from bs4 import BeautifulSoup
import requests
import urllib.parse as urlparse

headers = {
    'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
    'accept-language': 'fr-FR,fr;q=0.7',
    'cache-control': 'no-cache',
    'pragma': 'no-cache',
    'priority': 'u=0, i',
    'sec-ch-ua': '"Brave";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
    'sec-ch-ua-mobile': '?0',
    'sec-ch-ua-platform': '"macOS"',
    'sec-fetch-dest': 'document',
    'sec-fetch-mode': 'navigate',
    'sec-fetch-site': 'same-origin',
    'sec-fetch-user': '?1',
    'sec-gpc': '1',
    'upgrade-insecure-requests': '1',
    'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
}

params = {
    'action': 'affiche',
    'quoi': 'mpsi/feuillesexo/matrices',
    'type': 'fexo',
}

response = requests.get('https://bibmath.net/ressources/index.php', headers=headers, params=params)

if response.status_code == 200:
    soup = BeautifulSoup(response.text, 'html.parser')
    article = soup.find('article', id='contenugauche')
    if article:
        title = article.find('h1').get_text(strip=True)
        print(f"Title: {title}")
        
        # Find all part titles
        part_titles = article.find_all('div', class_='titrepartie')
        for part in part_titles:
            part_text = part.get_text(strip=True)
            print(f"Part of the File: {part_text}")
        
        exercises = article.find_all('div', class_='exo')
        for exo in exercises:
            exo_title_div = exo.find('div', class_='titreexo')
            
            exercise_number = exo_title_div.find_all('span')[1].text.strip()
            title_start = exo_title_div.text.find(' - ') + 3
            title_end = exo_title_div.text.find('[Signaler une erreur]')
            exercise_title = exo_title_div.text[title_start:title_end].strip()

            error_link = exo_title_div.find('a', href=lambda href: href and 'signalerreur.php' in href)['href']
            parsed_url = urlparse.urlparse(error_link)
            exercise_id = urlparse.parse_qs(parsed_url.query)['numero'][0]

            stars_count = len(exo_title_div.find_all('img'))

            enonce = exo.find('div', class_='enonce').find('div', class_='inner').get_text(strip=True)
            indication_div = exo.find('div', class_='indication')
            indication = (
                indication_div.find('div', class_='inner').get_text(strip=True) 
                if indication_div else "No indication"
            )

            answer_div = exo.find('div', class_='corrige')
            answer = (
                answer_div.find('div', class_='inner').get_text(strip=True)
                if answer_div else "No answer"
            )
            # print(f"Exercise Number: {exercise_number}")
            # print(f"Exercise Title: {exercise_title}")
            # print(f"Exercise ID: {exercise_id}")
            # print(f"Stars: {stars_count} stars")
            # print(f"Enonce: {enonce}")
            # print(f"Indication: {indication}")
            # print(f"Answer: {answer}")
    else:
        print("Article with id 'contenugauche' not found.")
else:
    print(f"Request failed with status code: {response.status_code}")