Update app.py

app.py

@@ -1,9 +1,11 @@
+import logging
+import re
 from flask import Flask, request, render_template
 import requests
 from bs4 import BeautifulSoup
-import re
 
 app = Flask(__name__)
+logging.basicConfig(level=logging.DEBUG)
 
 def extract_price(price_str):
     """Extract a numeric value from a price string like '₹1,187'."""
@@ -22,99 +24,116 @@ def index():
 
     if request.method == 'POST':
         product_name = request.form.get('product')
+        app.logger.debug("Search initiated for product: %s", product_name)
         if product_name:
             # --------- AMAZON SCRAPING ----------- 
-            amazon_url = f"https://www.amazon.in/s?k={product_name.replace(' ', '+')}+for+farms"
+            amazon_url = f"https://www.amazon.in/s?k={product_name.replace(' ', '+')}"
             headers = {
-                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                              "AppleWebKit/537.36 (KHTML, like Gecko) "
-                              "Chrome/90.0.4430.212 Safari/537.36"
+                "User-Agent": ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                               "AppleWebKit/537.36 (KHTML, like Gecko) "
+                               "Chrome/90.0.4430.212 Safari/537.36")
             }
-            response_amazon = requests.get(amazon_url, headers=headers)
-            if response_amazon.status_code == 200:
-                soup_amazon = BeautifulSoup(response_amazon.text, 'html.parser')
-                products = soup_amazon.find_all("div", attrs={"data-csa-c-item-id": True})
-                for product in products:
-                    title_tag = product.find("h2", class_="a-size-base-plus")
-                    title = title_tag.get_text(strip=True) if title_tag else None
+            try:
+                response_amazon = requests.get(amazon_url, headers=headers, timeout=10)
+                app.logger.debug("Amazon response status: %s", response_amazon.status_code)
+                if response_amazon.status_code == 200:
+                    soup_amazon = BeautifulSoup(response_amazon.text, 'html.parser')
+                    products = soup_amazon.find_all("div", attrs={"data-csa-c-item-id": True})
+                    app.logger.debug("Found %d Amazon products", len(products))
+                    for product in products:
+                        title_tag = product.find("h2", class_="a-size-base-plus")
+                        title = title_tag.get_text(strip=True) if title_tag else None
 
-                    img_tag = product.find("img", class_="s-image")
-                    image_url = img_tag["src"] if img_tag and img_tag.has_attr("src") else ""
+                        img_tag = product.find("img", class_="s-image")
+                        image_url = img_tag["src"] if img_tag and img_tag.has_attr("src") else ""
 
-                    price = None
-                    price_tag = product.find("span", class_="a-price")
-                    if price_tag:
-                        offscreen = price_tag.find("span", class_="a-offscreen")
-                        if offscreen:
-                            price = offscreen.get_text(strip=True)
-                    
-                    product_url = None
-                    link_tag = product.find("a", class_="a-link-normal s-line-clamp-4 s-link-style a-text-normal")
-                    if link_tag and link_tag.has_attr("href"):
-                        product_url = link_tag["href"]
-                        if product_url.startswith("/"):
-                            product_url = "https://www.amazon.in" + product_url
+                        price = None
+                        price_tag = product.find("span", class_="a-price")
+                        if price_tag:
+                            offscreen = price_tag.find("span", class_="a-offscreen")
+                            if offscreen:
+                                price = offscreen.get_text(strip=True)
+                        
+                        product_url = None
+                        link_tag = product.find("a", class_="a-link-normal s-line-clamp-4 s-link-style a-text-normal")
+                        if link_tag and link_tag.has_attr("href"):
+                            product_url = link_tag["href"]
+                            if product_url.startswith("/"):
+                                product_url = "https://www.amazon.in" + product_url
+
+                        if not title or not price or not product_url:
+                            continue
+                        
+                        price_val = extract_price(price)
+                        
+                        amazon_list.append({
+                            "title": title,
+                            "image": image_url,
+                            "price": price,
+                            "url": product_url,
+                            "price_val": price_val
+                        })
+                        if len(amazon_list) >= 6:
+                            break
+                else:
+                    app.logger.debug("Failed to retrieve Amazon page")
+            except Exception as e:
+                app.logger.error("Error during Amazon scraping: %s", e)
 
-                    if not title or not price or not product_url:
-                        continue
-                    
-                    price_val = extract_price(price)
-                    
-                    amazon_list.append({
-                        "title": title,
-                        "image": image_url,
-                        "price": price,
-                        "url": product_url,
-                        "price_val": price_val
-                    })
-                    if len(amazon_list) >= 6:
-                        break
             amazon_list = sorted(amazon_list, key=lambda x: x['price_val'])[:6]
             
             # --------- FLIPKART SCRAPING ----------- 
-            flipkart_url = f"https://www.flipkart.com/search?q={product_name.replace(' ', '+')}+for+farms"
+            flipkart_url = f"https://www.flipkart.com/search?q={product_name.replace(' ', '+')}"
             headers_flip = {
-                "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
-                              "AppleWebKit/537.36 (KHTML, like Gecko) "
-                              "Chrome/90.0.4430.212 Safari/537.36"
+                "User-Agent": ("Mozilla/5.0 (Windows NT 10.0; Win64; x64) "
+                               "AppleWebKit/537.36 (KHTML, like Gecko) "
+                               "Chrome/90.0.4430.212 Safari/537.36")
             }
-            response_flip = requests.get(flipkart_url, headers=headers_flip)
-            if response_flip.status_code == 200:
-                soup_flip = BeautifulSoup(response_flip.text, 'html.parser')
-                flipkart_products = soup_flip.find_all("div", class_="slAVV4")
-                for product in flipkart_products:
-                    title_tag = product.find("a", class_="wjcEIp")
-                    title = title_tag.get_text(strip=True) if title_tag else None
-                    
-                    product_url = None
-                    if title_tag and title_tag.has_attr("href"):
-                        product_url = title_tag["href"]
-                        if product_url.startswith("/"):
-                            product_url = "https://www.flipkart.com" + product_url
-                    
-                    img_tag = product.find("img", class_="DByuf4")
-                    image_url = img_tag["src"] if img_tag and img_tag.has_attr("src") else ""
-                    
-                    price_tag = product.find("div", class_="Nx9bqj")
-                    price = price_tag.get_text(strip=True) if price_tag else None
+            try:
+                response_flip = requests.get(flipkart_url, headers=headers_flip, timeout=10)
+                app.logger.debug("Flipkart response status: %s", response_flip.status_code)
+                if response_flip.status_code == 200:
+                    soup_flip = BeautifulSoup(response_flip.text, 'html.parser')
+                    flipkart_products = soup_flip.find_all("div", class_="slAVV4")
+                    app.logger.debug("Found %d Flipkart products", len(flipkart_products))
+                    for product in flipkart_products:
+                        title_tag = product.find("a", class_="wjcEIp")
+                        title = title_tag.get_text(strip=True) if title_tag else None
+                        
+                        product_url = None
+                        if title_tag and title_tag.has_attr("href"):
+                            product_url = title_tag["href"]
+                            if product_url.startswith("/"):
+                                product_url = "https://www.flipkart.com" + product_url
+                        
+                        img_tag = product.find("img", class_="DByuf4")
+                        image_url = img_tag["src"] if img_tag and img_tag.has_attr("src") else ""
+                        
+                        price_tag = product.find("div", class_="Nx9bqj")
+                        price = price_tag.get_text(strip=True) if price_tag else None
+
+                        if not title or not price or not product_url:
+                            continue
+                        
+                        price_val = extract_price(price)
+                        
+                        flipkart_list.append({
+                            "title": title,
+                            "image": image_url,
+                            "price": price,
+                            "url": product_url,
+                            "price_val": price_val
+                        })
+                        if len(flipkart_list) >= 6:
+                            break
+                else:
+                    app.logger.debug("Failed to retrieve Flipkart page")
+            except Exception as e:
+                app.logger.error("Error during Flipkart scraping: %s", e)
 
-                    if not title or not price or not product_url:
-                        continue
-                    
-                    price_val = extract_price(price)
-                    
-                    flipkart_list.append({
-                        "title": title,
-                        "image": image_url,
-                        "price": price,
-                        "url": product_url,
-                        "price_val": price_val
-                    })
-                    if len(flipkart_list) >= 6:
-                        break
             flipkart_list = sorted(flipkart_list, key=lambda x: x['price_val'])[:6]
 
     return render_template('index.html', amazon=amazon_list, flipkart=flipkart_list)
 
 if __name__ == '__main__':
-    app.run(host='0.0.0.0', port=8080)
+    app.run(host='0.0.0.0', port=8080, debug=True)