Spaces:
Running
on
Zero
Running
on
Zero
File size: 2,675 Bytes
4006c1a |
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 |
import os
import requests
import zipfile
import io
import gradio as gr
def get_file_summary(file_info):
return {
"name": file_info.filename,
"type": "binary" if file_info.file_size > 1024 * 1024 else "text",
"size": file_info.file_size,
}
def extract_repo_content(url):
if "huggingface.co" not in url:
return "Invalid URL. Please provide a valid Hugging Face URL."
repo_name = url.split('/')[-2]
repo_type = url.split('/')[-3]
api_url = f"https://huggingface.co/api/{repo_type}/{repo_name}/tree/main"
response = requests.get(api_url)
if response.status_code != 200:
return f"Failed to fetch repository content. Status code: {response.status_code}"
repo_content = response.json()
extracted_content = []
headers = []
for file_info in repo_content:
file_summary = get_file_summary(file_info)
headers.append(file_summary)
if file_summary["type"] == "text" and file_summary["size"] <= 1024 * 1024:
file_url = f"https://huggingface.co/{repo_type}/{repo_name}/resolve/main/{file_info['filename']}"
file_response = requests.get(file_url)
if file_response.status_code == 200:
file_content = file_response.text
extracted_content.append({"header": file_summary, "content": file_content})
else:
extracted_content.append({"header": file_summary, "content": "Failed to fetch file content."})
else:
extracted_content.append({"header": file_summary, "content": "File too large or binary, content not captured."})
return extracted_content
def format_output(extracted_content):
formatted_output = ""
for file_data in extracted_content:
formatted_output += f"### File: {file_data['header']['name']}\n"
formatted_output += f"**Type:** {file_data['header']['type']}\n"
formatted_output += f"**Size:** {file_data['header']['size']} bytes\n"
formatted_output += "#### Content:\n"
formatted_output += f"```\n{file_data['content']}\n```\n\n"
return formatted_output
def extract_and_display(url):
extracted_content = extract_repo_content(url)
formatted_output = format_output(extracted_content)
return formatted_output
app = gr.Blocks()
with app:
gr.Markdown("# Gradio Space/Model Content Extractor")
url_input = gr.Textbox(label="Hugging Face Space/Model URL")
output_display = gr.Markdown()
extract_button = gr.Button("Extract Content")
extract_button.click(fn=extract_and_display, inputs=url_input, outputs=output_display)
app.launch()
|