feat(company-explorer): add impressum scraping, robust json parsing, and enhanced ui polling

- Implemented Impressum scraping with Root-URL fallback and enhanced keyword detection.
- Added 'clean_json_response' helper to strip Markdown from LLM outputs, preventing JSONDecodeErrors.
- Improved numeric extraction for German formatting (thousands separators vs decimals).
- Updated Inspector UI with Polling logic for auto-refresh and display of AI Dossier and Legal Data.
- Added Manual Override for Website URL.

company-explorer/backend/services/classification.py

@@ -2,7 +2,7 @@ import json
 import logging
 import os
 from typing import Dict, Any, List
-from ..lib.core_utils import call_gemini
+from ..lib.core_utils import call_gemini, clean_json_response
 from ..config import settings
 from ..database import SessionLocal, RoboticsCategory
 
@@ -55,7 +55,7 @@ class ClassificationService:
 
         prompt = f"""
         You are a Senior B2B Market Analyst for 'Roboplanet', a specialized robotics distributor.
-        Your task is to analyze a target company based on their website text to determine their **operational need** for service robotics.
+        Your task is to analyze the target company based on their website text and create a concise **Dossier**.
 
         --- TARGET COMPANY ---
         Name: {company_name}
@@ -66,36 +66,33 @@ class ClassificationService:
         You MUST assign the company to exactly ONE of these industries. If unsure, choose the closest match or "Sonstige".
         {json.dumps(self.allowed_industries, ensure_ascii=False)}
 
-        --- ANALYSIS GUIDELINES (CHAIN OF THOUGHT) ---
-        1. **Infrastructure Analysis:** What physical assets does this company likely operate based on their business model? 
-           - Factories / Production Plants? (-> Needs Cleaning, Security, Intralogistics)
-           - Large Warehouses? (-> Needs Intralogistics, Security, Floor Washing)
-           - Offices / Headquarters? (-> Needs Vacuuming, Window Cleaning)
-           - Critical Infrastructure (Solar Parks, Wind Farms)? (-> Needs Perimeter Security, Inspection)
-           - Hotels / Hospitals? (-> Needs Service, Cleaning, Transport)
-        
-        2. **Provider vs. User Distinction (CRITICAL):**
-           - If a company SELLS cleaning products (e.g., 3M, Henkel), they do NOT necessarily have a higher need for cleaning robots than any other manufacturer. Do not score them high just because the word "cleaning" appears. Score them based on their *factories*.
-           - If a company SELLS security services, they might be a potential PARTNER, but check if they *manage* sites.
-        
-        3. **Scale Assessment:** 
-           - 5 locations implies more need than 1. 
-           - "Global player" implies large facilities.
+        --- ANALYSIS PART 1: BUSINESS MODEL ---
+        1. Identify the core products/services.
+        2. Summarize in 2-3 German sentences: What do they do and for whom? (Target: "business_model")
 
-        --- SCORING CATEGORIES (0-100) ---
-        Based on the current strategic focus of Roboplanet:
+        --- ANALYSIS PART 2: INFRASTRUCTURE & POTENTIAL (Chain of Thought) ---
+        1. **Infrastructure Scan:** Look for evidence of physical assets like *Factories, Large Warehouses, Production Lines, Campuses, Hospitals*.
+        2. **Provider vs. User Check:** 
+           - Does the company USE this infrastructure (Potential Customer)?
+           - Or do they SELL products for it (Competitor/Partner)? 
+           - *Example:* "Cleaning" -> Do they sell soap (Provider) or do they have a 50,000sqm factory (User)?
+        3. **Evidence Extraction:** Extract 1-2 key sentences from the text proving this infrastructure. (Target: "infrastructure_evidence")
+
+        --- ANALYSIS PART 3: SCORING (0-100) ---
+        Based on the identified infrastructure, score the potential for these categories:
         
         {category_guidance}
 
         --- OUTPUT FORMAT (JSON ONLY) ---
         {{
             "industry": "String (from list)",
-            "summary": "Concise analysis of their infrastructure and business model (German)",
+            "business_model": "2-3 sentences summary (German)",
+            "infrastructure_evidence": "1-2 key sentences proving physical assets (German)",
             "potentials": {{
-                "cleaning": {{ "score": 0-100, "reason": "Specific reasoning based on infrastructure (e.g. 'Operates 5 production plants in DE')." }},
-                "transport": {{ "score": 0-100, "reason": "..." }},
-                "security": {{ "score": 0-100, "reason": "..." }},
-                "service": {{ "score": 0-100, "reason": "..." }}
+                "cleaning": {{ "score": 0-100, "reason": "Reasoning based on infrastructure." }},
+                "transport": {{ "score": 0-100, "reason": "Reasoning based on logistics volume." }},
+                "security": {{ "score": 0-100, "reason": "Reasoning based on perimeter/assets." }},
+                "service": {{ "score": 0-100, "reason": "Reasoning based on guest interaction." }}
             }}
         }}
         """
@@ -106,7 +103,7 @@ class ClassificationService:
                 json_mode=True,
                 temperature=0.1 # Very low temp for analytical reasoning
             )
-            return json.loads(response_text)
+            return json.loads(clean_json_response(response_text))
         except Exception as e:
             logger.error(f"Classification failed: {e}")
             return {"error": str(e)}