Python - Selenium - sappi.com (Stackoverflow)

# date: 2025.08.26

# [pandas - Python 3.9, get in MS excel ALL physical addresses from the URL -> https://www.sappi.com/en-gb/about-us/locations - Stack Overflow](https://stackoverflow.com/questions/79746723/python-3-9-get-in-ms-excel-all-physical-addresses-from-the-url-https-www-s)

# https://www.sappi.com/en-gb/about-us/locations

from selenium import webdriver
#import time

# ---

import selenium
print('Selenium:', selenium.__version__)

# ---

url = "https://www.sappi.com/en-gb/about-us/locations"

#driver = webdriver.Chrome()
driver = webdriver.Firefox()

driver.get(url)

#time.sleep(5)

html = driver.page_source

driver.close()

# ----

from bs4 import BeautifulSoup
import pandas as pd

soup = BeautifulSoup(html, 'html.parser')

location_cards = soup.find_all('article', class_='node-type__location')

if len(location_cards) == 0:
    print("Can't find data !!!")
else:
    data = []
    for card in location_cards:

        item = card.find('h3')
        name = item.get_text(strip=True, separator='|') if item else ""

        item = card.find('li', class_='location-address')
        address = item.get_text(strip=True, separator='|') if item else ""

        # there is no `location-country`
        #item = card.find('li', class_='location-country')
        item = card.find('span', class_='address-country')
        country = item.get_text(strip=True, separator='|') if item else ""

        data.append({
            'Name': name,
            'Address': address,
            'Country': country
        })

    # Convert to DataFrame and export to Excel
    df = pd.DataFrame(data)
    df.to_excel('sappi_locations.xlsx', index=False)
    #df.to_csv('sappi_locations.csv', index=False)

    print("Data exported to sappi_locations.xlsx")