Spaces:
Running
Running
File size: 3,243 Bytes
523358f b124a22 9a91666 064c454 9a91666 6221aa6 064c454 9a91666 77c4d7d 9a91666 064c454 523358f 9a91666 064c454 9a91666 064c454 523358f 064c454 b124a22 9a91666 b124a22 9a91666 064c454 9a91666 064c454 9a91666 064c454 9a91666 064c454 9a91666 77c4d7d 064c454 9a91666 523358f 9a91666 064c454 9a91666 064c454 9a91666 064c454 9a91666 064c454 9a91666 064c454 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | import os
import requests
import gradio as gr
from huggingface_hub import HfApi
from pathlib import Path
# Get token from Space Secrets
HF_TOKEN = os.environ.get("HF_TOKEN")
api = HfApi(token=HF_TOKEN)
def get_repo_info(url):
"""Extracts repo_id and repo_type from a standard HF URL."""
try:
parts = url.strip().split("huggingface.co/")[1].split("/")
if parts[0] == "datasets":
return f"{parts[1]}/{parts[2]}", "dataset"
else:
return f"{parts[0]}/{parts[1]}", "model"
except:
return None, None
def download_and_upload(dataset_url, download_url, progress=gr.Progress()):
if not HF_TOKEN:
return "❌ Error: HF_TOKEN not found in Secrets."
repo_id, repo_type = get_repo_info(dataset_url)
if not repo_id:
return "❌ Error: Invalid Dataset/Repo URL format."
filename = download_url.split("/")[-1].split("?")[0]
local_path = Path(filename)
try:
# Step 1: Download with status updates
progress(0, desc="Initializing stream...")
with requests.get(download_url, stream=True, timeout=60) as r:
r.raise_for_status()
total_size = int(r.headers.get('content-length', 0))
downloaded = 0
with open(local_path, 'wb') as f:
for chunk in r.iter_content(chunk_size=1024*1024): # 1MB chunks
if chunk:
f.write(chunk)
downloaded += len(chunk)
if total_size > 0:
done = downloaded / total_size
# Update every few MBs to keep the connection alive
progress(done * 0.5, desc=f"Downloading: {downloaded/(1024**3):.2f}GB / {total_size/(1024**3):.2f}GB")
# Step 2: Upload to HF
progress(0.6, desc="Uploading to Hugging Face...")
api.upload_file(
path_or_fileobj=str(local_path),
path_in_repo=filename,
repo_id=repo_id,
repo_type=repo_type,
commit_message=f"Uploaded {filename} via UpDownUrl",
# This is key for large files:
run_as_future=False
)
return f"✅ Done! '{filename}' is now in {repo_id}"
except Exception as e:
return f"❌ Error: {str(e)}"
finally:
if local_path.exists():
os.remove(local_path)
# --- UI Setup ---
with gr.Blocks() as demo:
gr.Markdown("# 🚀 UpDownUrl v1.1")
with gr.Row():
with gr.Column():
dataset_link = gr.Textbox(label="Target Repo Link", placeholder="https://huggingface.co/datasets/AIDev07/AIModelsLoaded")
download_link = gr.Textbox(label="Download URL", placeholder="Direct link to file")
upload_btn = gr.Button("Boom! Upload", variant="primary")
with gr.Column():
output_log = gr.Textbox(label="Status", interactive=False)
upload_btn.click(
fn=download_and_upload,
inputs=[dataset_link, download_link],
outputs=output_log
)
# Fixed Gradio 6.0 syntax: Theme goes here
if __name__ == "__main__":
demo.launch(theme=gr.themes.Soft())
|