app.py

import gradio as gr
from PIL import Image
import requests
from bs4 import BeautifulSoup
import os
import subprocess
from huggingface_hub import ModelCard, SpaceCard, HfApi

# PNG Info Tool
def png_info(file):
    img = Image.open(file)
    metadata = img.info
    metadata_str = "\n".join([f"{key}: {value}" for key, value in metadata.items()])
    return metadata_str

# Web Info Tool
def web_info(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    title = soup.title.string if soup.title else ""
    meta_description = soup.find("meta", attrs={"name": "description"})
    description = meta_description["content"] if meta_description else ""
    meta_tags = soup.find_all("meta")
    headers = {f"h{i}": len(soup.find_all(f"h{i}")) for i in range(1, 7)}
    links = [a["href"] for a in soup.find_all("a", href=True)]
    basic_info = f"Title: {title}\nDescription: {description}"
    html_info = f"Meta Tags: {len(meta_tags)}\nHeaders: {headers}\nLinks: {len(links)}"
    return f"{basic_info}\n\nHTML Info:\n{html_info}"

# View Source Info Tool
def view_source_info(url):
    if url.startswith("view-source:"):
        url = url.replace("view-source:", "").strip()
    if not url.startswith(("http://", "https://")):
        url = "https://" + url
    response = requests.get(url)
    return response.text

# Document Info Tool
def document_info(file):
    file_extension = os.path.splitext(file.name)[1].lower()
    content = ""
    preview = None
    if file_extension in [".txt", ".md"]:
        with open(file.name, "r") as f:
            content = f.read()
    elif file_extension in [".png", ".jpg", ".jpeg", ".bmp", ".gif"]:
        preview = file.name
    else:
        content = "Unsupported file format"
    return content, preview

# Video Info Tool
def video_info(file):
    video_display = file
    result = subprocess.run(
        ["ffprobe", "-v", "error", "-show_format", "-show_streams", file],
        stdout=subprocess.PIPE,
        stderr=subprocess.PIPE,
        text=True,
    )
    return video_display, result.stdout

# Model Info Tool
def model_info(model_id):
    try:
        card = ModelCard.load(model_id)
        api = HfApi()
        model_info = api.model_info(model_id)
        by = model_info.author if model_info.author else ""
        description = card.content if card.content else ""
        related_spaces = model_info.siblings
        related_spaces = [s.rfilename for s in related_spaces if s.rfilename.endswith(".py")]
        related_spaces = "\n".join(related_spaces) if related_spaces else ""
        install_instructions = f"pip install transformers\n\n# To use the model:\nfrom transformers import AutoModel, AutoTokenizer\nmodel = AutoModel.from_pretrained('{model_id}')\ntokenizer = AutoTokenizer.from_pretrained('{model_id}')"
        return by, description, related_spaces, install_instructions
    except Exception:
        return "", "", "", ""

# Space Info Tool
def space_info(space_id):
    try:
        card = SpaceCard.load(space_id)
        api = HfApi()
        space_info = api.space_info(space_id)
        makes = space_info.author if space_info.author else ""
        description = card.content if card.content else ""
        code_files = space_info.siblings
        code_files = [s.rfilename for s in code_files if s.rfilename.endswith(".py")]
        code = "\n".join(code_files) if code_files else ""
        return makes, code, description
    except Exception:
        return "", "", ""

# Gradio Interface
with gr.Blocks() as demo:
    gr.Markdown("## Information Extraction Tools")
    
    with gr.Tab("PNG Info"):
        png_input = gr.File(label="Upload PNG File")
        png_output = gr.Textbox(label="PNG Metadata", lines=10)
        png_button = gr.Button("Extract PNG Info")
        png_button.click(png_info, inputs=png_input, outputs=png_output)
    
    with gr.Tab("Web Info"):
        web_input = gr.Textbox(label="Enter URL")
        web_output = gr.Textbox(label="Web Info")
        web_button = gr.Button("Extract Web Info")
        web_button.click(web_info, inputs=web_input, outputs=web_output)
    
    with gr.Tab("View Source Info"):
        source_input = gr.Textbox(label="Enter URL (with or without 'view-source:')", placeholder="e.g., https://example.com or view-source:example.com")
        source_output = gr.Textbox(label="HTML Source Code", lines=20)
        source_button = gr.Button("View Source")
        source_button.click(view_source_info, inputs=source_input, outputs=source_output)
    
    with gr.Tab("Document Info"):
        doc_input = gr.File(label="Upload Document")
        content_output = gr.Textbox(label="Content", lines=10, visible=False)
        preview_output = gr.Image(label="Preview (Image)", visible=False)
        doc_button = gr.Button("Extract Document Info")
        
        def update_output_components(file):
            if file is None:
                return gr.Textbox(visible=False), gr.Image(visible=False)
            file_extension = os.path.splitext(file.name)[1].lower()
            if file_extension in [".txt", ".md"]:
                return gr.Textbox(visible=True), gr.Image(visible=False)
            elif file_extension in [".png", ".jpg", ".jpeg", ".bmp", ".gif"]:
                return gr.Textbox(visible=False), gr.Image(visible=True)
            else:
                return gr.Textbox(visible=True), gr.Image(visible=False)
        
        doc_button.click(document_info, inputs=doc_input, outputs=[content_output, preview_output])
        doc_input.change(update_output_components, inputs=doc_input, outputs=[content_output, preview_output])
    
    with gr.Tab("Video Info"):
        video_input = gr.Video(label="Upload Video")
        video_output = gr.Video(label="Video Preview")
        metadata_output = gr.Textbox(label="Video Metadata", lines=10)
        video_button = gr.Button("Extract Video Info")
        video_button.click(video_info, inputs=video_input, outputs=[video_output, metadata_output])
    
    with gr.Tab("Model Info"):
        model_input = gr.Textbox(label="Enter Model ID", placeholder="e.g., bert-base-uncased")
        by_output = gr.Textbox(label="By", value="")
        description_output = gr.Textbox(label="Description", value="", lines=5)
        spaces_output = gr.Textbox(label="Related Spaces", value="", lines=3)
        install_output = gr.Textbox(label="How to Install", value="", lines=5)
        model_button = gr.Button("Fetch Model Info")
        model_button.click(model_info, inputs=model_input, outputs=[by_output, description_output, spaces_output, install_output])
    
    with gr.Tab("Space Info"):
        space_input = gr.Textbox(label="Enter Space ID", placeholder="e.g., gradio/hello-world")
        makes_output = gr.Textbox(label="Makes", value="")
        code_output = gr.Textbox(label="Code", value="", lines=5)
        description_output = gr.Textbox(label="Description", value="", lines=10)
        space_button = gr.Button("Fetch Space Info")
        space_button.click(space_info, inputs=space_input, outputs=[makes_output, code_output, description_output])

# Launch the Gradio app
demo.launch()