Update product_recommender.py

product_recommender.py

@@ -1,41 +1,112 @@
-from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModelForTokenClassification
+from typing import Dict, List
+import requests
+from bs4 import BeautifulSoup
+import aiohttp
+import asyncio
+import json
 from sentence_transformers import SentenceTransformer
-import torch
 import numpy as np
-from typing import Dict, List, Optional
-import json
+import re
 
-class ProductRecommender:
+class DynamicRecommender:
     def __init__(self):
-        self.model_analyzer = MultiModelAnalyzer()
+        self.headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'
+        }
+        self.model = SentenceTransformer('all-mpnet-base-v2')
         
-    def get_recommendations(self, query: str, product_database: List[Dict]) -> List[Dict]:
+    async def search_amazon(self, query: str) -> List[Dict]:
+        """Search Amazon for products"""
+        search_url = f"https://www.amazon.in/s?k={query}"
+        async with aiohttp.ClientSession() as session:
+            async with session.get(search_url, headers=self.headers) as response:
+                if response.status == 200:
+                    html = await response.text()
+                    return self._parse_amazon_results(html)
+        return []
+    
+    async def search_flipkart(self, query: str) -> List[Dict]:
+        """Search Flipkart for products"""
+        search_url = f"https://www.flipkart.com/search?q={query}"
+        async with aiohttp.ClientSession() as session:
+            async with session.get(search_url, headers=self.headers) as response:
+                if response.status == 200:
+                    html = await response.text()
+                    return self._parse_flipkart_results(html)
+        return []
+
+    def _parse_amazon_results(self, html: str) -> List[Dict]:
+        soup = BeautifulSoup(html, 'html.parser')
+        products = []
+        for item in soup.select('.s-result-item'):
+            try:
+                name = item.select_one('.a-text-normal')
+                price = item.select_one('.a-price-whole')
+                if name and price:
+                    products.append({
+                        'name': name.text.strip(),
+                        'price': price.text.strip(),
+                        'source': 'Amazon',
+                        'url': 'https://amazon.in' + item.select_one('a')['href']
+                    })
+            except Exception:
+                continue
+        return products[:5]
+
+    def _parse_flipkart_results(self, html: str) -> List[Dict]:
+        soup = BeautifulSoup(html, 'html.parser')
+        products = []
+        for item in soup.select('._1AtVbE'):
+            try:
+                name = item.select_one('._4rR01T')
+                price = item.select_one('._30jeq3')
+                if name and price:
+                    products.append({
+                        'name': name.text.strip(),
+                        'price': price.text.strip(),
+                        'source': 'Flipkart',
+                        'url': 'https://flipkart.com' + item.select_one('a')['href']
+                    })
+            except Exception:
+                continue
+        return products[:5]
+
+    def _extract_keywords(self, text: str) -> List[str]:
+        """Extract relevant search keywords from input"""
+        age_match = re.search(r'age\s+(\d+)', text.lower())
+        age = age_match.group(1) if age_match else None
+
+        interests = []
+        if 'software' in text.lower() or 'engineer' in text.lower():
+            interests.extend(['programming books', 'tech gadgets'])
+        if 'books' in text.lower():
+            interests.append('books')
+        if 'successful' in text.lower():
+            interests.extend(['self help books', 'business books'])
+
+        return [f"{interest} for {age} year old" if age else interest for interest in interests]
+
+    async def get_recommendations(self, text: str) -> Dict:
+        """Get personalized recommendations"""
         try:
-            query_analysis = self.model_analyzer.analyze_text(query)
+            keywords = self._extract_keywords(text)
+            all_products = []
+            
+            for keyword in keywords:
+                amazon_products = await self.search_amazon(keyword)
+                flipkart_products = await self.search_flipkart(keyword)
+                all_products.extend(amazon_products + flipkart_products)
+            
+            # Remove duplicates and sort by relevance
+            seen = set()
+            unique_products = []
+            for product in all_products:
+                if product['name'] not in seen:
+                    seen.add(product['name'])
+                    unique_products.append(product)
+            
+            return unique_products[:5]
             
-            # For testing, return a simple recommendation
-            return [{
-                "name": "Test Product",
-                "price": "₹999",
-                "category": "test",
-                "similarity": 0.95
-            }]
         except Exception as e:
             print(f"Error in recommendations: {str(e)}")
-            return []
-
-class MultiModelAnalyzer:
-    def __init__(self):
-        try:
-            self.category_model = AutoModelForSequenceClassification.from_pretrained("bert-base-uncased")
-            self.category_tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased")
-            self.semantic_model = SentenceTransformer('paraphrase-MiniLM-L6-v2')
-        except Exception as e:
-            print(f"Error initializing models: {str(e)}")
-    
-    def analyze_text(self, text: str) -> Dict:
-        return {
-            "category": "test",
-            "embedding": np.zeros(10),
-            "features": ["test"]
-        }
+            return []