ARTICLE AD BOX
I need help in understanding if this code is malicious. Or if it is generic? Or can it download a virus? I deployed this as an exe file.
This is a code I wrote while working. I got feedback that this is too generic. And it can download a virus. I used AI tools like ChatGPT/perplexity to write it. Is it obvious? I'm new to coding, and please explain as if you are expaining to someone who just started coding.
# CODE for phone data Amazon Web Scapping using Pincode for Geolocation works fine. Folder created -- # -- for scrapped data along with screenshot of each product page. import os import time import pandas as pd from selenium import webdriver from selenium.webdriver.common.by import By from selenium.webdriver.common.keys import Keys from selenium.webdriver.chrome.options import Options from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC # --------- User input section --------- brand = "Samsung" pincode_input = input("Enter pincodes separated by commas (e.g. 400001,110001,560001): ") pincodes = [p.strip() for p in pincode_input.split(',') if p.strip()] max_pages = 20 # Cap on pages per pincode out_dir = "scraped_data" screenshot_dir = os.path.join(out_dir, "screenshots") os.makedirs(out_dir, exist_ok=True) os.makedirs(screenshot_dir, exist_ok=True) excel_path = os.path.join(out_dir, "phones_amazon_pincode_scrape.xlsx") # -------------------------------------- def setup_driver(headless=True): options = Options() if headless: options.add_argument("--headless=new") options.add_argument("--window-size=1920,1080") options.add_argument('--disable-blink-features=AutomationControlled') options.add_argument('--no-sandbox') options.add_argument('--disable-dev-shm-usage') return webdriver.Chrome(options=options) def set_location_amazon(driver, pincode): print(f"Setting Amazon location to pincode: {pincode} ...") driver.get("https://www.amazon.in/") WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.ID, "nav-global-location-popover-link"))) time.sleep(2) try: driver.find_element(By.ID, "nav-global-location-popover-link").click() time.sleep(1) pin_input = WebDriverWait(driver, 10).until(EC.element_to_be_clickable((By.ID, "GLUXZipUpdateInput"))) pin_input.clear() pin_input.send_keys(pincode) driver.find_element(By.XPATH, "//input[@aria-labelledby='GLUXZipUpdate-announce']").click() time.sleep(1) try: done_btn = driver.find_element(By.NAME, "glowDoneButton") done_btn.click() except Exception: pass time.sleep(2) # Close popups try: driver.find_element(By.XPATH, "//button[@data-action='a-popover-close']").click() except Exception: pass print(f"Amazon pincode set to {pincode}") return True except Exception as e: print(f"Amazon location not set for pincode {pincode}: {e}") return False def search_amazon(driver, keyword): print(f"Searching Amazon for '{keyword}' ...") try: box = WebDriverWait(driver, 20).until(EC.element_to_be_clickable((By.ID, "twotabsearchtextbox"))) box.clear() box.send_keys(keyword) box.send_keys(Keys.RETURN) time.sleep(3) except Exception as e: print("Amazon search failed:", e) def get_all_amazon_product_links(driver, max_pages=20): print("Extracting all Amazon product links ...") links = [] page = 1 while page <= max_pages: print(f"Scanning Amazon page {page}") WebDriverWait(driver, 20).until(EC.presence_of_element_located((By.XPATH, "//div[@data-component-type='s-search-result']"))) items = driver.find_elements(By.XPATH, "//div[@data-component-type='s-search-result']") for item in items: try: url = item.find_element(By.TAG_NAME, "a").get_attribute("href") if url and url.startswith("https://www.amazon.in"): links.append(url) except Exception: continue # Try to click next page try: next_button = driver.find_element(By.XPATH, "//a[contains(@class,'s-pagination-next') and not(contains(@class,'disabled'))]") driver.execute_script("arguments[0].scrollIntoView();", next_button) next_button.click() time.sleep(3) page += 1 except Exception: print("No more Amazon pages or unable to find Next button.") break print(f"Total Amazon products found: {len(links)}") return list(dict.fromkeys(links)) def extract_amazon_details_and_screenshot(driver, url, idx, pincode): driver.get(url) time.sleep(2) screenshot_path = os.path.join(screenshot_dir, f"amazon_{pincode}_product_{idx+1}.png") driver.save_screenshot(screenshot_path) def get_text(by, value): try: return driver.find_element(by, value).text.strip() except: return "" title = get_text(By.ID, "productTitle") price = get_text(By.CLASS_NAME, "a-price-whole") if not price: price = get_text(By.ID, "priceblock_ourprice") if not price: price = get_text(By.ID, "priceblock_dealprice") rating = get_text(By.ID, "acrPopover") seller = "" for by, value in [ (By.ID, "sellerProfileTriggerId"), (By.ID, "merchant-info"), (By.XPATH, "//a[@id='bylineInfo']"), (By.XPATH, "//div[@id='tabular-buybox']//div[contains(text(),'Sold by')]"), (By.XPATH, "//div[contains(@id,'merchant-info')]"), (By.XPATH, "//div[contains(text(),'Sold by')]"), ]: seller = get_text(by, value) if seller: break return { "site": "Amazon", "title": title, "price": price, "rating": rating, "seller": seller, "url": url, "pincode": pincode, "screenshot": screenshot_path } # --- Main scraping process for all pincodes --- all_data = [] for pincode in pincodes: print(f"\n=== Scraping for Amazon, pincode: {pincode} ===") driver = setup_driver(headless=True) try: if not set_location_amazon(driver, pincode): print(f"Skipping {pincode}: could not set location on Amazon.") continue search_amazon(driver, brand) links = get_all_amazon_product_links(driver, max_pages) for idx, link in enumerate(links): print(f"Scraping product {idx+1}/{len(links)} for pincode {pincode} on Amazon") details = extract_amazon_details_and_screenshot(driver, link, idx, pincode) all_data.append(details) finally: driver.quit() df = pd.DataFrame(all_data) df.to_excel(excel_path, index=False) print(f"\nData saved in Excel: {excel_path}") print(f"Screenshots saved in: {screenshot_dir}")