import gradio as gr
import requests
from urllib.parse import urlparse, urljoin
from bs4 import BeautifulSoup

def is_valid_url(url):
    """Checks if the string is a valid URL."""
    try:
        result = urlparse(url)
        return all([result.scheme, result.netloc])  # Check for scheme and domain
    except:
        return False

def extract_additional_resources(url):
    """Extracts links to CSS, JS, and images from HTML code."""
    try:
        response = requests.get(url)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, "html.parser")

        # Extract CSS links
        css_links = [urljoin(url, link["href"]) for link in soup.find_all("link", rel="stylesheet") if "href" in link.attrs]

        # Extract JS links
        js_links = [urljoin(url, script["src"]) for script in soup.find_all("script") if "src" in script.attrs]

        # Extract image links
        img_links = [urljoin(url, img["src"]) for img in soup.find_all("img") if "src" in img.attrs]

        return css_links, js_links, img_links
    except Exception as e:
        return [], [], []

def fetch_file_content(url):
    """Fetches the content of a file (CSS, JS, etc.) from a URL."""
    try:
        response = requests.get(url)
        response.raise_for_status()
        return response.text
    except:
        return "Failed to fetch content."

def convert_to_text(url):
    if not is_valid_url(url):
        return "Error: Please enter a valid URL.", "", None, [], [], [], [], []  # Return error message and empty data

    try:
        # Set headers to mimic a browser request
        headers = {
            "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36"
        }
        response = requests.get(url, headers=headers)
        response.raise_for_status()  # Check for HTTP errors (e.g., 404, 500)

        # Return results
        status = f"Request status: {response.status_code}"
        content_length = f"Content size: {len(response.text)} characters"
        results = f"{status}\n{content_length}"

        # Save text content to a file
        file_path = "downloaded_content.txt"
        with open(file_path, "w", encoding="utf-8") as file:
            file.write(response.text)

        # Extract additional resources
        css_links, js_links, img_links = extract_additional_resources(url)

        # Fetch CSS and JS content
        css_content = [fetch_file_content(link) for link in css_links]
        js_content = [fetch_file_content(link) for link in js_links]

        return results, response.text, file_path, css_links, js_links, img_links, css_content, js_content
    except requests.exceptions.RequestException as e:
        return f"Error: {e}", "", None, [], [], [], [], []  # Return error message and empty data

# HTML and JavaScript for the "Copy Code" button
copy_button_html = """
<script>
function copyCode() {
    const text = document.querySelector("#output-text textarea").value;
    navigator.clipboard.writeText(text).then(() => {
        alert("Text copied to clipboard!");
    }).catch(() => {
        alert("Failed to copy text.");
    });
}
</script>
<button onclick="copyCode()">Copy Code</button>
"""

# Link to the CSS file
css = "app.css"

# Create the Gradio interface
with gr.Blocks(css=css) as demo:
    gr.Markdown("## URL to Text Converter")
    gr.Markdown("Enter a URL to fetch its text content and download it as a .txt file.")
    
    with gr.Row():
        url_input = gr.Textbox(label="Enter URL", placeholder="https://example.com")
    
    with gr.Row():
        results_output = gr.Textbox(label="Request Results", interactive=False)
        text_output = gr.Textbox(label="Text Content", interactive=True, elem_id="output-text")
    
    with gr.Row():
        gr.HTML(copy_button_html)  # Add the "Copy Code" button
        file_output = gr.File(label="Download File", visible=False)  # Hidden file download component
    
    submit_button = gr.Button("Fetch Content")
    submit_button.click(
        fn=convert_to_text,
        inputs=url_input,
        outputs=[
            results_output, text_output, file_output,
            gr.Textbox(label="CSS Files"), gr.Textbox(label="JS Files"), gr.Textbox(label="Images"),
            gr.Textbox(label="CSS Content"), gr.Textbox(label="JS Content")
        ]
    )

    # Add an Accordion to show/hide additional resources
    with gr.Accordion("Show/Hide Additional Resources", open=False):
        gr.Markdown("### CSS Files")
        css_output = gr.Textbox(label="CSS Files", interactive=False)
        
        gr.Markdown("### JS Files")
        js_output = gr.Textbox(label="JS Files", interactive=False)
        
        gr.Markdown("### Images")
        img_output = gr.Textbox(label="Images", interactive=False)
        
        gr.Markdown("### CSS Content")
        css_content_output = gr.Textbox(label="CSS Content", interactive=True)
        
        gr.Markdown("### JS Content")
        js_content_output = gr.Textbox(label="JS Content", interactive=True)

# Launch the interface
demo.launch()