Spaces:
Runtime error
Runtime error
Delete app.py
Browse files
app.py
DELETED
|
@@ -1,517 +0,0 @@
|
|
| 1 |
-
import asyncio
|
| 2 |
-
import os
|
| 3 |
-
import re
|
| 4 |
-
import time
|
| 5 |
-
import uuid
|
| 6 |
-
import shutil
|
| 7 |
-
import aiohttp
|
| 8 |
-
import gc # Memory management ke liye garbage collector
|
| 9 |
-
import zipfile # ZIP file handle karne ke liye in-built library
|
| 10 |
-
import urllib3 # Zero-buffer strict low RAM downloding ke liye
|
| 11 |
-
from fastapi import FastAPI, BackgroundTasks, Request, File, UploadFile
|
| 12 |
-
from fastapi.middleware.cors import CORSMiddleware
|
| 13 |
-
from fastapi.responses import FileResponse, StreamingResponse
|
| 14 |
-
from pydantic import BaseModel
|
| 15 |
-
from concurrent.futures import ThreadPoolExecutor
|
| 16 |
-
|
| 17 |
-
app = FastAPI()
|
| 18 |
-
|
| 19 |
-
app.add_middleware(
|
| 20 |
-
CORSMiddleware,
|
| 21 |
-
allow_origins=["*"],
|
| 22 |
-
allow_credentials=True,
|
| 23 |
-
allow_methods=["*"],
|
| 24 |
-
allow_headers=["*"],
|
| 25 |
-
)
|
| 26 |
-
|
| 27 |
-
tasks = {}
|
| 28 |
-
DATA_DIR = "/data"
|
| 29 |
-
os.makedirs(DATA_DIR, exist_ok=True)
|
| 30 |
-
|
| 31 |
-
# Parallel chunks handle karne ke liye separate dedicated pool executor
|
| 32 |
-
thread_executor = ThreadPoolExecutor(max_workers=8)
|
| 33 |
-
|
| 34 |
-
class DownloadRequest(BaseModel):
|
| 35 |
-
url: str
|
| 36 |
-
|
| 37 |
-
def clean_filename(url: str) -> str:
|
| 38 |
-
"""URL se sahi extension aur filename nikalne ka jugaad"""
|
| 39 |
-
path = url.split("?")[0]
|
| 40 |
-
filename = path.split("/")[-1]
|
| 41 |
-
if not filename or "." not in filename:
|
| 42 |
-
return "downloaded_file.bin"
|
| 43 |
-
return filename
|
| 44 |
-
|
| 45 |
-
async def cleanup_old_files():
|
| 46 |
-
while True:
|
| 47 |
-
try:
|
| 48 |
-
now = time.time()
|
| 49 |
-
for filename in os.listdir(DATA_DIR):
|
| 50 |
-
filepath = os.path.join(DATA_DIR, filename)
|
| 51 |
-
if os.path.isfile(filepath):
|
| 52 |
-
if now - os.path.getmtime(filepath) > 86400:
|
| 53 |
-
os.remove(filepath)
|
| 54 |
-
for tid, tinfo in list(tasks.items()):
|
| 55 |
-
if tinfo.get("file_path") == filepath:
|
| 56 |
-
del tasks[tid]
|
| 57 |
-
except Exception as e:
|
| 58 |
-
print(f"Cleanup error: {e}")
|
| 59 |
-
await asyncio.sleep(3600)
|
| 60 |
-
|
| 61 |
-
@app.on_event("startup")
|
| 62 |
-
async def startup_event():
|
| 63 |
-
asyncio.create_task(cleanup_old_files())
|
| 64 |
-
|
| 65 |
-
def download_segment(url: str, start_byte: int, end_byte: int, file_path: str, task_id: str, http_pool):
|
| 66 |
-
"""Specific range ka part target file ke precise offset me write karne ka concurrent worker"""
|
| 67 |
-
headers = {"Range": f"bytes={start_byte}-{end_byte}"}
|
| 68 |
-
try:
|
| 69 |
-
# Network socket parameters push karenge peak buffer utilization ke liye
|
| 70 |
-
response = http_pool.request('GET', url, headers=headers, preload_content=False, timeout=None)
|
| 71 |
-
|
| 72 |
-
# Binary file stream mode me precise positioning par write karenge
|
| 73 |
-
with open(file_path, 'rb+') as f:
|
| 74 |
-
f.seek(start_byte)
|
| 75 |
-
chunk_size = 128 * 1024 # Standard network maximum transmission frame alignment
|
| 76 |
-
|
| 77 |
-
for chunk in response.stream(chunk_size):
|
| 78 |
-
if not chunk:
|
| 79 |
-
break
|
| 80 |
-
f.write(chunk)
|
| 81 |
-
chunk_len = len(chunk)
|
| 82 |
-
|
| 83 |
-
# Global dictionary progress data thread-safe incremental updating
|
| 84 |
-
tasks[task_id]["downloaded"] += chunk_len
|
| 85 |
-
tasks[task_id]["chunk_speed_counter"] += chunk_len
|
| 86 |
-
del chunk
|
| 87 |
-
|
| 88 |
-
response.release_conn()
|
| 89 |
-
except Exception as e:
|
| 90 |
-
tasks[task_id]["status"] = "error"
|
| 91 |
-
tasks[task_id]["error"] = str(e)
|
| 92 |
-
|
| 93 |
-
def sync_download_worker(task_id: str, url: str):
|
| 94 |
-
"""Smart dynamic downloader: Choti files single connections se aur badi files segmented parallel connections se jayengi"""
|
| 95 |
-
file_path = tasks[task_id]["file_path"]
|
| 96 |
-
try:
|
| 97 |
-
# High pool allocation limit taaki multiple concurrent sockets blocking interface na karein
|
| 98 |
-
http = urllib3.PoolManager(block=False, maxsize=10, num_pools=4)
|
| 99 |
-
|
| 100 |
-
# HEAD call optimization for content metadata verification
|
| 101 |
-
head_response = http.request('HEAD', url, timeout=10.0)
|
| 102 |
-
total_size = int(head_response.headers.get('Content-Length', 0))
|
| 103 |
-
tasks[task_id]["total_size"] = total_size
|
| 104 |
-
|
| 105 |
-
cd = head_response.headers.get('Content-Disposition')
|
| 106 |
-
if cd and 'filename=' in cd:
|
| 107 |
-
fname = re.findall('filename="([^"]+)"', cd)
|
| 108 |
-
if not fname:
|
| 109 |
-
fname = re.findall('filename=([^;]+)', cd)
|
| 110 |
-
if fname:
|
| 111 |
-
new_filename = fname[0]
|
| 112 |
-
file_path = os.path.join(DATA_DIR, f"{task_id}_{new_filename}")
|
| 113 |
-
tasks[task_id]["file_path"] = file_path
|
| 114 |
-
tasks[task_id]["original_filename"] = new_filename
|
| 115 |
-
|
| 116 |
-
# Empty/Pre-allocated file buffer skeleton banayenge parallel offsets synchronization ke liye
|
| 117 |
-
with open(file_path, 'wb') as f:
|
| 118 |
-
if total_size > 0:
|
| 119 |
-
f.truncate(total_size)
|
| 120 |
-
|
| 121 |
-
# Speed measurement background metrics setup
|
| 122 |
-
tasks[task_id]["chunk_speed_counter"] = 0
|
| 123 |
-
|
| 124 |
-
# SPEED TRACER THREAD LAUNCH (Independent metrics tracking engine)
|
| 125 |
-
def tracking_loop():
|
| 126 |
-
last_time = time.time()
|
| 127 |
-
while tasks[task_id]["status"] == "downloading":
|
| 128 |
-
time.sleep(1.0)
|
| 129 |
-
current_time = time.time()
|
| 130 |
-
elapsed = current_time - last_time
|
| 131 |
-
if elapsed > 0:
|
| 132 |
-
current_speed = tasks[task_id]["chunk_speed_counter"] / elapsed
|
| 133 |
-
tasks[task_id]["speed"] = current_speed
|
| 134 |
-
tasks[task_id]["chunk_speed_counter"] = 0
|
| 135 |
-
last_time = current_time
|
| 136 |
-
|
| 137 |
-
import threading
|
| 138 |
-
tracker = threading.Thread(target=tracking_loop, daemon=True)
|
| 139 |
-
tracker.start()
|
| 140 |
-
|
| 141 |
-
# SEGMENTATION LOGIC: Agar file size 20MB se badi hai aur chunk capabilities supported hain
|
| 142 |
-
is_range_supported = head_response.headers.get('Accept-Ranges') == 'bytes' or 'Content-Length' in head_response.headers
|
| 143 |
-
|
| 144 |
-
if total_size > 20 * 1024 * 1024 and is_range_supported:
|
| 145 |
-
num_segments = 6 # Hugging Face par safest efficient thread concurrency limit
|
| 146 |
-
segment_size = total_size // num_segments
|
| 147 |
-
futures = []
|
| 148 |
-
|
| 149 |
-
for i in range(num_segments):
|
| 150 |
-
start = i * segment_size
|
| 151 |
-
end = total_size - 1 if i == num_segments - 1 else (start + segment_size - 1)
|
| 152 |
-
futures.append(thread_executor.submit(download_segment, url, start, end, file_path, task_id, http))
|
| 153 |
-
|
| 154 |
-
# Sub-threads compilation resolution waiting window
|
| 155 |
-
for fut in futures:
|
| 156 |
-
fut.result()
|
| 157 |
-
|
| 158 |
-
# Final verification sequence check
|
| 159 |
-
if tasks[task_id]["status"] == "downloading":
|
| 160 |
-
tasks[task_id]["status"] = "completed"
|
| 161 |
-
else:
|
| 162 |
-
# Fallback process standard streaming workflow agar ranges completely blank/unsupported ho
|
| 163 |
-
response = http.request('GET', url, preload_content=False, timeout=None)
|
| 164 |
-
downloaded = 0
|
| 165 |
-
chunk_counter = 0
|
| 166 |
-
|
| 167 |
-
with open(file_path, 'wb') as f:
|
| 168 |
-
for chunk in response.stream(128 * 1024): # Increased to 128KB for better TCP throughput
|
| 169 |
-
if not chunk:
|
| 170 |
-
break
|
| 171 |
-
f.write(chunk)
|
| 172 |
-
len_c = len(chunk)
|
| 173 |
-
downloaded += len_c
|
| 174 |
-
tasks[task_id]["downloaded"] = downloaded
|
| 175 |
-
tasks[task_id]["chunk_speed_counter"] += len_c
|
| 176 |
-
|
| 177 |
-
chunk_counter += 1
|
| 178 |
-
# Reduced excessive filesystem sync/gc overhead frequency to optimize hardware bottleneck
|
| 179 |
-
if chunk_counter % 50 == 0:
|
| 180 |
-
f.flush()
|
| 181 |
-
del chunk
|
| 182 |
-
gc.collect()
|
| 183 |
-
|
| 184 |
-
response.release_conn()
|
| 185 |
-
tasks[task_id]["status"] = "completed"
|
| 186 |
-
|
| 187 |
-
tasks[task_id]["speed"] = 0.0
|
| 188 |
-
except Exception as e:
|
| 189 |
-
tasks[task_id]["status"] = "error"
|
| 190 |
-
tasks[task_id]["error"] = str(e)
|
| 191 |
-
finally:
|
| 192 |
-
gc.collect()
|
| 193 |
-
|
| 194 |
-
async def download_file(task_id: str, url: str):
|
| 195 |
-
loop = asyncio.get_event_loop()
|
| 196 |
-
await loop.run_in_executor(thread_executor, sync_download_worker, task_id, url)
|
| 197 |
-
|
| 198 |
-
@app.post("/start_download")
|
| 199 |
-
async def start_download(req: DownloadRequest, background_tasks: BackgroundTasks):
|
| 200 |
-
task_id = str(uuid.uuid4())
|
| 201 |
-
filename = clean_filename(req.url)
|
| 202 |
-
|
| 203 |
-
tasks[task_id] = {
|
| 204 |
-
"task_id": task_id,
|
| 205 |
-
"url": req.url,
|
| 206 |
-
"status": "downloading",
|
| 207 |
-
"total_size": 0,
|
| 208 |
-
"downloaded": 0,
|
| 209 |
-
"speed": 0.0,
|
| 210 |
-
"file_path": os.path.join(DATA_DIR, f"{task_id}_{filename}"),
|
| 211 |
-
"original_filename": filename,
|
| 212 |
-
"timestamp": time.time()
|
| 213 |
-
}
|
| 214 |
-
background_tasks.add_task(download_file, task_id, req.url)
|
| 215 |
-
return {"task_id": task_id}
|
| 216 |
-
|
| 217 |
-
@app.get("/status/{task_id}")
|
| 218 |
-
async def get_status(task_id: str):
|
| 219 |
-
if task_id not in tasks:
|
| 220 |
-
return {"error": "Task not found"}
|
| 221 |
-
return tasks[task_id]
|
| 222 |
-
|
| 223 |
-
@app.get("/download/{task_id}")
|
| 224 |
-
async def download(task_id: str):
|
| 225 |
-
if task_id not in tasks or tasks[task_id]["status"] != "completed":
|
| 226 |
-
return {"error": "File not ready"}
|
| 227 |
-
return FileResponse(tasks[task_id]["file_path"], filename=tasks[task_id].get("original_filename"))
|
| 228 |
-
|
| 229 |
-
@app.get("/stream/{task_id}")
|
| 230 |
-
async def stream(task_id: str, request: Request):
|
| 231 |
-
if task_id not in tasks or tasks[task_id]["status"] != "completed":
|
| 232 |
-
return {"error": "File not ready"}
|
| 233 |
-
|
| 234 |
-
file_path = tasks[task_id]["file_path"]
|
| 235 |
-
file_size = os.path.getsize(file_path)
|
| 236 |
-
range_header = request.headers.get("Range")
|
| 237 |
-
|
| 238 |
-
if range_header:
|
| 239 |
-
byte1, byte2 = 0, None
|
| 240 |
-
match = range_header.replace("bytes=", "").split("-")
|
| 241 |
-
if match[0]:
|
| 242 |
-
byte1 = int(match[0])
|
| 243 |
-
if len(match) > 1 and match[1]:
|
| 244 |
-
byte2 = int(match[1])
|
| 245 |
-
|
| 246 |
-
length = file_size - byte1
|
| 247 |
-
if byte2 is not None:
|
| 248 |
-
length = byte2 + 1 - byte1
|
| 249 |
-
|
| 250 |
-
def file_iterator(start, length):
|
| 251 |
-
with open(file_path, "rb") as f:
|
| 252 |
-
f.seek(start)
|
| 253 |
-
chunk_size = 128 * 1024
|
| 254 |
-
while length > 0:
|
| 255 |
-
read_size = min(chunk_size, length)
|
| 256 |
-
data = f.read(read_size)
|
| 257 |
-
if not data:
|
| 258 |
-
break
|
| 259 |
-
yield data
|
| 260 |
-
length -= len(data)
|
| 261 |
-
del data
|
| 262 |
-
|
| 263 |
-
headers = {
|
| 264 |
-
"Content-Range": f"bytes {byte1}-{byte1+length-1}/{file_size}",
|
| 265 |
-
"Accept-Ranges": "bytes",
|
| 266 |
-
"Content-Length": str(length),
|
| 267 |
-
"X-Accel-Buffering": "no", # Proxy distribution bottleneck bypass hack
|
| 268 |
-
"Cache-Control": "no-cache"
|
| 269 |
-
}
|
| 270 |
-
return StreamingResponse(file_iterator(byte1, length), status_code=206, headers=headers)
|
| 271 |
-
else:
|
| 272 |
-
return FileResponse(file_path, headers={"X-Accel-Buffering": "no", "Cache-Control": "no-cache"})
|
| 273 |
-
|
| 274 |
-
@app.get("/storage")
|
| 275 |
-
async def get_storage():
|
| 276 |
-
total, used, free = shutil.disk_usage(DATA_DIR)
|
| 277 |
-
return {"total": total, "used": used, "free": free}
|
| 278 |
-
|
| 279 |
-
@app.post("/delete_all")
|
| 280 |
-
async def delete_all():
|
| 281 |
-
for filename in os.listdir(DATA_DIR):
|
| 282 |
-
filepath = os.path.join(DATA_DIR, filename)
|
| 283 |
-
try:
|
| 284 |
-
if os.path.isfile(filepath):
|
| 285 |
-
os.remove(filepath)
|
| 286 |
-
elif os.path.isdir(filepath):
|
| 287 |
-
shutil.rmtree(filepath)
|
| 288 |
-
except Exception as e:
|
| 289 |
-
print(f"Failed to delete {filepath}: {e}")
|
| 290 |
-
tasks.clear()
|
| 291 |
-
gc.collect()
|
| 292 |
-
return {"status": "success"}
|
| 293 |
-
|
| 294 |
-
@app.get("/history")
|
| 295 |
-
async def get_history():
|
| 296 |
-
return {"history": list(tasks.values())}
|
| 297 |
-
|
| 298 |
-
@app.post("/upload")
|
| 299 |
-
async def upload_file(file: UploadFile = File(...)):
|
| 300 |
-
task_id = str(uuid.uuid4())
|
| 301 |
-
original_filename = file.filename if file.filename else "uploaded_file.bin"
|
| 302 |
-
file_path = os.path.join(DATA_DIR, f"{task_id}_{original_filename}")
|
| 303 |
-
|
| 304 |
-
with open(file_path, "wb") as buffer:
|
| 305 |
-
while True:
|
| 306 |
-
chunk = await file.read(128 * 1024)
|
| 307 |
-
if not chunk:
|
| 308 |
-
break
|
| 309 |
-
buffer.write(chunk)
|
| 310 |
-
|
| 311 |
-
await file.close()
|
| 312 |
-
file_size = os.path.getsize(file_path)
|
| 313 |
-
|
| 314 |
-
tasks[task_id] = {
|
| 315 |
-
"task_id": task_id,
|
| 316 |
-
"url": "local_upload",
|
| 317 |
-
"status": "completed",
|
| 318 |
-
"total_size": file_size,
|
| 319 |
-
"downloaded": file_size,
|
| 320 |
-
"speed": 0.0,
|
| 321 |
-
"file_path": file_path,
|
| 322 |
-
"original_filename": original_filename,
|
| 323 |
-
"timestamp": time.time()
|
| 324 |
-
}
|
| 325 |
-
gc.collect()
|
| 326 |
-
return {"task_id": task_id}
|
| 327 |
-
|
| 328 |
-
@app.post("/start_gofile_transfer")
|
| 329 |
-
async def start_gofile_transfer(req: DownloadRequest, background_tasks: BackgroundTasks):
|
| 330 |
-
task_id = str(uuid.uuid4())
|
| 331 |
-
filename = clean_filename(req.url)
|
| 332 |
-
|
| 333 |
-
tasks[task_id] = {
|
| 334 |
-
"task_id": task_id,
|
| 335 |
-
"url": req.url,
|
| 336 |
-
"status": "downloading",
|
| 337 |
-
"total_size": 0,
|
| 338 |
-
"downloaded": 0,
|
| 339 |
-
"speed": 0.0,
|
| 340 |
-
"file_path": os.path.join(DATA_DIR, f"{task_id}_{filename}"),
|
| 341 |
-
"original_filename": filename,
|
| 342 |
-
"gofile_url": None,
|
| 343 |
-
"timestamp": time.time()
|
| 344 |
-
}
|
| 345 |
-
background_tasks.add_task(process_gofile_transfer, task_id, req.url)
|
| 346 |
-
return {"task_id": task_id}
|
| 347 |
-
|
| 348 |
-
async def file_sender(file_path, chunk_size=128 * 1024):
|
| 349 |
-
with open(file_path, 'rb') as f:
|
| 350 |
-
while True:
|
| 351 |
-
chunk = f.read(chunk_size)
|
| 352 |
-
if not chunk:
|
| 353 |
-
break
|
| 354 |
-
yield chunk
|
| 355 |
-
del chunk
|
| 356 |
-
|
| 357 |
-
def sync_gofile_download_part(task_id: str, url: str):
|
| 358 |
-
"""Same optimized multi-segment execution injection inside secondary functions"""
|
| 359 |
-
file_path = tasks[task_id]["file_path"]
|
| 360 |
-
http = urllib3.PoolManager(block=False, maxsize=10, num_pools=4)
|
| 361 |
-
|
| 362 |
-
head_response = http.request('HEAD', url, timeout=10.0)
|
| 363 |
-
total_size = int(head_response.headers.get('Content-Length', 0))
|
| 364 |
-
tasks[task_id]["total_size"] = total_size
|
| 365 |
-
|
| 366 |
-
cd = head_response.headers.get('Content-Disposition')
|
| 367 |
-
if cd and 'filename=' in cd:
|
| 368 |
-
fname = re.findall('filename="([^"]+)"', cd)
|
| 369 |
-
if not fname:
|
| 370 |
-
fname = re.findall('filename=([^;]+)', cd)
|
| 371 |
-
if fname:
|
| 372 |
-
new_filename = fname[0]
|
| 373 |
-
file_path = os.path.join(DATA_DIR, f"{task_id}_{new_filename}")
|
| 374 |
-
tasks[task_id]["file_path"] = file_path
|
| 375 |
-
tasks[task_id]["original_filename"] = new_filename
|
| 376 |
-
|
| 377 |
-
with open(file_path, 'wb') as f:
|
| 378 |
-
if total_size > 0:
|
| 379 |
-
f.truncate(total_size)
|
| 380 |
-
|
| 381 |
-
tasks[task_id]["chunk_speed_counter"] = 0
|
| 382 |
-
def tracking_loop():
|
| 383 |
-
last_time = time.time()
|
| 384 |
-
while tasks[task_id]["status"] == "downloading":
|
| 385 |
-
time.sleep(1.0)
|
| 386 |
-
current_time = time.time()
|
| 387 |
-
elapsed = current_time - last_time
|
| 388 |
-
if elapsed > 0:
|
| 389 |
-
tasks[task_id]["speed"] = tasks[task_id]["chunk_speed_counter"] / elapsed
|
| 390 |
-
tasks[task_id]["chunk_speed_counter"] = 0
|
| 391 |
-
last_time = current_time
|
| 392 |
-
|
| 393 |
-
import threading
|
| 394 |
-
tracker = threading.Thread(target=tracking_loop, daemon=True)
|
| 395 |
-
tracker.start()
|
| 396 |
-
|
| 397 |
-
is_range_supported = head_response.headers.get('Accept-Ranges') == 'bytes' or 'Content-Length' in head_response.headers
|
| 398 |
-
if total_size > 20 * 1024 * 1024 and is_range_supported:
|
| 399 |
-
num_segments = 6
|
| 400 |
-
segment_size = total_size // num_segments
|
| 401 |
-
futures = []
|
| 402 |
-
for i in range(num_segments):
|
| 403 |
-
start = i * segment_size
|
| 404 |
-
end = total_size - 1 if i == num_segments - 1 else (start + segment_size - 1)
|
| 405 |
-
futures.append(thread_executor.submit(download_segment, url, start, end, file_path, task_id, http))
|
| 406 |
-
for fut in futures:
|
| 407 |
-
fut.result()
|
| 408 |
-
else:
|
| 409 |
-
response = http.request('GET', url, preload_content=False, timeout=None)
|
| 410 |
-
downloaded = 0
|
| 411 |
-
with open(file_path, 'wb') as f:
|
| 412 |
-
for chunk in response.stream(128 * 1024):
|
| 413 |
-
if not chunk:
|
| 414 |
-
break
|
| 415 |
-
f.write(chunk)
|
| 416 |
-
len_c = len(chunk)
|
| 417 |
-
downloaded += len_c
|
| 418 |
-
tasks[task_id]["downloaded"] = downloaded
|
| 419 |
-
tasks[task_id]["chunk_speed_counter"] += len_c
|
| 420 |
-
response.release_conn()
|
| 421 |
-
|
| 422 |
-
async def process_gofile_transfer(task_id: str, url: str):
|
| 423 |
-
try:
|
| 424 |
-
loop = asyncio.get_event_loop()
|
| 425 |
-
await loop.run_in_executor(thread_executor, sync_gofile_download_part, task_id, url)
|
| 426 |
-
|
| 427 |
-
file_path = tasks[task_id]["file_path"]
|
| 428 |
-
tasks[task_id]["status"] = "uploading_to_gofile"
|
| 429 |
-
tasks[task_id]["speed"] = 0.0
|
| 430 |
-
|
| 431 |
-
async with aiohttp.ClientSession() as session:
|
| 432 |
-
async with session.get("https://api.gofile.io/servers") as resp:
|
| 433 |
-
servers_data = await resp.json()
|
| 434 |
-
server = servers_data["data"]["servers"][0]["name"]
|
| 435 |
-
|
| 436 |
-
upload_url = f"https://{server}.gofile.io/uploadFile"
|
| 437 |
-
|
| 438 |
-
data = aiohttp.FormData()
|
| 439 |
-
data.add_field('file', file_sender(file_path), filename=tasks[task_id]["original_filename"])
|
| 440 |
-
|
| 441 |
-
async with session.post(upload_url, data=data) as upload_resp:
|
| 442 |
-
upload_result = await upload_resp.json()
|
| 443 |
-
if upload_result["status"] == "ok":
|
| 444 |
-
tasks[task_id]["gofile_url"] = upload_result["data"]["downloadPage"]
|
| 445 |
-
tasks[task_id]["status"] = "completed"
|
| 446 |
-
else:
|
| 447 |
-
raise Exception("GoFile upload failed")
|
| 448 |
-
|
| 449 |
-
try:
|
| 450 |
-
os.remove(file_path)
|
| 451 |
-
except:
|
| 452 |
-
pass
|
| 453 |
-
|
| 454 |
-
except Exception as e:
|
| 455 |
-
tasks[task_id]["status"] = "error"
|
| 456 |
-
tasks[task_id]["error"] = str(e)
|
| 457 |
-
finally:
|
| 458 |
-
gc.collect()
|
| 459 |
-
|
| 460 |
-
# ==================== ZIP MANAGEMENT FEATURES ====================
|
| 461 |
-
|
| 462 |
-
@app.get("/list_zip/{task_id}")
|
| 463 |
-
async def list_zip_contents(task_id: str):
|
| 464 |
-
if task_id not in tasks:
|
| 465 |
-
return {"error": "Task not found"}
|
| 466 |
-
|
| 467 |
-
file_path = tasks[task_id]["file_path"]
|
| 468 |
-
if not os.path.exists(file_path):
|
| 469 |
-
return {"error": "File does not exist on server"}
|
| 470 |
-
|
| 471 |
-
if not zipfile.is_zipfile(file_path):
|
| 472 |
-
return {"error": "This file is not a valid ZIP archive"}
|
| 473 |
-
|
| 474 |
-
try:
|
| 475 |
-
with zipfile.ZipFile(file_path, 'r') as z:
|
| 476 |
-
file_list = []
|
| 477 |
-
for info in z.infolist():
|
| 478 |
-
file_list.append({
|
| 479 |
-
"filename": info.filename,
|
| 480 |
-
"file_size_mb": round(info.file_size / (1024 * 1024), 2),
|
| 481 |
-
"is_dir": info.is_dir()
|
| 482 |
-
})
|
| 483 |
-
return {"task_id": task_id, "total_files": len(file_list), "files": file_list}
|
| 484 |
-
except Exception as e:
|
| 485 |
-
return {"error": f"Failed to read ZIP: {str(e)}"}
|
| 486 |
-
|
| 487 |
-
@app.post("/extract_zip/{task_id}")
|
| 488 |
-
async def extract_zip_file(task_id: str, background_tasks: BackgroundTasks):
|
| 489 |
-
if task_id not in tasks:
|
| 490 |
-
return {"error": "Task not found"}
|
| 491 |
-
|
| 492 |
-
file_path = tasks[task_id]["file_path"]
|
| 493 |
-
if not os.path.exists(file_path):
|
| 494 |
-
return {"error": "File does not exist on server"}
|
| 495 |
-
|
| 496 |
-
if not zipfile.is_zipfile(file_path):
|
| 497 |
-
return {"error": "This file is not a valid ZIP archive"}
|
| 498 |
-
|
| 499 |
-
extract_folder = os.path.join(DATA_DIR, f"extracted_{task_id}")
|
| 500 |
-
os.makedirs(extract_folder, exist_ok=True)
|
| 501 |
-
|
| 502 |
-
tasks[task_id]["status"] = "extracting"
|
| 503 |
-
tasks[task_id]["extract_path"] = extract_folder
|
| 504 |
-
|
| 505 |
-
background_tasks.add_task(process_zip_extraction, task_id, file_path, extract_folder)
|
| 506 |
-
return {"status": "extraction_started", "task_id": task_id, "target_folder": extract_folder}
|
| 507 |
-
|
| 508 |
-
def process_zip_extraction(task_id: str, zip_path: str, target_dir: str):
|
| 509 |
-
try:
|
| 510 |
-
with zipfile.ZipFile(zip_path, 'r') as z:
|
| 511 |
-
file_counter = 0
|
| 512 |
-
for member in z.namelist():
|
| 513 |
-
z.extract(member, path=target_dir)
|
| 514 |
-
file_counter += 1
|
| 515 |
-
if file_counter % 50 == 0:
|
| 516 |
-
gc.collect()
|
| 517 |
-
tasks[task
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|