terabox_utils.py

# terabox_utils.py

import re
import aiohttp
import os
import asyncio
import logging
import uuid

logger = logging.getLogger(__name__)

# List of supported domains
TERABOX_DOMAINS = [
    "terabox.com",
    "teraboxapp.com",
    "terasharelink.com",
    "1024tera.com",
    "freeterabox.com",
    "4funbox.com",
    "box-links.com",
]

# --- Extract short_id ---
async def extract_terabox_short_id(url: str) -> str | None:
    pattern = re.compile(
        r"https?://(?:"
        + "|".join(re.escape(domain) for domain in TERABOX_DOMAINS)
        + r")/s/([a-zA-Z0-9_-]+)"
    )
    match = pattern.search(url)
    if match:
        return match.group(1)
    return None

# --- Get direct URL and filename ---
async def get_final_url_and_filename(original_link: str) -> tuple[str | None, str | None, str | None]:
    try:
        async with aiohttp.ClientSession() as session:
            async with session.get(original_link, allow_redirects=True) as resp:
                if resp.status != 200:
                    return None, None, f"Failed to access link: HTTP {resp.status}"
                html = await resp.text()

        # Try to extract filename and direct URL (depends on Terabox's HTML structure — needs to be robust!)
        file_name_match = re.search(r'"file_name":"(.*?)"', html)
        dlink_match = re.search(r'"dlink":"(https:[^"]+)"', html)

        if not dlink_match:
            return None, None, "Failed to extract direct link (dlink) from Terabox page."

        download_url = dlink_match.group(1).encode('utf-8').decode('unicode_escape')

        raw_filename = "file_from_terabox_" + str(uuid.uuid4()) if not file_name_match else file_name_match.group(1)

        logger.info(f"Resolved direct URL: {download_url}, filename: {raw_filename}")

        return download_url, raw_filename, None

    except Exception as e:
        logger.exception("Error in get_final_url_and_filename()")
        return None, None, str(e)

# --- Download file ---
async def download_terabox_file(bot, chat_id: int, status_message_id: int, download_url: str, raw_filename: str) -> tuple[str | None, str | None, str | None]:
    try:
        local_filepath = os.path.join("downloads", raw_filename)

        async with aiohttp.ClientSession() as session:
            async with session.get(download_url) as resp:
                if resp.status != 200:
                    return None, None, f"Failed to download file: HTTP {resp.status}"

                with open(local_filepath, "wb") as f:
                    while True:
                        chunk = await resp.content.read(1024 * 1024)
                        if not chunk:
                            break
                        f.write(chunk)

        # You may implement optional fast thumbnail here — for now we'll just skip thumb
        thumb_path = None

        return local_filepath, thumb_path, None

    except Exception as e:
        logger.exception("Error in download_terabox_file()")
        return None, None, str(e)