Implement manual JSON parsing for company profiles; enhance data extraction and processing efficiency; add comprehensive test script for validation

test_company_parser.py

@@ -0,0 +1,78 @@
+#!/usr/bin/env python3
+"""
+Test script for the company parser with manual JSON parsing.
+"""
+
+import asyncio
+import os
+import sys
+
+sys.path.insert(0, "/home/oluwasanmi/Documents/Work/MKD/anton_wireframe/app")
+
+import pandas as pd
+from dotenv import load_dotenv
+from services.llm_parser import InvestorProcessor
+
+# Load environment variables from root directory
+load_dotenv("/home/oluwasanmi/Documents/Work/MKD/anton_wireframe/.env")
+
+# Also check if API key is set (not needed for companies now but for consistency)
+if not os.getenv("OPENROUTER_API_KEY"):
+    print("⚠️  WARNING: OPENROUTER_API_KEY not found in environment")
+    print("This is OK for companies (no LLM needed), but will fail for investors")
+
+
+async def test_parser():
+    """Test the new company parser with a small sample"""
+    print("🧪 Testing Manual Company JSON Parser (No LLM)\n")
+
+    # Load the company data
+    df = pd.read_csv(
+        "/home/oluwasanmi/Documents/Work/MKD/anton_wireframe/data/300 Companies data.csv"
+    )
+
+    # Process just the first 3 rows for testing
+    test_df = df.head(3)
+
+    processor = InvestorProcessor()
+
+    print(f"Processing {len(test_df)} test companies...\n")
+    results = await processor.parse_companies(test_df, save_to_db=False)
+
+    print("\n" + "=" * 80)
+    print("📊 TEST RESULTS")
+    print("=" * 80)
+
+    for idx, result in enumerate(results, 1):
+        print(f"\n{idx}. {result.get('name')}")
+        print(f"   Website: {result.get('website')}")
+        print(f"   Location: {result.get('location')}")
+        print(f"   Industry: {result.get('industry')}")
+        print(
+            f"   Founded: {result.get('founded_year')}"
+            if result.get("founded_year")
+            else "   Founded: Unknown"
+        )
+        print(f"   Executives: {len(result.get('key_executives', []))}")
+        if result.get("key_executives"):
+            for exec_member in result.get("key_executives", [])[:3]:  # Show first 3
+                print(f"      - {exec_member.get('name')} ({exec_member.get('title')})")
+        print(f"   Investors: {len(result.get('investor_names', []))}")
+        if result.get("investor_names"):
+            print(
+                f"      - {', '.join(result.get('investor_names', [])[:5])}"
+            )  # Show first 5
+        print(f"   Client Categories: {len(result.get('client_categories', []))}")
+        if result.get("client_categories"):
+            print(
+                f"      - {', '.join(result.get('client_categories', [])[:3])}"
+            )  # Show first 3
+
+    print("\n" + "=" * 80)
+    print(f"✅ Successfully processed {len(results)}/{len(test_df)} companies")
+    print("🎉 No LLM calls needed - 100% manual parsing!")
+    print("=" * 80)
+
+
+if __name__ == "__main__":
+    asyncio.run(test_parser())