pip install requests
pip install pyfiglet
pip install beautifulsoup4

import requests
from bs4 import BeautifulSoup
from urllib.parse import urlparse, urljoin
import pyfiglet

ascii_banner = pyfiglet.figlet_format("GELİŞTİR")
print(ascii_banner)

IMAGE_EXTENSIONS = ('.jpg', '.jpeg', '.png', '.gif', '.bmp', '.svg', '.webp')
WEBPAGE_EXTENSIONS = ('.html', '.htm', '.php', '.asp', '.aspx', '.jsp', '.jspx', '.cgi', '.pl')

def get_links(url):
    try:
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        links = [a.get('href') for a in soup.find_all('a', href=True)]
        absolute_links = [urljoin(url, link) for link in links]
        return absolute_links
    except Exception as e:
        print(f"Hata: {str(e)}")
        return []

def is_valid_url(url):
    parsed_url = urlparse(url)
    return (parsed_url.path.endswith(WEBPAGE_EXTENSIONS) or not parsed_url.path or '.' not in parsed_url.path.split('/')[-1]) and not parsed_url.path.endswith(IMAGE_EXTENSIONS)

def crawl_site(root_url, domain, max_depth=-1):
    visited = set()
    queue = [(root_url, 0)]

    while queue:
        url, depth = queue.pop(0)
        if max_depth != -1 and depth > max_depth:
            continue
        if url in visited:
            continue
        visited.add(url)

        if domain not in url:
            continue

        if not is_valid_url(url):
            continue

        print(f"Processing: {url}")

        links = get_links(url)
        for link in links:
            if link not in visited and domain in link:
                queue.append((link, depth + 1))

    sitemap_filename = input("Sitemap dosyasının adını girin (örneğin, sitemap.xml): ")
    create_sitemap(root_url, visited, sitemap_filename)

def create_sitemap(start_url, visited, filename):
    with open(filename, 'w', encoding='utf-8') as file:
        file.write('<?xml version="1.0" encoding="UTF-8"?>\n')
        file.write('<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9">\n')
        for url in visited:
            file.write(f'<url><loc>{url}</loc></url>\n')
        file.write('</urlset>\n')

if __name__ == "__main__":
    root_url = input("Web sitesi URL'sini girin: ")
    domain = input("Dahil etmek istediğiniz alan adını girin (örneğin, smsvar.com): ")
    max_depth = int(input("Derinlik sınırlamasını girin (tam tarama için -1): "))

    crawl_site(root_url, domain, max_depth)