Update app.py

app.py

@@ -3,16 +3,18 @@ import os
 import asyncio
 import json
 import datetime
-import requests # For making HTTP requests to external APIs like Perplexity AI
+import re       # For regular expressions (used in voucher scraping)
 from dotenv import load_dotenv
 
+# --- Playwright Imports for Web Scraping ---
+from playwright.async_api import async_playwright
+
 # --- Langchain Imports ---
-# These libraries are essential for interacting with language models and parsing their outputs.
 from langchain_core.prompts import ChatPromptTemplate
 from langchain_core.output_parsers import JsonOutputParser
 from langchain_core.pydantic_v1 import BaseModel, Field
 from langchain_openai import ChatOpenAI
-from langchain_google_genai import ChatGoogleGenerativeAI # Kept for potential future use or redundancy
+from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_core.messages import SystemMessage, HumanMessage
 
 # Load environment variables from .env file (for local testing).
@@ -21,19 +23,12 @@ load_dotenv()
 
 # --- 1. API KEY CHECK ---
 # This block ensures that the necessary API keys are set before the application starts.
-# This makes the app "fail early" if a critical dependency is missing.
 try:
     openai_api_key = os.environ["OPENAI_API_KEY"]
 except KeyError:
-    # If the key is not found, an error is raised, prompting the user to set it up.
     raise EnvironmentError("Missing OPENAI_API_KEY. Please set it in a .env file locally, or in Hugging Face Space secrets.")
 
-# Perplexity AI API Key Check
-perplexity_api_key = None # Initialize to None
-try:
-    perplexity_api_key = os.environ["PERPLEXITY_API_KEY"]
-except KeyError:
-    print("Warning: PERPLEXITY_API_KEY not found. Perplexity AI web search will not function. Please add it to your .env file or Hugging Face Space secrets for live web search.")
+# Removed PERPLEXITY_API_KEY check as it's no longer used.
 
 
 # --- 2. PYDANTIC DATA STRUCTURE DEFINITION ---
@@ -79,95 +74,124 @@ async def search_get_your_guide(details):
 
 async def scrape_flight_vouchers(details):
     """
-    This function currently simulates searching for flight vouchers and promo codes.
-    You will implement real web crawling logic here using Playwright later.
-    """
-    print(f"Searching for flight vouchers related to: {details.get('destination_city', 'general travel')}")
-    await asyncio.sleep(4) # Simulate a longer crawl time due to web scraping complexity
-    return [{
-        "source": "VoucherSiteExample",
-        "type": "voucher",
-        "details": "20% off selected Summer Flights!",
-        "price": "N/A", # Vouchers typically don't have a direct price, but a discount amount/code
-        "link": "https://www.example-vouchers.com/summer-deal"
-    },
-    {
-        "source": "AirlineDeals",
-        "type": "voucher",
-        "details": "Flat $50 off on flights to Europe with code EUROFLY",
-        "price": "N/A",
-        "link": "https://www.airline-deals.com/europe-promo"
-    }]
-
-async def search_perplexity_web(details):
+    Performs real web scraping for flight vouchers and promo codes using Playwright.
+    This function navigates to common deal sites and attempts to extract voucher information.
+    Note: Web scraping is highly dependent on website structure and may require frequent updates.
     """
-    Performs a live web search using Perplexity AI API based on the user's travel request.
-    This demonstrates fetching real-time general information from the web.
-    """
-    if not perplexity_api_key:
-        return [] # Return an empty list if API key is not set.
-
-    search_query = (
-        f"Best travel tips for {details.get('destination_city', 'general travel')}. "
-        f"Budget: {details.get('budget_preference', 'any')}. "
-        f"Travel dates: {details.get('departure_date', 'any')} to {details.get('return_date', 'any')}. "
-        f"Interests: {details.get('activity_interests', 'any activities')}."
-    )
-
-    url = "https://api.perplexity.ai/chat/completions" # Perplexity AI's chat completions endpoint for web search
-    headers = {
-        "Authorization": f"Bearer {perplexity_api_key}",
-        "Content-Type": "application/json"
-    }
-    payload = {
-        "model": "llama-3-sonar-small-32k-online",
-        "messages": [
-            {"role": "system", "content": "You are a helpful assistant that performs web searches and provides concise, travel-related summaries or tips."},
-            {"role": "user", "content": search_query}
-        ],
-        "temperature": 0.2,
-        "max_tokens": 500
-    }
+    print(f"Starting real web scraping for flight vouchers related to: {details.get('destination_city', 'general travel')}")
+    vouchers_found = []
+    
+    # Define target websites. Removed Groupon due to persistent ERR_HTTP2_PROTOCOL_ERROR.
+    target_urls = [
+        "https://www.retailmenot.com/coupons/flights",
+    ]
 
-    print(f"Searching Perplexity AI for: '{search_query}'")
+    browser = None # Initialize browser variable outside the try block
     try:
-        response = await asyncio.to_thread(requests.post, url, headers=headers, json=payload, timeout=20)
-        response.raise_for_status()
-        data = response.json()
-
-        if data and data.get("choices") and data["choices"][0].get("message"):
-            content = data["choices"][0]["message"]["content"]
-            # Corrected to always return a list of dictionaries.
-            return [{
-                "source": "Perplexity AI Web Search",
-                "type": "insight",
-                "details": content,
-                "link": "https://www.perplexity.ai/"
-            }]
-        else:
-            print("Perplexity AI response was empty or malformed.")
-            return [] # Returns an empty list
-    except requests.exceptions.Timeout:
-        print("Perplexity AI request timed out after 20 seconds.")
-        # Corrected to always return a list of dictionaries.
-        return [{"source": "Perplexity AI Web Search", "type": "insight", "details": "Web search timed out. Please try again.", "link": "https://www.perplexity.ai/"}]
-    except requests.exceptions.RequestException as e:
-        print(f"Error calling Perplexity AI: {e}")
-        # Corrected to always return a list of dictionaries.
-        return [{"source": "Perplexity AI Web Search", "type": "insight", "details": f"Failed to get web insights: {e}", "link": "https://www.perplexity.ai/"}]
+        async with async_playwright() as p:
+            # Launch a headless Chromium browser (runs in the background without a visual window).
+            browser = await p.chromium.launch(headless=True)
+            
+            # Add a human-like User-Agent to try and bypass basic bot detection.
+            context = await browser.new_context(
+                user_agent="Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
+            )
+            page = await context.new_page()
+
+            for url in target_urls:
+                try:
+                    print(f"Navigating to: {url}")
+                    # Use 'domcontentloaded' or 'load' as 'networkidle' can sometimes wait indefinitely.
+                    await page.goto(url, wait_until='domcontentloaded', timeout=60000) 
+
+                    # --- Generic scraping strategy ---
+                    deals_locator = page.locator('div:has-text("coupon code"), div:has-text("promo code"), div:has-text("discount"), '
+                                                 'a[href*="deal"], a[href*="promo"], a[href*="discount"], '
+                                                 '[class*="deal"], [class*="promo"]')
+                    
+                    deals = await deals_locator.all()
+
+                    for i, deal_elem in enumerate(deals):
+                        if len(vouchers_found) >= 3: # Limit the number of vouchers found
+                            break
+                        try:
+                            text_content = await deal_elem.inner_text()
+                            link = await deal_elem.get_attribute('href') if await deal_elem.get_attribute('href') else url
+                            
+                            if len(text_content.strip()) > 20 and \
+                                ("flight" in text_content.lower() or \
+                                 "travel" in text_content.lower() or \
+                                 details.get('destination_city', '').lower() in text_content.lower()):
+                                
+                                code_match = re.search(r'\b[A-Z0-9]{4,10}\b', text_content)
+                                code = code_match.group(0) if code_match else "N/A"
+
+                                vouchers_found.append({
+                                    "source": f"Scraped from {url.split('/')[2]}",
+                                    "type": "voucher",
+                                    "details": f"{text_content[:150]}..." if len(text_content) > 150 else text_content,
+                                    "price": f"Code: {code}",
+                                    "link": link
+                                })
+                        except Exception as e_deal:
+                            print(f"Error processing deal element on {url}: {e_deal}")
+                            continue
+                except Exception as e_url_nav: # Catching general Exception for Playwright errors
+                    print(f"Navigation error for {url}: {e_url_nav}")
+                    vouchers_found.append({
+                        "source": f"Scraper Error for {url.split('/')[2]}",
+                        "type": "voucher",
+                        "details": f"Could not retrieve vouchers from {url.split('/')[2]} due to navigation error. (Error: {e_url_nav})",
+                        "price": "N/A",
+                        "link": url
+                    })
+                    continue
+    except Exception as e_browser_launch: # Catching general Exception for browser launch errors
+        print(f"Playwright browser launch error: {e_browser_launch}. Ensure `playwright install` was run.")
+        return [{
+            "source": "Scraper Initialization Error",
+            "type": "voucher",
+            "details": f"Failed to start web scraper: {e_browser_launch}. Please ensure Playwright browsers are installed locally and on Hugging Face.",
+            "price": "N/A",
+            "link": "#"
+        }]
+    except Exception as e_general:
+        print(f"An unexpected error occurred during scraping: {e_general}")
+        return [{
+            "source": "Scraper General Error",
+            "type": "voucher",
+            "details": f"An unexpected error prevented voucher scraping: {e_general}",
+            "price": "N/A",
+            "link": "#"
+        }]
+    finally:
+        if browser:
+            await browser.close()
+    
+    if not vouchers_found:
+        print("No specific vouchers found during scraping.")
+        return [{
+            "source": "Web Scraping",
+            "type": "voucher",
+            "details": "No specific flight vouchers or codes were found matching your criteria on the browsed sites.",
+            "price": "N/A",
+            "link": "#"
+        }]
+    return vouchers_found
+
+
+# search_perplexity_web function is removed
 
 
 async def search_llm_redundancy(details, llm, llm_name):
     """
     Queries another LLM for additional, general travel ideas or insights.
-    This function was the main cause of the TypeError, now fixed to return a list.
     """
     print(f"Querying {llm_name} for additional ideas...")
     prompt = f"""As a helpful travel assistant, provide some brief travel suggestions for a trip based on these details: {details}.
     Focus on general tips, hidden gems, or activity ideas. Do not suggest specific prices or flights."""
     messages = [SystemMessage(content=prompt), HumanMessage(content="What are your suggestions?")]
     response = await llm.ainvoke(messages)
-    # FIX: Ensure this always returns a list of dictionaries, even if it's just one item.
     return [{"source": llm_name, "type": "insight", "details": response.content}]
 
 # --- 4. MAIN BOT LOGIC (ask_bot function) ---
@@ -202,9 +226,9 @@ async def ask_bot(question):
         search_expedia(structured_request),             # Hotel search task (simulated)
         scrape_Google_Flights(structured_request),      # Another flight source task (simulated scraping)
         search_get_your_guide(structured_request),      # Activities search task (simulated)
-        scrape_flight_vouchers(structured_request),     # Flight voucher search task (simulated)
+        scrape_flight_vouchers(structured_request),     # NEW: Live Flight voucher search task (Playwright)
         search_llm_redundancy(structured_request, llm_openai_creative, "ChatGPT (Creative)"), # AI insights from OpenAI (LIVE)
-        search_perplexity_web(structured_request)       # Live Web Search from Perplexity AI (LIVE if key set)
+        # search_perplexity_web(structured_request)       # Removed Perplexity AI task
         # search_llm_redundancy(structured_request, llm_gemini_search, "Gemini"), # Uncomment for Gemini insights
     ]
 
@@ -216,8 +240,8 @@ async def ask_bot(question):
     for res in results:
         if isinstance(res, Exception):
             print(f"A search task failed: {res}")
-        elif res: # This 'elif res' checks if res is not None and not empty.
-            all_results.extend(res) # res must be an iterable (like a list)
+        elif res:
+            all_results.extend(res)
 
     flights = sorted([r for r in all_results if r['type'] == 'flight'], key=lambda x: x['price'])
     hotels = sorted([r for r in all_results if r['type'] == 'hotel'], key=lambda x: x['price'])
@@ -272,7 +296,7 @@ async def ask_bot(question):
         output_text += "_No specific flight vouchers or codes found at this time._\n"
     output_text += "\n"
 
-    # Format AI Insights section (from redundant LLMs, now including Perplexity AI)
+    # Format AI Insights section (from redundant LLMs)
     output_text += "### 💡 Additional AI Insights (for Redundancy)\n"
     if insights:
         for insight in insights:
@@ -289,8 +313,8 @@ async def ask_bot(question):
 with gr.Blocks(theme=gr.themes.Soft()) as iface:
     gr.Markdown(
         """
-        # ✨ The Ultimate Global Travel Planner Bot ✨
-        Your smart AI assistant for finding the best flights, hotels, and activities worldwide!
+        # ✨ The Ultimate Global Travel Planner Bot - Bazinga Edition ✨
+        Your smart AI assistant for finding the best flights, hotels, and activities worldwide BAZINGA!
         """
     )
     with gr.Row():