import requests
from bs4 import BeautifulSoup
import os
base_url = "https://www.hkubs.hku.hk/people/faculty?pg={}&staff_type=faculty&subject_area=all&track=professoriate&region=hku"
os.makedirs('profile_photos', exist_ok=True)
for page in range(1, 11):
    url = base_url.format(page)
    print(f"Fetching page: {url}")
    response = requests.get(url)
    if response.status_code == 200:
        soup = BeautifulSoup(response.text, 'html.parser')
        photo_divs = soup.find_all('div', class_='people-item')
        for idx, div in enumerate(photo_divs):
            img_tag = div.find('img')
            if img_tag and 'src' in img_tag.attrs:
                photo_url = img_tag['src']
                img_response = requests.get(photo_url)
                if img_response.status_code == 200:
                    photo_filename = f'profile_photos/photo_page{page}_{idx + 1}.jpg'
                    with open(photo_filename, 'wb') as f:
                        f.write(img_response.content)
                    print(f'Downloaded: {photo_filename}')
                else:
                    print(f'Failed to download photo from {photo_url}')
    else:
        print(f'Failed to retrieve the page. Status code: {response.status_code}')