Untitled

mail@pastecode.io avatar
unknown
python
a month ago
1.2 kB
14
Indexable
Never
from selenium import webdriver
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup

# Set up Chrome driver options
chrome_options = Options()
chrome_options.add_argument("--headless")  # Run Chrome in headless mode

# Set up Chrome driver
driver = webdriver.Chrome(options=chrome_options)

# Load the page
url = 'https://www.amazon.com/s?k=laptops'
driver.get(url)

# Get the page source after JavaScript execution
page_source = driver.page_source

# Close the driver
driver.quit()

# Parse the page source with BeautifulSoup
soup = BeautifulSoup(page_source, 'html.parser')

# Scrape the desired information
products = soup.find_all('div', {'data-component-type': 's-search-result'})

for product in products:
    title = product.find('span', {'class': 'a-size-medium'}).text.strip()
    
    price_element = product.find('span', {'class': 'a-offscreen'})
    if price_element is not None:
        price = price_element.text.strip()
    else:
        price = 'N/A'
    
    rating = product.find('span', {'class': 'a-icon-alt'}).text.strip()
    
    print(f"Title: {title}")
    print(f"Price: {price}")
    print(f"Rating: {rating}")
    print()
Leave a Comment