Initial commit: MIB bot

download_files.py

@@ -0,0 +1,63 @@
+import os
+import re
+import tempfile
+from pathlib import Path
+from urllib.parse import urlencode, unquote
+
+import aiohttp
+
+from config import create_aiohttp_session, get_aiohttp_request_kwargs
+
+DOWNLOAD_DIR = Path("downloads")
+DOWNLOAD_DIR.mkdir(exist_ok=True)
+
+
+def sanitize_filename(filename: str) -> str:
+    filename = os.path.basename(filename).strip()
+    filename = re.sub(r"[\\/:*?\"<>|]+", "_", filename)
+    return filename or "downloaded_file"
+
+
+async def download_yandex_files(public_url: str, progress_callback=None) -> str:
+    base_url = "https://cloud-api.yandex.net/v1/disk/public/resources/download?"
+    final_url = base_url + urlencode({"public_key": public_url})
+
+    timeout = aiohttp.ClientTimeout(total=None, sock_connect=30, sock_read=300)
+
+    async with create_aiohttp_session(timeout=timeout) as session:
+        request_kwargs = get_aiohttp_request_kwargs()
+
+        async with session.get(final_url, **request_kwargs) as response:
+            response.raise_for_status()
+            payload = await response.json()
+            download_url = payload["href"]
+
+        async with session.get(download_url, **request_kwargs) as response:
+            response.raise_for_status()
+
+            content_disposition = response.headers.get("Content-Disposition", "")
+            filename = download_url.split("/")[-1]
+
+            if "filename*" in content_disposition:
+                try:
+                    encoded = content_disposition.split("filename*=")[1].strip()
+                    parts = encoded.split("''", 1)
+                    if len(parts) == 2:
+                        filename = unquote(parts[1], encoding=parts[0] or "utf-8")
+                except Exception:
+                    pass
+
+            filename = sanitize_filename(filename)
+            suffix = Path(filename).suffix or ".bin"
+
+            with tempfile.NamedTemporaryFile(delete=False, suffix=suffix, dir=DOWNLOAD_DIR) as tmp_file:
+                total_size = int(response.headers.get("Content-Length", 0))
+                downloaded_size = 0
+
+                async for chunk in response.content.iter_chunked(1024 * 64):
+                    tmp_file.write(chunk)
+                    downloaded_size += len(chunk)
+                    if progress_callback:
+                        await progress_callback(downloaded_size, total_size)
+
+                return tmp_file.name