Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from urllib.parse import urljoin, urlparse | |
| from weasyprint import HTML | |
| import tempfile | |
| 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) | |
| combined_html = "<html><body>" | |
| for page_url in all_pages: | |
| response = requests.get(page_url) | |
| combined_html += f"<h1>{page_url}</h1>" | |
| combined_html += response.text | |
| combined_html += "</body></html>" | |
| with tempfile.NamedTemporaryFile(delete=False, suffix='.pdf') as tmp: | |
| HTML(string=combined_html).write_pdf(tmp.name) | |
| output_file = tmp.name | |
| 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() |