from .base import BaseDownloader
from bs4 import BeautifulSoup
import re


class UptoboxDownloader(BaseDownloader):
    """Downloader for uptobox.com"""

    BASE_DOMAINS = ["uptobox.com", "uptobox.fr"]

    def can_handle(self, url: str) -> bool:
        return any(domain in url.lower() for domain in self.BASE_DOMAINS)

    async def get_download_link(self, url: str) -> tuple[str, str]:
        """Extract direct download link from uptobox"""
        try:
            response = await self.client.get(url, follow_redirects=True)
            soup = BeautifulSoup(response.text, 'lxml')

            # Method 1: Look for direct download button/link
            download_btn = soup.find('a', {'id': 'directDownload'}) or soup.find('a', class_='download-btn')
            if download_btn and download_btn.get('href'):
                href = download_btn['href']
                filename = self._extract_filename_from_url(url) or "uptobox_file"
                return href, filename

            # Method 2: Look for any download link in page
            links = soup.find_all('a', href=True)
            for link in links:
                href = link['href']
                text = link.get_text().lower()
                if any(keyword in text for keyword in ['download', 'télécharger', 'ddl']):
                    if href.startswith('http'):
                        filename = self._extract_filename_from_url(url) or "uptobox_file"
                        return href, filename

            # Method 3: Return the original URL (uptobox handles downloads directly)
            filename = self._extract_filename_from_url(url) or "uptobox_file"
            return url, filename

        except Exception as e:
            raise Exception(f"Error extracting Uptobox link: {str(e)}")

    def _extract_filename_from_url(self, url: str) -> str | None:
        """Try to extract filename from URL"""
        # Look for filename parameter in URL
        match = re.search(r'[&?]filename=([^&]+)', url)
        if match:
            from urllib.parse import unquote
            return unquote(match.group(1))

        # Extract from path
        parts = url.split('/')
        if len(parts) > 0:
            last_part = parts[-1]
            if '.' in last_part:
                return last_part

        return None