.py
@@ -0,0 +1,102 @@
+import argparse
+import subprocess
+import os
+import sys
+from datetime import datetime
+
+# --- Setup Paths ---
+SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__))
+SCRIPTS_SUBDIR = os.path.join(SCRIPT_DIR, "scripts")
+LOG_DIR = os.path.join(SCRIPT_DIR, "logs")
+THROUGHPUT_LOG = os.path.join(LOG_DIR, "throughput.log")
+
+# Add scripts subdir to path to allow imports
+sys.path.append(SCRIPTS_SUBDIR)
+
+# TODO: Import other modules once they are ready
+# from company_explorer_connector import handle_company_workflow
+# from generate_sniper_copy import generate_copy
+
+def setup_environment():
+    """Ensures necessary directories exist."""
+    os.makedirs(LOG_DIR, exist_ok=True)
+
+def log_throughput(identifier):
+    """Logs a successful processing event for the dashboard."""
+    with open(THROUGHPUT_LOG, "a") as f:
+        f.write(f"{datetime.utcnow().isoformat()},{identifier}\n")
+    print(f"📈 Logged successful processing for '{identifier}' for dashboard.")
+
+def run_sync():
+    """Runs the database sync script to ensure local data is fresh."""
+    print("\n--- [Step 1: Syncing local Company Explorer database] ---")
+    sync_script_path = os.path.join(SCRIPTS_SUBDIR, "sync_ce_to_sqlite.py")
+    
+    if not os.path.exists(sync_script_path):
+        print(f"❌ ERROR: Sync script not found at {sync_script_path}")
+        return False
+
+    result = subprocess.run(["python3", sync_script_path], capture_output=True, text=True, check=False)
+    
+    if result.returncode != 0:
+        print("❌ ERROR: Database sync failed.")
+        print(result.stderr)
+        return False
+        
+    print("✅ Sync successful.")
+    return True
+
+def process_lead(identifier):
+    """
+    Orchestrates the full enrichment and copy generation for a single lead.
+    """
+    print(f"\n======= PROCESSING LEAD: {identifier} =======")
+    
+    # --- Step 2: Enrich Company (if necessary) ---
+    print("\n--- [Step 2: Check/Enrich Company Data] ---")
+    # ce_data = handle_company_workflow(identifier) # Example of direct import
+    # if not ce_data or 'error' in ce_data:
+    #     print(f"❌ Failed to enrich '{identifier}'. Aborting.")
+    #     return
+    print("... (Placeholder for Enrichment Logic)")
+    print("✅ Enrichment complete.")
+
+
+    # --- Step 3: Generate Sniper Copy ---
+    print("\n--- [Step 3: Generate Sniper Copy] ---")
+    # sniper_copy = generate_copy(ce_data['data']['id'])
+    # print("\nGENERATED COPY:\n", sniper_copy)
+    print("... (Placeholder for Sniper Copy Generation)")
+    print("✅ Copy generation complete.")
+    
+    # --- Step 4: Finalize & Log ---
+    print("\n--- [Step 4: Finalizing] ---")
+    log_throughput(identifier)
+    print(f"✅ Successfully processed lead '{identifier}'.")
+    print("============================================")
+
+
+def main():
+    parser = argparse.ArgumentParser(description="GTM Lead Engine Orchestrator.")
+    parser.add_argument("leads", nargs='+', help="One or more company names or SuperOffice IDs to process.")
+    parser.add_argument("--skip-sync", action="store_true", help="Skip the initial database sync for faster iteration.")
+    args = parser.parse_args()
+
+    print("🚀 GTM Lead Engine Orchestrator started.")
+    
+    setup_environment()
+
+    if not args.skip_sync:
+        if not run_sync():
+            sys.exit(1) # Exit if sync fails
+    else:
+        print("\n--- [Skipping Step 1: Database Sync] ---")
+
+    for lead_identifier in args.leads:
+        process_lead(lead_identifier)
+        
+    print("\n🎉 Orchestration complete for all leads. 🎉")
+
+
+if __name__ == "__main__":
+    main()