raena-crawler-engine/amazon_crawler_engine/test.py

45 lines
864 B
Python

from selenium import webdriver
from selenium.webdriver.common.by import By
import time
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
op = webdriver.ChromeOptions()
op.add_argument('--no-sandbox')
op.add_argument('--disable-notifications')
op.add_argument("--lang=en-GB")
#op.headless = True
driver=webdriver.Chrome( options=op)
driver.get('https://www.noon.com/uae-en/beauty/')
time.sleep(10)
element = driver.find_element(By.CSS_SELECTOR, '.componentArea-9')
title = element.find_element(By.CSS_SELECTOR, '.truncate-title-header').text
products = element.find_elements(By.CSS_SELECTOR, '.sc-kCMKrZ.ealOXE')
urls = []
for product in products:
url = product.find_element(By.TAG_NAME, 'a').get_attribute('href')
urls.append(url)
data = {
"title": title,
"products": urls
}
print(data)
driver.close()