Create app.py

app.py

@@ -0,0 +1,64 @@
+import gradio as gr
+import requests
+from bs4 import BeautifulSoup
+from urllib.parse import urljoin, urlparse
+import pdfkit
+import os
+
+def get_subdirectory_pages(url, base_url, visited=set()):
+    if url in visited:
+        return []
+    
+    visited.add(url)
+    pages = [url]
+    
+    try:
+        response = requests.get(url)
+        soup = BeautifulSoup(response.text, 'html.parser')
+        
+        for link in soup.find_all('a'):
+            href = link.get('href')
+            if href:
+                full_url = urljoin(base_url, href)
+                if full_url.startswith(base_url) and full_url not in visited:
+                    pages.extend(get_subdirectory_pages(full_url, base_url, visited))
+    except Exception as e:
+        print(f"Error processing {url}: {e}")
+    
+    return pages
+
+def website_to_pdf(url):
+    parsed_url = urlparse(url)
+    base_url = f"{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path.rstrip('/')}/"
+    all_pages = get_subdirectory_pages(base_url, base_url)
+    
+    options = {
+        'page-size': 'A4',
+        'margin-top': '0.75in',
+        'margin-right': '0.75in',
+        'margin-bottom': '0.75in',
+        'margin-left': '0.75in',
+    }
+    
+    output_file = "subdirectory_documentation.pdf"
+    pdfkit.from_url(all_pages, output_file, options=options)
+    
+    return output_file
+
+def process_url(url):
+    try:
+        pdf_file = website_to_pdf(url)
+        return pdf_file
+    except Exception as e:
+        return f"An error occurred: {str(e)}"
+
+iface = gr.Interface(
+    fn=process_url,
+    inputs=gr.Textbox(label="Enter website URL (e.g., https://www.gradio.app/docs)"),
+    outputs=gr.File(label="Download PDF"),
+    title="Website Subdirectory to PDF Converter",
+    description="Enter a website URL to convert its subdirectories into a PDF."
+)
+
+if __name__ == "__main__":
+    iface.launch()