hreflang flag getter for pi

flag_getter.py

from selenium import webdriver
from bs4 import BeautifulSoup
import requests
import os
from flag_recognition import recognize_flag, is_flag
from config import CHROMEDRIVER_PATH, STARTING_URL

# Configure WebDriver for Chrome
options = webdriver.ChromeOptions()
options.add_argument('headless')
driver = webdriver.Chrome(executable_path=CHROMEDRIVER_PATH, options=options)

def crawl_website(url):
    driver.get(url)
    soup = BeautifulSoup(driver.page_source, 'html.parser')
    links = {a['href'] for a in soup.find_all('a', href=True) if a['href'].startswith('http')}
    images = {img['src']: url for img in soup.find_all('img', src=True) if img['src'].startswith('http')}
    download_images(images)
    return links

def download_images(image_urls):
    for image_url, source_url in image_urls.items():
        try:
            response = requests.get(image_url)
            if response.status_code == 200:
                image_path = f'images/img_{os.path.basename(image_url)}'
                with open(image_path, 'wb') as f:
                    f.write(response.content)
                if is_flag(image_path):
                    country_name = recognize_flag(image_path)
                    if country_name:
                        iso_code = fetch_iso_code(country_name)
                        print(f"Flag of {country_name} identified: ISO code is {iso_code}. Found at {source_url}")
        except requests.exceptions.RequestException as e:
            print(f"Failed to download {image_url}: {e}")

def fetch_iso_code(country_name):
    url = "https://en.wikipedia.org/wiki/ISO_3166-1"
    driver.get(url)
    soup = BeautifulSoup(driver.page_source, 'html.parser')
    table = soup.find('table', {'class': 'wikitable sortable'})
    for row in table.find_all('tr'):
        cells = row.find_all('td')
        if cells and country_name in cells[0].text:
            return cells[1].text.strip()  # Assuming the ISO code is in the second column

def main():
    if not os.path.exists('images'):
        os.mkdir('images')
    links = crawl_website(STARTING_URL)

if __name__ == "__main__":
    main()