Upload app.py with huggingface_hub

app.py

@@ -3,6 +3,85 @@ import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import json
 import os
+import requests
+import re
+
+# Function to extract text from HTML (from shopping_assistant.py)
+def extract_text_from_html(html):
+    """
+    Extract text from HTML without using BeautifulSoup
+    """
+    # Remove HTML tags
+    text = re.sub(r'<[^>]+>', ' ', html)
+    # Remove extra whitespace
+    text = re.sub(r'\s+', ' ', text)
+    # Decode HTML entities
+    text = text.replace('&nbsp;', ' ').replace('&amp;', '&').replace('&lt;', '<').replace('&gt;', '>')
+    return text.strip()
+
+# Function to fetch deals from DealsFinders.com (from shopping_assistant.py)
+def fetch_deals_data(url="https://www.dealsfinders.com/wp-json/wp/v2/posts", num_pages=2, per_page=100):
+    """
+    Fetch deals data exclusively from the DealsFinders API
+    """
+    all_deals = []
+    
+    # Fetch from the DealsFinders API
+    for page in range(1, num_pages + 1):
+        try:
+            # Add a user agent to avoid being blocked
+            headers = {
+                'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.114 Safari/537.36'
+            }
+            response = requests.get(f"{url}?page={page}&per_page={per_page}", headers=headers)
+            
+            if response.status_code == 200:
+                deals = response.json()
+                all_deals.extend(deals)
+                print(f"Fetched page {page} with {len(deals)} deals from DealsFinders API")
+                
+                # If we get fewer deals than requested, we've reached the end
+                if len(deals) < per_page:
+                    print(f"Reached the end of available deals at page {page}")
+                    break
+            else:
+                print(f"Failed to fetch page {page} from DealsFinders API: {response.status_code}")
+                break
+        except Exception as e:
+            print(f"Error fetching page {page} from DealsFinders API: {str(e)}")
+            break
+    
+    return all_deals
+
+# Function to process deals data (from shopping_assistant.py)
+def process_deals_data(deals_data):
+    """
+    Process the deals data into a structured format
+    """
+    processed_deals = []
+    
+    for deal in deals_data:
+        try:
+            # Extract relevant information using our HTML text extractor
+            content_html = deal.get('content', {}).get('rendered', '')
+            excerpt_html = deal.get('excerpt', {}).get('rendered', '')
+            
+            clean_content = extract_text_from_html(content_html)
+            clean_excerpt = extract_text_from_html(excerpt_html)
+            
+            processed_deal = {
+                'id': deal.get('id'),
+                'title': deal.get('title', {}).get('rendered', ''),
+                'link': deal.get('link', ''),
+                'date': deal.get('date', ''),
+                'content': clean_content,
+                'excerpt': clean_excerpt
+            }
+            processed_deals.append(processed_deal)
+        except Exception as e:
+            print(f"Error processing deal: {str(e)}")
+    
+    return processed_deals
 
 # Load the model and tokenizer
 model_path = os.path.dirname(os.path.abspath(__file__))
@@ -17,11 +96,16 @@ except Exception as e:
     print(f"Error loading categories: {str(e)}")
     categories = ["electronics", "clothing", "home", "kitchen", "toys", "other"]
 
-def classify_text(text):
+# Global variable to store deals data
+deals_cache = None
+
+def classify_text(text, fetch_deals=True):
     """
-    Classify the text using the model
+    Classify the text using the model and fetch relevant deals
     """
-    # Prepare the input
+    global deals_cache
+    
+    # Prepare the input for classification
     inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
     
     # Get the model prediction
@@ -38,31 +122,73 @@ def classify_text(text):
     # Sort by score
     top_categories.sort(key=lambda x: x[1], reverse=True)
     
-    # Format the results
+    # Format the classification results
     if top_categories:
         result = f"Top categories for '{text}':\n\n"
         for category, score in top_categories:
             result += f"- {category}: {score:.4f}\n"
         
-        result += f"\nBased on your query, I would recommend looking for deals in the **{top_categories[0][0]}** category."
+        result += f"\nBased on your query, I would recommend looking for deals in the **{top_categories[0][0]}** category.\n\n"
     else:
-        result = f"No categories found for '{text}'. Please try a different query."
+        result = f"No categories found for '{text}'. Please try a different query.\n\n"
+    
+    # Fetch and display deals if requested
+    if fetch_deals:
+        result += "## Relevant Deals from DealsFinders.com\n\n"
+        
+        try:
+            # Fetch deals data if not already cached
+            if deals_cache is None:
+                deals_data = fetch_deals_data(num_pages=2)  # Limit to 2 pages for faster response
+                deals_cache = process_deals_data(deals_data)
+            
+            # Search for relevant deals
+            query_terms = text.lower().split()
+            relevant_deals = []
+            
+            for deal in deals_cache:
+                title = deal['title'].lower()
+                content = deal['content'].lower()
+                excerpt = deal['excerpt'].lower()
+                
+                # Check if any query term is in the deal information
+                if any(term in title or term in content or term in excerpt for term in query_terms):
+                    relevant_deals.append(deal)
+            
+            # Limit to top 5 most relevant deals
+            relevant_deals = relevant_deals[:5]
+            
+            if relevant_deals:
+                for i, deal in enumerate(relevant_deals, 1):
+                    result += f"{i}. [{deal['title']}]({deal['link']})\n\n"
+            else:
+                result += "No specific deals found for your query. Try a different search term or browse the recommended category.\n\n"
+        
+        except Exception as e:
+            result += f"Error fetching deals: {str(e)}\n\n"
     
     return result
 
 # Create the Gradio interface
 demo = gr.Interface(
     fn=classify_text,
-    inputs=gr.Textbox(
-        lines=2, 
-        placeholder="Enter your shopping query here...",
-        label="Shopping Query"
-    ),
+    inputs=[
+        gr.Textbox(
+            lines=2, 
+            placeholder="Enter your shopping query here...",
+            label="Shopping Query"
+        ),
+        gr.Checkbox(
+            label="Fetch Deals",
+            value=True,
+            info="Check to fetch and display deals from DealsFinders.com"
+        )
+    ],
     outputs=gr.Markdown(label="Results"),
     title="Shopping Assistant",
     description="""
-    This demo shows how to use the Shopping Assistant model to classify shopping queries into categories.
-    Enter a shopping query below to see which categories it belongs to.
+    This demo shows how to use the Shopping Assistant model to classify shopping queries into categories and find relevant deals.
+    Enter a shopping query below to see which categories it belongs to and find deals from DealsFinders.com.
     
     Examples:
     - "I'm looking for headphones"
@@ -71,10 +197,11 @@ demo = gr.Interface(
     - "I need a new smart TV"
     """,
     examples=[
-        ["I'm looking for headphones"],
-        ["Do you have any kitchen appliance deals?"],
-        ["Show me the best laptop deals"],
-        ["I need a new smart TV"]
+        ["I'm looking for headphones", True],
+        ["Do you have any kitchen appliance deals?", True],
+        ["Show me the best laptop deals", True],
+        ["I need a new smart TV", True],
+        ["headphone deals", True]
     ],
     theme=gr.themes.Soft()
 )