Update terabox_utils.py

terabox_utils.py

@@ -1,37 +1,87 @@
 # terabox_utils.py
 
+import re
+import aiohttp
 import os
 import asyncio
+import logging
+import uuid
 
-# Example extract function
+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:
-    # Dummy logic — implement your real one
-    if "terabox.com" in url:
-        return url.split("/")[-1].split("?")[0]
+    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
 
-# Example function to get direct download URL & filename
-async def get_final_url_and_filename(original_link: str) -> tuple[str, str, str | None]:
+# --- Get direct URL and filename ---
+async def get_final_url_and_filename(original_link: str) -> tuple[str | None, str | None, str | None]:
     try:
-        # Here you should implement calling your TERABOX_WORKER_URL or scraping logic
-        # For now we return dummy values:
-        download_url = f"https://dummy-terabox-link/{original_link.split('/')[-1]}"
-        filename = f"{original_link.split('/')[-1]}.mp4"
-        return download_url, filename, None
+        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:
-        return "", "", str(e)
+        logger.exception("Error in get_final_url_and_filename()")
+        return None, None, str(e)
 
-# Example function to simulate download
-async def download_terabox_file(bot, chat_id, message_id, download_url, raw_filename) -> tuple[str, str, str | None]:
+# --- 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:
-        # Simulate a file download — here you would implement your real download logic
-        local_filepath = f"downloads/{raw_filename}"
-        with open(local_filepath, "wb") as f:
-            f.write(b"dummy content")  # Replace with actual file download
+        local_filepath = os.path.join("downloads", raw_filename)
 
-        # Thumbnail path — you can leave empty or create a dummy image
-        thumb_path = ""  # Optional thumbnail path
+        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:
-        return "", "", str(e)
+        logger.exception("Error in download_terabox_file()")
+        return None, None, str(e)