34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
|
import re
|
||
|
|
import json
|
||
|
|
from selenium import webdriver
|
||
|
|
from selenium.webdriver.chrome.options import Options
|
||
|
|
from selenium.webdriver.common.by import By
|
||
|
|
|
||
|
|
# Configure the Selenium driver options
|
||
|
|
options = Options()
|
||
|
|
options.add_argument('--headless')
|
||
|
|
options.add_argument('--disable-gpu')
|
||
|
|
driver = webdriver.Chrome(options=options)
|
||
|
|
|
||
|
|
# Load the page and extract the __NEXT_DATA__ data
|
||
|
|
url = 'https://www.sayweee.com/en/product/Want-Want-Senbei-Rice-Crackers/17119'
|
||
|
|
driver.get(url)
|
||
|
|
next_data_element = None
|
||
|
|
for script_element in driver.find_elements(By.XPATH, '//script'):
|
||
|
|
script_text = script_element.get_attribute('innerHTML')
|
||
|
|
match = re.search(r'__NEXT_DATA__ = (\{.*\});', script_text)
|
||
|
|
if match:
|
||
|
|
next_data_json = match.group(1)
|
||
|
|
next_data = json.loads(next_data_json)
|
||
|
|
# Extract the price from the __NEXT_DATA__ data
|
||
|
|
price = next_data['props']['pageProps']['product']['price']
|
||
|
|
# Print the price
|
||
|
|
print(price)
|
||
|
|
break
|
||
|
|
|
||
|
|
if next_data_element is None:
|
||
|
|
print('__NEXT_DATA__ element not found')
|
||
|
|
|
||
|
|
# Close the Selenium driver
|
||
|
|
driver.quit()
|