Update app.py

app.py

@@ -2,13 +2,14 @@ import gradio as gr
 import requests
 from bs4 import BeautifulSoup
 import pandas as pd
-import chromedriver_autoinstaller
 from selenium import webdriver
 from selenium.webdriver.chrome.options import Options
 import csv
 import random
 import time
 import os
+import subprocess
+import chromedriver_autoinstaller
 
 # List of user agents to avoid bot detection
 USER_AGENTS = [
@@ -17,7 +18,27 @@ USER_AGENTS = [
     "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:89.0) Gecko/20100101 Firefox/89.0"
 ]
 
-# Function to initialize Selenium driver (headless)
+# Install Chrome and dependencies dynamically
+def install_chrome():
+    try:
+        # Update package list and install Chrome dependencies
+        subprocess.run("apt-get update", shell=True, check=True)
+        subprocess.run(
+            "apt-get install -y libxss1 libappindicator1 libindicator7 fonts-liberation libnss3 xdg-utils unzip", 
+            shell=True, check=True
+        )
+        # Download and install Chrome
+        subprocess.run(
+            "wget https://dl.google.com/linux/direct/google-chrome-stable_current_amd64.deb", 
+            shell=True, check=True
+        )
+        subprocess.run("dpkg -i google-chrome-stable_current_amd64.deb || apt-get install -f -y", shell=True, check=True)
+        # Install ChromeDriver
+        chromedriver_autoinstaller.install()
+    except Exception as e:
+        raise Exception(f"Failed to install Chrome: {str(e)}")
+
+# Function to initialize Selenium driver
 def get_driver():
     chrome_options = Options()
     chrome_options.add_argument("--headless")  # Run in headless mode
@@ -29,13 +50,17 @@ def get_driver():
 # Function to scrape Flipkart laptop data
 def scrape_flipkart(url):
     try:
+        # Ensure Chrome is installed
+        if not os.path.exists("/usr/bin/google-chrome"):
+            install_chrome()
+        
         # Set up Selenium driver
         driver = get_driver()
         headers = {"User-Agent": random.choice(USER_AGENTS)}
         
         # Load the page
         driver.get(url)
-        time.sleep(5)  # Wait for JavaScript to load content
+        time.sleep(5)  # Wait for JavaScript to load
         
         # Get page source and parse with BeautifulSoup
         soup = BeautifulSoup(driver.page_source, "html.parser")